{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/quantization/papers/7","list_of":"/task/quantization","task":"Quantization","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":7,"pages_in_order":50,"rows_per_page":100,"rows":[601,700],"of":4925,"counts":{"archive_papers_tagged":4925,"with_a_code_link":1596,"where_syntology_ran_a_sample":515,"not_listed_spam_title":0,"listed":4925,"listed_where_code_ran":515,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":452,"every_run_a_failure_of_syntologys_instrument":63,"listed_with_a_run_with_no_instrument_failure":452,"listed_every_run_a_failure_of_syntologys_instrument":63,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/quantization","prev":"/task/quantization/papers/6","next":"/task/quantization/papers/8","papers":[{"url":"/paper/on-the-perturbed-states-for-transformed-input","slug":"on-the-perturbed-states-for-transformed-input","title":"On the Perturbed States for Transformed Input-robust Reinforcement Learning","date":"2024-07-31","arxiv_id":"2408.00023","repositories_listed":1,"syntology":null},{"url":"/paper/integer-valued-training-and-spike-driven","slug":"integer-valued-training-and-spike-driven","title":"Integer-Valued Training and Spike-Driven Inference Spiking Neural Network for High-performance and Energy-efficient Object Detection","date":"2024-07-30","arxiv_id":"2407.20708","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":4,"n_pointer_only":6,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/integer-valued-training-and-spike-driven#ran","syntology_url":"https://syntology.ai/paper/2407.20708","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.20708"}},"official":{"repos":["biclab/spikeyolo"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/palu-compressing-kv-cache-with-low-rank","slug":"palu-compressing-kv-cache-with-low-rank","title":"Palu: Compressing KV-Cache with Low-Rank Projection","date":"2024-07-30","arxiv_id":"2407.21118","repositories_listed":1,"syntology":null},{"url":"/paper/pruning-large-language-models-with-semi","slug":"pruning-large-language-models-with-semi","title":"Pruning Large Language Models with Semi-Structural Adaptive Sparse Training","date":"2024-07-30","arxiv_id":"2407.20584","repositories_listed":1,"syntology":{"n":8,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/pruning-large-language-models-with-semi#ran","syntology_url":"https://syntology.ai/paper/2407.20584","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.20584"}},"official":{"repos":["thu-ml/adaptive-sparse-trainer"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/temporal-feature-matters-a-framework-for","slug":"temporal-feature-matters-a-framework-for","title":"Temporal Feature Matters: A Framework for Diffusion Model Quantization","date":"2024-07-28","arxiv_id":"2407.19547","repositories_listed":1,"syntology":{"n":14,"n_ran":14,"n_constructed":0,"n_ran_checked":6,"n_instrument":8,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":5,"n_pointer_only":5,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 8 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/temporal-feature-matters-a-framework-for#ran","syntology_url":"https://syntology.ai/paper/2407.19547","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.19547"}},"official":null}},{"url":"/paper/mixed-non-linear-quantization-for-vision","slug":"mixed-non-linear-quantization-for-vision","title":"Mixed Non-linear Quantization for Vision Transformers","date":"2024-07-26","arxiv_id":"2407.18437","repositories_listed":1,"syntology":null},{"url":"/paper/accurate-and-efficient-fine-tuning-of","slug":"accurate-and-efficient-fine-tuning-of","title":"Accurate and Efficient Fine-Tuning of Quantized Large Language Models Through Optimal Balance","date":"2024-07-24","arxiv_id":"2407.17029","repositories_listed":1,"syntology":null},{"url":"/paper/low-dimensional-representation-of-multi","slug":"low-dimensional-representation-of-multi","title":"Low dimensional representation of multi-patient flow cytometry datasets using optimal transport for minimal residual disease detection in leukemia","date":"2024-07-24","arxiv_id":"2407.17329","repositories_listed":1,"syntology":null},{"url":"/paper/differentiable-product-quantization-for-1","slug":"differentiable-product-quantization-for-1","title":"Differentiable Product Quantization for Memory Efficient Camera Relocalization","date":"2024-07-22","arxiv_id":"2407.15540","repositories_listed":1,"syntology":null},{"url":"/paper/a-benchmark-for-gaussian-splatting","slug":"a-benchmark-for-gaussian-splatting","title":"A Benchmark for Gaussian Splatting Compression and Quality Assessment Study","date":"2024-07-19","arxiv_id":"2407.14197","repositories_listed":1,"syntology":null},{"url":"/paper/mixed-precision-neural-networks-on-risc-v","slug":"mixed-precision-neural-networks-on-risc-v","title":"Mixed-precision Neural Networks on RISC-V Cores: ISA extensions for Multi-Pumped Soft SIMD Operations","date":"2024-07-19","arxiv_id":"2407.14274","repositories_listed":1,"syntology":null},{"url":"/paper/adalog-post-training-quantization-for-vision","slug":"adalog-post-training-quantization-for-vision","title":"AdaLog: Post-Training Quantization for Vision Transformers with Adaptive Logarithm Quantizer","date":"2024-07-17","arxiv_id":"2407.12951","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/adalog-post-training-quantization-for-vision#ran","syntology_url":"https://syntology.ai/paper/2407.12951","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.12951"}},"official":{"repos":["GoatWu/AdaLog"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/glare-low-light-image-enhancement-via","slug":"glare-low-light-image-enhancement-via","title":"GLARE: Low Light Image Enhancement via Generative Latent Feature based Codebook Retrieval","date":"2024-07-17","arxiv_id":"2407.12431","repositories_listed":1,"syntology":null},{"url":"/paper/spectra-a-comprehensive-study-of-ternary","slug":"spectra-a-comprehensive-study-of-ternary","title":"Spectra: Surprising Effectiveness of Pretraining Ternary Language Models at Scale","date":"2024-07-17","arxiv_id":"2407.12327","repositories_listed":1,"syntology":null},{"url":"/paper/stox-net-stochastic-processing-of-partial","slug":"stox-net-stochastic-processing-of-partial","title":"StoX-Net: Stochastic Processing of Partial Sums for Efficient In-Memory Computing DNN Accelerators","date":"2024-07-17","arxiv_id":"2407.12378","repositories_listed":1,"syntology":null},{"url":"/paper/exploring-quantization-for-efficient-pre","slug":"exploring-quantization-for-efficient-pre","title":"Exploring Quantization for Efficient Pre-Training of Transformer Language Models","date":"2024-07-16","arxiv_id":"2407.11722","repositories_listed":1,"syntology":null},{"url":"/paper/nitro-d-native-integer-only-training-of-deep","slug":"nitro-d-native-integer-only-training-of-deep","title":"NITRO-D: Native Integer-only Training of Deep Convolutional Neural Networks","date":"2024-07-16","arxiv_id":"2407.11698","repositories_listed":1,"syntology":null},{"url":"/paper/turbo-informativity-driven-acceleration-plug-1","slug":"turbo-informativity-driven-acceleration-plug-1","title":"Turbo: Informativity-Driven Acceleration Plug-In for Vision-Language Large Models","date":"2024-07-16","arxiv_id":"2407.11717","repositories_listed":1,"syntology":null},{"url":"/paper/fast-matrix-multiplications-for-lookup-table","slug":"fast-matrix-multiplications-for-lookup-table","title":"Fast Matrix Multiplications for Lookup Table-Quantized LLMs","date":"2024-07-15","arxiv_id":"2407.10960","repositories_listed":1,"syntology":null},{"url":"/paper/quantized-prompt-for-efficient-generalization","slug":"quantized-prompt-for-efficient-generalization","title":"Quantized Prompt for Efficient Generalization of Vision-Language Models","date":"2024-07-15","arxiv_id":"2407.10704","repositories_listed":1,"syntology":null},{"url":"/paper/seminar-search-enhanced-multi-modal-interest","slug":"seminar-search-enhanced-multi-modal-interest","title":"SEMINAR: Search Enhanced Multi-modal Interest Network and Approximate Retrieval for Lifelong Sequential Recommendation","date":"2024-07-15","arxiv_id":"2407.10714","repositories_listed":1,"syntology":null},{"url":"/paper/semi-supervised-3d-object-detection-with-1","slug":"semi-supervised-3d-object-detection-with-1","title":"Semi-supervised 3D Object Detection with PatchTeacher and PillarMix","date":"2024-07-13","arxiv_id":"2407.09787","repositories_listed":1,"syntology":{"n":9,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/semi-supervised-3d-object-detection-with-1#ran","syntology_url":"https://syntology.ai/paper/2407.09787","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.09787"}},"official":{"repos":["littlepey/ptpm"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/zero-shot-image-compression-with-diffusion","slug":"zero-shot-image-compression-with-diffusion","title":"PSC: Posterior Sampling-Based Compression","date":"2024-07-13","arxiv_id":"2407.09896","repositories_listed":1,"syntology":{"n":17,"n_ran":15,"n_constructed":0,"n_ran_checked":8,"n_instrument":7,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":7,"n_pointer_only":17,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 7 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/zero-shot-image-compression-with-diffusion#ran","syntology_url":"https://syntology.ai/paper/2407.09896","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.09896"}},"official":{"repos":["noamelata/AdaSense"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/on-exact-bit-level-reversible-transformers","slug":"on-exact-bit-level-reversible-transformers","title":"On Exact Bit-level Reversible Transformers Without Changing Architectures","date":"2024-07-12","arxiv_id":"2407.09093","repositories_listed":1,"syntology":null},{"url":"/paper/applying-generative-neural-networks-for-fast","slug":"applying-generative-neural-networks-for-fast","title":"Applying generative neural networks for fast simulations of the ALICE (CERN) experiment","date":"2024-07-10","arxiv_id":"2407.16704","repositories_listed":1,"syntology":null},{"url":"/paper/efficientqat-efficient-quantization-aware","slug":"efficientqat-efficient-quantization-aware","title":"EfficientQAT: Efficient Quantization-Aware Training for Large Language Models","date":"2024-07-10","arxiv_id":"2407.11062","repositories_listed":1,"syntology":{"n":9,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":2,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/efficientqat-efficient-quantization-aware#ran","syntology_url":"https://syntology.ai/paper/2407.11062","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.11062"}},"official":{"repos":["opengvlab/efficientqat"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/rolora-fine-tuning-rotated-outlier-free-llms","slug":"rolora-fine-tuning-rotated-outlier-free-llms","title":"RoLoRA: Fine-tuning Rotated Outlier-free LLMs for Effective Weight-Activation Quantization","date":"2024-07-10","arxiv_id":"2407.08044","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/rolora-fine-tuning-rotated-outlier-free-llms#ran","syntology_url":"https://syntology.ai/paper/2407.08044","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.08044"}},"official":{"repos":["huangowen/rolora"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/dataset-quantization-with-active-learning","slug":"dataset-quantization-with-active-learning","title":"Dataset Quantization with Active Learning based Adaptive Sampling","date":"2024-07-09","arxiv_id":"2407.07268","repositories_listed":1,"syntology":null},{"url":"/paper/clamp-vit-contrastive-data-free-learning-for","slug":"clamp-vit-contrastive-data-free-learning-for","title":"CLAMP-ViT: Contrastive Data-Free Learning for Adaptive Post-Training Quantization of ViTs","date":"2024-07-07","arxiv_id":"2407.05266","repositories_listed":1,"syntology":{"n":6,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/clamp-vit-contrastive-data-free-learning-for#ran","syntology_url":"https://syntology.ai/paper/2407.05266","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.05266"}},"official":{"repos":["georgia-tech-synergy-lab/clamp-vit"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/cosyvoice-a-scalable-multilingual-zero-shot","slug":"cosyvoice-a-scalable-multilingual-zero-shot","title":"CosyVoice: A Scalable Multilingual Zero-shot Text-to-speech Synthesizer based on Supervised Semantic Tokens","date":"2024-07-07","arxiv_id":"2407.05407","repositories_listed":1,"syntology":null},{"url":"/paper/ovsw-overcoming-silent-weights-for-accurate","slug":"ovsw-overcoming-silent-weights-for-accurate","title":"OvSW: Overcoming Silent Weights for Accurate Binary Neural Networks","date":"2024-07-07","arxiv_id":"2407.05257","repositories_listed":1,"syntology":{"n":13,"n_ran":13,"n_constructed":13,"n_ran_checked":13,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":13,"n_pointer_only":13,"phrase":"13 ran (of which 13 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 13 samples that ran constructed an object rather than computing a result","sample_list":"/paper/ovsw-overcoming-silent-weights-for-accurate#ran","syntology_url":"https://syntology.ai/paper/2407.05257","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.05257"}},"official":{"repos":["JingyangXiang/OvSW"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":13,"n_ran_no_instrument_failure":13,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/beyond-perplexity-multi-dimensional-safety","slug":"beyond-perplexity-multi-dimensional-safety","title":"Beyond Perplexity: Multi-dimensional Safety Evaluation of LLM Compression","date":"2024-07-06","arxiv_id":"2407.04965","repositories_listed":1,"syntology":{"n":16,"n_ran":14,"n_constructed":0,"n_ran_checked":14,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":14,"n_pointer_only":16,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/beyond-perplexity-multi-dimensional-safety#ran","syntology_url":"https://syntology.ai/paper/2407.04965","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.04965"}},"official":{"repos":["zhichaoxu-shufe/beyond-perplexity-compression-safety-eval"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":14,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/resource-efficient-speech-quality-prediction","slug":"resource-efficient-speech-quality-prediction","title":"Resource-Efficient Speech Quality Prediction through Quantization Aware Training and Binary Activation Maps","date":"2024-07-05","arxiv_id":"2407.04578","repositories_listed":1,"syntology":null},{"url":"/paper/spikellm-scaling-up-spiking-neural-network-to","slug":"spikellm-scaling-up-spiking-neural-network-to","title":"SpikeLLM: Scaling up Spiking Neural Network to Large Language Models via Saliency-based Spiking","date":"2024-07-05","arxiv_id":"2407.04752","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/spikellm-scaling-up-spiking-neural-network-to#ran","syntology_url":"https://syntology.ai/paper/2407.04752","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.04752"}},"official":null}},{"url":"/paper/qsync-quantization-minimized-synchronous","slug":"qsync-quantization-minimized-synchronous","title":"QSync: Quantization-Minimized Synchronous Distributed Training Across Hybrid Devices","date":"2024-07-02","arxiv_id":"2407.02327","repositories_listed":1,"syntology":null},{"url":"/paper/joint-pruning-and-channel-wise-mixed","slug":"joint-pruning-and-channel-wise-mixed","title":"Joint Pruning and Channel-wise Mixed-Precision Quantization for Efficient Deep Neural Networks","date":"2024-07-01","arxiv_id":"2407.01054","repositories_listed":1,"syntology":null},{"url":"/paper/kv-cache-compression-but-what-must-we-give-in","slug":"kv-cache-compression-but-what-must-we-give-in","title":"KV Cache Compression, But What Must We Give in Return? A Comprehensive Benchmark of Long Context Capable Approaches","date":"2024-07-01","arxiv_id":"2407.01527","repositories_listed":1,"syntology":{"n":13,"n_ran":13,"n_constructed":0,"n_ran_checked":11,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":10,"n_pointer_only":4,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/kv-cache-compression-but-what-must-we-give-in#ran","syntology_url":"https://syntology.ai/paper/2407.01527","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.01527"}},"official":{"repos":["henryzhongsc/longctx_bench"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/llmeasyquant-an-easy-to-use-toolkit-for-llm","slug":"llmeasyquant-an-easy-to-use-toolkit-for-llm","title":"LLMEasyQuant: Scalable Quantization for Parallel and Distributed LLM Inference","date":"2024-06-28","arxiv_id":"2406.19657","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/llmeasyquant-an-easy-to-use-toolkit-for-llm#ran","syntology_url":"https://syntology.ai/paper/2406.19657","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.19657"}},"official":{"repos":["NoakLiu/LLMEasyQuant"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/efficient-course-recommendations-with-t5","slug":"efficient-course-recommendations-with-t5","title":"Efficient course recommendations with T5-based ranking and summarization","date":"2024-06-27","arxiv_id":"2406.19018","repositories_listed":1,"syntology":null},{"url":"/paper/vit-1-58b-mobile-vision-transformers-in-the-1","slug":"vit-1-58b-mobile-vision-transformers-in-the-1","title":"ViT-1.58b: Mobile Vision Transformers in the 1-bit Era","date":"2024-06-26","arxiv_id":"2406.18051","repositories_listed":1,"syntology":{"n":9,"n_ran":9,"n_constructed":0,"n_ran_checked":6,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":5,"n_pointer_only":9,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/vit-1-58b-mobile-vision-transformers-in-the-1#ran","syntology_url":"https://syntology.ai/paper/2406.18051","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.18051"}},"official":{"repos":["dlyuangod/vit-1.58b"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/q-dit-accurate-post-training-quantization-for","slug":"q-dit-accurate-post-training-quantization-for","title":"Q-DiT: Accurate Post-Training Quantization for Diffusion Transformers","date":"2024-06-25","arxiv_id":"2406.17343","repositories_listed":1,"syntology":{"n":19,"n_ran":17,"n_constructed":0,"n_ran_checked":11,"n_instrument":6,"n_unverified":2,"n_honours":4,"n_violates":0,"n_no_contract":7,"n_pointer_only":19,"phrase":"17 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 4 honoured, 0 violated, 7 with no contract checked; 6 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/q-dit-accurate-post-training-quantization-for#ran","syntology_url":"https://syntology.ai/paper/2406.17343","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.17343"}},"official":{"repos":["juanerx/q-dit"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":2,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/t-mac-cpu-renaissance-via-table-lookup-for","slug":"t-mac-cpu-renaissance-via-table-lookup-for","title":"T-MAC: CPU Renaissance via Table Lookup for Low-Bit LLM Deployment on Edge","date":"2024-06-25","arxiv_id":"2407.00088","repositories_listed":1,"syntology":{"n":8,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/t-mac-cpu-renaissance-via-table-lookup-for#ran","syntology_url":"https://syntology.ai/paper/2407.00088","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.00088"}},"official":{"repos":["microsoft/t-mac"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/variable-layer-wise-quantization-a-simple-and","slug":"variable-layer-wise-quantization-a-simple-and","title":"Layer-Wise Quantization: A Pragmatic and Effective Method for Quantizing LLMs Beyond Integer Bit-Levels","date":"2024-06-25","arxiv_id":"2406.17415","repositories_listed":1,"syntology":null},{"url":"/paper/pruning-via-merging-compressing-llms-via","slug":"pruning-via-merging-compressing-llms-via","title":"Pruning via Merging: Compressing LLMs via Manifold Alignment Based Layer Merging","date":"2024-06-24","arxiv_id":"2406.16330","repositories_listed":1,"syntology":{"n":13,"n_ran":10,"n_constructed":0,"n_ran_checked":3,"n_instrument":7,"n_unverified":3,"n_honours":3,"n_violates":0,"n_no_contract":0,"n_pointer_only":13,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 7 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/pruning-via-merging-compressing-llms-via#ran","syntology_url":"https://syntology.ai/paper/2406.16330","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.16330"}},"official":{"repos":["sempraety/pruning-via-merging"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/shadowllm-predictor-based-contextual-sparsity","slug":"shadowllm-predictor-based-contextual-sparsity","title":"ShadowLLM: Predictor-based Contextual Sparsity for Large Language Models","date":"2024-06-24","arxiv_id":"2406.16635","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/shadowllm-predictor-based-contextual-sparsity#ran","syntology_url":"https://syntology.ai/paper/2406.16635","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.16635"}},"official":{"repos":["abdelfattah-lab/shadow_llm"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/edge-llm-enabling-efficient-large-language","slug":"edge-llm-enabling-efficient-large-language","title":"EDGE-LLM: Enabling Efficient Large Language Model Adaptation on Edge Devices via Layerwise Unified Compression and Adaptive Layer Tuning and Voting","date":"2024-06-22","arxiv_id":"2406.15758","repositories_listed":1,"syntology":null},{"url":"/paper/flocora-federated-learning-compression-with","slug":"flocora-federated-learning-compression-with","title":"FLoCoRA: Federated learning compression with low-rank adaptation","date":"2024-06-20","arxiv_id":"2406.14082","repositories_listed":1,"syntology":null},{"url":"/paper/xcomet-lite-bridging-the-gap-between","slug":"xcomet-lite-bridging-the-gap-between","title":"xCOMET-lite: Bridging the Gap Between Efficiency and Quality in Learned MT Evaluation Metrics","date":"2024-06-20","arxiv_id":"2406.14553","repositories_listed":1,"syntology":null},{"url":"/paper/mixture-of-scales-memory-efficient-token","slug":"mixture-of-scales-memory-efficient-token","title":"Mixture of Scales: Memory-Efficient Token-Adaptive Binarization for Large Language Models","date":"2024-06-18","arxiv_id":"2406.12311","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/mixture-of-scales-memory-efficient-token#ran","syntology_url":"https://syntology.ai/paper/2406.12311","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.12311"}},"official":null}},{"url":"/paper/excp-extreme-llm-checkpoint-compression-via","slug":"excp-extreme-llm-checkpoint-compression-via","title":"ExCP: Extreme LLM Checkpoint Compression via Weight-Momentum Joint Shrinking","date":"2024-06-17","arxiv_id":"2406.11257","repositories_listed":1,"syntology":{"n":10,"n_ran":10,"n_constructed":0,"n_ran_checked":7,"n_instrument":3,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/excp-extreme-llm-checkpoint-compression-via#ran","syntology_url":"https://syntology.ai/paper/2406.11257","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.11257"}},"official":{"repos":["gaffey/excp"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/prefixing-attention-sinks-can-mitigate","slug":"prefixing-attention-sinks-can-mitigate","title":"Prefixing Attention Sinks can Mitigate Activation Outliers for Large Language Model Quantization","date":"2024-06-17","arxiv_id":"2406.12016","repositories_listed":1,"syntology":null},{"url":"/paper/scaling-the-codebook-size-of-vqgan-to-100000","slug":"scaling-the-codebook-size-of-vqgan-to-100000","title":"Scaling the Codebook Size of VQGAN to 100,000 with a Utilization Rate of 99%","date":"2024-06-17","arxiv_id":"2406.11837","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/scaling-the-codebook-size-of-vqgan-to-100000#ran","syntology_url":"https://syntology.ai/paper/2406.11837","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.11837"}},"official":{"repos":["zh460045050/vqgan-lc"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/optimization-of-armv9-architecture-general","slug":"optimization-of-armv9-architecture-general","title":"Optimization of Armv9 architecture general large language model inference performance based on Llama.cpp","date":"2024-06-16","arxiv_id":"2406.10816","repositories_listed":1,"syntology":null},{"url":"/paper/evaluating-the-generalization-ability-of-1","slug":"evaluating-the-generalization-ability-of-1","title":"Evaluating the Generalization Ability of Quantized LLMs: Benchmark, Analysis, and Toolbox","date":"2024-06-15","arxiv_id":"2406.12928","repositories_listed":1,"syntology":{"n":12,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":8,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":12,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/evaluating-the-generalization-ability-of-1#ran","syntology_url":"https://syntology.ai/paper/2406.12928","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.12928"}},"official":{"repos":["tsingmaoai/mi-optimize"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":8,"ran_from_kinds":["official"]}}},{"url":"/paper/qqq-quality-quattuor-bit-quantization-for","slug":"qqq-quality-quattuor-bit-quantization-for","title":"QQQ: Quality Quattuor-Bit Quantization for Large Language Models","date":"2024-06-14","arxiv_id":"2406.09904","repositories_listed":1,"syntology":null},{"url":"/paper/delta-come-training-free-delta-compression","slug":"delta-come-training-free-delta-compression","title":"Delta-CoMe: Training-Free Delta-Compression with Mixed-Precision for Large Language Models","date":"2024-06-13","arxiv_id":"2406.08903","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":1,"n_ran_checked":1,"n_instrument":4,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"5 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/delta-come-training-free-delta-compression#ran","syntology_url":"https://syntology.ai/paper/2406.08903","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.08903"}},"official":{"repos":["thunlp/delta-come"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/q-s5-towards-quantized-state-space-models","slug":"q-s5-towards-quantized-state-space-models","title":"Q-S5: Towards Quantized State Space Models","date":"2024-06-13","arxiv_id":"2406.09477","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/q-s5-towards-quantized-state-space-models#ran","syntology_url":"https://syntology.ai/paper/2406.09477","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.09477"}},"official":{"repos":["kmheckel/q-S5"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/examining-post-training-quantization-for","slug":"examining-post-training-quantization-for","title":"Examining Post-Training Quantization for Mixture-of-Experts: A Benchmark","date":"2024-06-12","arxiv_id":"2406.08155","repositories_listed":1,"syntology":{"n":6,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/examining-post-training-quantization-for#ran","syntology_url":"https://syntology.ai/paper/2406.08155","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.08155"}},"official":{"repos":["unites-lab/moe-quantization"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/2dquant-low-bit-post-training-quantization","slug":"2dquant-low-bit-post-training-quantization","title":"2DQuant: Low-bit Post-Training Quantization for Image Super-Resolution","date":"2024-06-10","arxiv_id":"2406.06649","repositories_listed":1,"syntology":null},{"url":"/paper/low-rank-quantization-aware-training-for-llms","slug":"low-rank-quantization-aware-training-for-llms","title":"Low-Rank Quantization-Aware Training for LLMs","date":"2024-06-10","arxiv_id":"2406.06385","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/low-rank-quantization-aware-training-for-llms#ran","syntology_url":"https://syntology.ai/paper/2406.06385","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.06385"}},"official":{"repos":["qualcomm-ai-research/lr-qat"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/from-analog-to-digital-multi-order-digital","slug":"from-analog-to-digital-multi-order-digital","title":"From Analog to Digital: Multi-Order Digital Joint Coding-Modulation for Semantic Communication","date":"2024-06-08","arxiv_id":"2406.05437","repositories_listed":1,"syntology":null},{"url":"/paper/winner-takes-all-learners-are-geometry-aware","slug":"winner-takes-all-learners-are-geometry-aware","title":"Winner-takes-all learners are geometry-aware conditional density estimators","date":"2024-06-07","arxiv_id":"2406.04706","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/winner-takes-all-learners-are-geometry-aware#ran","syntology_url":"https://syntology.ai/paper/2406.04706","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.04706"}},"official":{"repos":["Victorletzelter/VoronoiWTA"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/bitsfusion-1-99-bits-weight-quantization-of","slug":"bitsfusion-1-99-bits-weight-quantization-of","title":"BitsFusion: 1.99 bits Weight Quantization of Diffusion Model","date":"2024-06-06","arxiv_id":"2406.04333","repositories_listed":1,"syntology":null},{"url":"/paper/real-time-spacecraft-pose-estimation-using","slug":"real-time-spacecraft-pose-estimation-using","title":"Real-Time Spacecraft Pose Estimation Using Mixed-Precision Quantized Neural Network on COTS Reconfigurable MPSoC","date":"2024-06-06","arxiv_id":"2407.06170","repositories_listed":1,"syntology":null},{"url":"/paper/fine-grained-causal-dynamics-learning-with","slug":"fine-grained-causal-dynamics-learning-with","title":"Fine-Grained Causal Dynamics Learning with Quantization for Improving Robustness in Reinforcement Learning","date":"2024-06-05","arxiv_id":"2406.03234","repositories_listed":1,"syntology":{"n":11,"n_ran":6,"n_constructed":0,"n_ran_checked":2,"n_instrument":4,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/fine-grained-causal-dynamics-learning-with#ran","syntology_url":"https://syntology.ai/paper/2406.03234","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.03234"}},"official":{"repos":["iwhwang/Fine-Grained-Causal-RL"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/qjl-1-bit-quantized-jl-transform-for-kv-cache","slug":"qjl-1-bit-quantized-jl-transform-for-kv-cache","title":"QJL: 1-Bit Quantized JL Transform for KV Cache Quantization with Zero Overhead","date":"2024-06-05","arxiv_id":"2406.03482","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":3,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/qjl-1-bit-quantized-jl-transform-for-kv-cache#ran","syntology_url":"https://syntology.ai/paper/2406.03482","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.03482"}},"official":{"repos":["amirzandieh/qjl"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/sltrain-a-sparse-plus-low-rank-approach-for","slug":"sltrain-a-sparse-plus-low-rank-approach-for","title":"SLTrain: a sparse plus low-rank approach for parameter and memory efficient pretraining","date":"2024-06-04","arxiv_id":"2406.02214","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":2,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/sltrain-a-sparse-plus-low-rank-approach-for#ran","syntology_url":"https://syntology.ai/paper/2406.02214","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.02214"}},"official":{"repos":["andyjm3/SLTrain"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/vidit-q-efficient-and-accurate-quantization","slug":"vidit-q-efficient-and-accurate-quantization","title":"ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation","date":"2024-06-04","arxiv_id":"2406.02540","repositories_listed":1,"syntology":{"n":10,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":7,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":10,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/vidit-q-efficient-and-accurate-quantization#ran","syntology_url":"https://syntology.ai/paper/2406.02540","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.02540"}},"official":{"repos":["a-suozhang/vidit-q"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/capsule-enhanced-variational-autoencoder-for","slug":"capsule-enhanced-variational-autoencoder-for","title":"CE-VAE: Capsule Enhanced Variational AutoEncoder for Underwater Image Enhancement","date":"2024-06-03","arxiv_id":"2406.01294","repositories_listed":1,"syntology":null},{"url":"/paper/rotation-and-permutation-for-advanced-outlier","slug":"rotation-and-permutation-for-advanced-outlier","title":"DuQuant: Distributing Outliers via Dual Transformation Makes Stronger Quantized LLMs","date":"2024-06-03","arxiv_id":"2406.01721","repositories_listed":1,"syntology":{"n":13,"n_ran":10,"n_constructed":0,"n_ran_checked":6,"n_instrument":4,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":4,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/rotation-and-permutation-for-advanced-outlier#ran","syntology_url":"https://syntology.ai/paper/2406.01721","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.01721"}},"official":{"repos":["hsu1023/duquant"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/magr-weight-magnitude-reduction-for-enhancing","slug":"magr-weight-magnitude-reduction-for-enhancing","title":"MagR: Weight Magnitude Reduction for Enhancing Post-Training Quantization","date":"2024-06-02","arxiv_id":"2406.00800","repositories_listed":1,"syntology":{"n":12,"n_ran":8,"n_constructed":0,"n_ran_checked":1,"n_instrument":7,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 7 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/magr-weight-magnitude-reduction-for-enhancing#ran","syntology_url":"https://syntology.ai/paper/2406.00800","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.00800"}},"official":{"repos":["aozhongzhang/magr"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/privacy-aware-randomized-quantization-via","slug":"privacy-aware-randomized-quantization-via","title":"Privacy-Aware Randomized Quantization via Linear Programming","date":"2024-06-01","arxiv_id":"2406.02599","repositories_listed":1,"syntology":null},{"url":"/paper/cv-vae-a-compatible-video-vae-for-latent","slug":"cv-vae-a-compatible-video-vae-for-latent","title":"CV-VAE: A Compatible Video VAE for Latent Generative Video Models","date":"2024-05-30","arxiv_id":"2405.20279","repositories_listed":1,"syntology":{"n":8,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":2,"n_no_contract":1,"n_pointer_only":8,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 2 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/cv-vae-a-compatible-video-vae-for-latent#ran","syntology_url":"https://syntology.ai/paper/2405.20279","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.20279"}},"official":{"repos":["ailab-cvc/cv-vae"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/p-2-vit-power-of-two-post-training","slug":"p-2-vit-power-of-two-post-training","title":"P$^2$-ViT: Power-of-Two Post-Training Quantization and Acceleration for Fully Quantized Vision Transformer","date":"2024-05-30","arxiv_id":"2405.19915","repositories_listed":1,"syntology":null},{"url":"/paper/compressing-large-language-models-using-low","slug":"compressing-large-language-models-using-low","title":"Compressing Large Language Models using Low Rank and Low Precision Decomposition","date":"2024-05-29","arxiv_id":"2405.18886","repositories_listed":1,"syntology":null},{"url":"/paper/4-bit-shampoo-for-memory-efficient-network","slug":"4-bit-shampoo-for-memory-efficient-network","title":"4-bit Shampoo for Memory-Efficient Network Training","date":"2024-05-28","arxiv_id":"2405.18144","repositories_listed":1,"syntology":{"n":15,"n_ran":13,"n_constructed":0,"n_ran_checked":13,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":13,"n_pointer_only":15,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/4-bit-shampoo-for-memory-efficient-network#ran","syntology_url":"https://syntology.ai/paper/2405.18144","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.18144"}},"official":{"repos":["sike-wang/low-bit-shampoo"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/exploiting-llm-quantization","slug":"exploiting-llm-quantization","title":"Exploiting LLM Quantization","date":"2024-05-28","arxiv_id":"2405.18137","repositories_listed":1,"syntology":null},{"url":"/paper/slmrec-empowering-small-language-models-for","slug":"slmrec-empowering-small-language-models-for","title":"SLMRec: Distilling Large Language Models into Small for Sequential Recommendation","date":"2024-05-28","arxiv_id":"2405.17890","repositories_listed":1,"syntology":{"n":3,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"0 ran · 3 unverified","sample_list":"/paper/slmrec-empowering-small-language-models-for#ran","syntology_url":"https://syntology.ai/paper/2405.17890","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.17890"}},"official":{"repos":["wujiangxu/slmrec"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":[]}}},{"url":"/paper/loqt-low-rank-adapters-for-quantized-training","slug":"loqt-low-rank-adapters-for-quantized-training","title":"LoQT: Low-Rank Adapters for Quantized Pretraining","date":"2024-05-26","arxiv_id":"2405.16528","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/loqt-low-rank-adapters-for-quantized-training#ran","syntology_url":"https://syntology.ai/paper/2405.16528","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.16528"}},"official":{"repos":["sebulo/LoQT"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/structure-aware-semantic-node-identifiers-for","slug":"structure-aware-semantic-node-identifiers-for","title":"Node Identifiers: Compact, Discrete Representations for Efficient Graph Learning","date":"2024-05-26","arxiv_id":"2405.16435","repositories_listed":1,"syntology":{"n":13,"n_ran":10,"n_constructed":0,"n_ran_checked":9,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":2,"n_no_contract":7,"n_pointer_only":3,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 2 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/structure-aware-semantic-node-identifiers-for#ran","syntology_url":"https://syntology.ai/paper/2405.16435","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.16435"}},"official":{"repos":["LUOyk1999/NodeID"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/m-3-gpt-an-advanced-multimodal-multitask","slug":"m-3-gpt-an-advanced-multimodal-multitask","title":"M$^3$GPT: An Advanced Multimodal, Multitask Framework for Motion Comprehension and Generation","date":"2024-05-25","arxiv_id":"2405.16273","repositories_listed":1,"syntology":{"n":25,"n_ran":17,"n_constructed":4,"n_ran_checked":15,"n_instrument":2,"n_unverified":8,"n_honours":0,"n_violates":0,"n_no_contract":15,"n_pointer_only":25,"phrase":"17 ran (of which 4 constructed an object rather than computing a result; 15 with no instrument failure: 0 honoured, 0 violated, 15 with no contract checked; 2 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/m-3-gpt-an-advanced-multimodal-multitask#ran","syntology_url":"https://syntology.ai/paper/2405.16273","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.16273"}},"official":{"repos":["luomingshuang/m3gpt"],"state":"official (archive's flag): 17 ran","n_ran":17,"n_constructed":4,"n_ran_no_instrument_failure":15,"n_unverified":8,"ran_from_kinds":["official"]}}},{"url":"/paper/ptq4dit-post-training-quantization-for","slug":"ptq4dit-post-training-quantization-for","title":"PTQ4DiT: Post-training Quantization for Diffusion Transformers","date":"2024-05-25","arxiv_id":"2405.16005","repositories_listed":1,"syntology":{"n":21,"n_ran":9,"n_constructed":6,"n_ran_checked":7,"n_instrument":2,"n_unverified":12,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":21,"phrase":"9 ran (of which 6 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 12 unverified","sample_list":"/paper/ptq4dit-post-training-quantization-for#ran","syntology_url":"https://syntology.ai/paper/2405.16005","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.16005"}},"official":{"repos":["adreamwu/ptq4dit"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":6,"n_ran_no_instrument_failure":7,"n_unverified":12,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/mitigating-quantization-errors-due-to","slug":"mitigating-quantization-errors-due-to","title":"Mitigating Quantization Errors Due to Activation Spikes in GLU-Based LLMs","date":"2024-05-23","arxiv_id":"2405.14428","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/mitigating-quantization-errors-due-to#ran","syntology_url":"https://syntology.ai/paper/2405.14428","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.14428"}},"official":{"repos":["onnoo/activation-spikes"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/pv-tuning-beyond-straight-through-estimation","slug":"pv-tuning-beyond-straight-through-estimation","title":"PV-Tuning: Beyond Straight-Through Estimation for Extreme LLM Compression","date":"2024-05-23","arxiv_id":"2405.14852","repositories_listed":1,"syntology":{"n":10,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/pv-tuning-beyond-straight-through-estimation#ran","syntology_url":"https://syntology.ai/paper/2405.14852","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.14852"}},"official":{"repos":["vahe1994/aqlm"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/raq-vae-rate-adaptive-vector-quantized","slug":"raq-vae-rate-adaptive-vector-quantized","title":"Rate-Adaptive Quantization: A Multi-Rate Codebook Adaptation for Vector Quantization-based Generative Models","date":"2024-05-23","arxiv_id":"2405.14222","repositories_listed":1,"syntology":null},{"url":"/paper/slim-llm-salience-driven-mixed-precision","slug":"slim-llm-salience-driven-mixed-precision","title":"SliM-LLM: Salience-Driven Mixed-Precision Quantization for Large Language Models","date":"2024-05-23","arxiv_id":"2405.14917","repositories_listed":1,"syntology":{"n":13,"n_ran":8,"n_constructed":0,"n_ran_checked":5,"n_instrument":3,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":13,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/slim-llm-salience-driven-mixed-precision#ran","syntology_url":"https://syntology.ai/paper/2405.14917","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.14917"}},"official":{"repos":["Aaronhuang-778/SliM-LLM"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/terdit-ternary-diffusion-models-with","slug":"terdit-ternary-diffusion-models-with","title":"TerDiT: Ternary Diffusion Models with Transformers","date":"2024-05-23","arxiv_id":"2405.14854","repositories_listed":1,"syntology":{"n":12,"n_ran":10,"n_constructed":0,"n_ran_checked":5,"n_instrument":5,"n_unverified":2,"n_honours":3,"n_violates":0,"n_no_contract":2,"n_pointer_only":6,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 3 honoured, 0 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/terdit-ternary-diffusion-models-with#ran","syntology_url":"https://syntology.ai/paper/2405.14854","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.14854"}},"official":{"repos":["Lucky-Lance/TerDiT"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/zipcache-accurate-and-efficient-kv-cache","slug":"zipcache-accurate-and-efficient-kv-cache","title":"ZipCache: Accurate and Efficient KV Cache Quantization with Salient Token Identification","date":"2024-05-23","arxiv_id":"2405.14256","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/zipcache-accurate-and-efficient-kv-cache#ran","syntology_url":"https://syntology.ai/paper/2405.14256","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.14256"}},"official":null}},{"url":"/paper/clipped-uniform-quantizers-for-communication","slug":"clipped-uniform-quantizers-for-communication","title":"Communication-Efficient Federated Learning via Clipped Uniform Quantization","date":"2024-05-22","arxiv_id":"2405.13365","repositories_listed":1,"syntology":null},{"url":"/paper/nearest-is-not-dearest-towards-practical","slug":"nearest-is-not-dearest-towards-practical","title":"Nearest is Not Dearest: Towards Practical Defense against Quantization-conditioned Backdoor Attacks","date":"2024-05-21","arxiv_id":"2405.12725","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/nearest-is-not-dearest-towards-practical#ran","syntology_url":"https://syntology.ai/paper/2405.12725","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.12725"}},"official":{"repos":["antigonerandy/quantbackdoor_efrap"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/rabitq-quantizing-high-dimensional-vectors","slug":"rabitq-quantizing-high-dimensional-vectors","title":"RaBitQ: Quantizing High-Dimensional Vectors with a Theoretical Error Bound for Approximate Nearest Neighbor Search","date":"2024-05-21","arxiv_id":"2405.12497","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/rabitq-quantizing-high-dimensional-vectors#ran","syntology_url":"https://syntology.ai/paper/2405.12497","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.12497"}},"official":{"repos":["gaoj0017/RaBitQ"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/unlocking-data-free-low-bit-quantization-with","slug":"unlocking-data-free-low-bit-quantization-with","title":"Unlocking Data-free Low-bit Quantization with Matrix Decomposition for KV Cache Compression","date":"2024-05-21","arxiv_id":"2405.12591","repositories_listed":1,"syntology":{"n":10,"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":10,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/unlocking-data-free-low-bit-quantization-with#ran","syntology_url":"https://syntology.ai/paper/2405.12591","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.12591"}},"official":{"repos":["lpyhdzx/DecoQuant_code"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/imp-highly-capable-large-multimodal-models","slug":"imp-highly-capable-large-multimodal-models","title":"Imp: Highly Capable Large Multimodal Models for Mobile Devices","date":"2024-05-20","arxiv_id":"2405.12107","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":4,"n_instrument":3,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":2,"n_pointer_only":1,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 1 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/imp-highly-capable-large-multimodal-models#ran","syntology_url":"https://syntology.ai/paper/2405.12107","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.12107"}},"official":{"repos":["milvlg/imp"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/deep-learning-enabled-one-bit-doa-estimation","slug":"deep-learning-enabled-one-bit-doa-estimation","title":"Deep Learning-Enabled One-Bit DoA Estimation","date":"2024-05-15","arxiv_id":"2405.09712","repositories_listed":1,"syntology":null},{"url":"/paper/feature-based-federated-transfer-learning","slug":"feature-based-federated-transfer-learning","title":"Feature-based Federated Transfer Learning: Communication Efficiency, Robustness and Privacy","date":"2024-05-15","arxiv_id":"2405.09014","repositories_listed":1,"syntology":null},{"url":"/paper/properties-that-allow-or-prohibit","slug":"properties-that-allow-or-prohibit","title":"Properties that allow or prohibit transferability of adversarial attacks among quantized networks","date":"2024-05-15","arxiv_id":"2405.09598","repositories_listed":1,"syntology":null},{"url":"/paper/ditto-quantization-aware-secure-inference-of","slug":"ditto-quantization-aware-secure-inference-of","title":"Ditto: Quantization-aware Secure Inference of Transformers upon MPC","date":"2024-05-09","arxiv_id":"2405.05525","repositories_listed":1,"syntology":null},{"url":"/paper/llm-qbench-a-benchmark-towards-the-best","slug":"llm-qbench-a-benchmark-towards-the-best","title":"LLMC: Benchmarking Large Language Model Quantization with a Versatile Compression Toolkit","date":"2024-05-09","arxiv_id":"2405.06001","repositories_listed":1,"syntology":{"n":2,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 2 unverified","sample_list":"/paper/llm-qbench-a-benchmark-towards-the-best#ran","syntology_url":"https://syntology.ai/paper/2405.06001","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.06001"}},"official":{"repos":["modeltc/llmc"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]}}},{"url":"/paper/learning-from-students-applying-t","slug":"learning-from-students-applying-t","title":"Learning from Students: Applying t-Distributions to Explore Accurate and Efficient Formats for LLMs","date":"2024-05-06","arxiv_id":"2405.03103","repositories_listed":1,"syntology":null},{"url":"/paper/ptq4sam-post-training-quantization-for","slug":"ptq4sam-post-training-quantization-for","title":"PTQ4SAM: Post-Training Quantization for Segment Anything","date":"2024-05-06","arxiv_id":"2405.03144","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":5,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":9,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/ptq4sam-post-training-quantization-for#ran","syntology_url":"https://syntology.ai/paper/2405.03144","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.03144"}},"official":{"repos":["chengtao-lv/ptq4sam"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}}],"record_sha256":"b03c8555187af8ef454440d943776bd2908d0bc55521202e030e80807d8ee8ba","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}