{"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/6","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":6,"pages_in_order":50,"rows_per_page":100,"rows":[501,600],"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/5","next":"/task/quantization/papers/7","papers":[{"url":"/paper/microscopiq-accelerating-foundational-models","slug":"microscopiq-accelerating-foundational-models","title":"MicroScopiQ: Accelerating Foundational Models through Outlier-Aware Microscaling Quantization","date":"2024-11-08","arxiv_id":"2411.05282","repositories_listed":1,"syntology":{"n":12,"n_ran":6,"n_constructed":0,"n_ran_checked":4,"n_instrument":2,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":1,"phrase":"6 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; 2 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/microscopiq-accelerating-foundational-models#ran","syntology_url":"https://syntology.ai/paper/2411.05282","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.05282"}},"official":{"repos":["georgia-tech-synergy-lab/microscopiq-llm-quantization"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/bitnet-a4-8-4-bit-activations-for-1-bit-llms","slug":"bitnet-a4-8-4-bit-activations-for-1-bit-llms","title":"BitNet a4.8: 4-bit Activations for 1-bit LLMs","date":"2024-11-07","arxiv_id":"2411.04965","repositories_listed":1,"syntology":null},{"url":"/paper/scaling-laws-for-precision","slug":"scaling-laws-for-precision","title":"Scaling Laws for Precision","date":"2024-11-07","arxiv_id":"2411.04330","repositories_listed":1,"syntology":null},{"url":"/paper/an-edge-computing-based-solution-for-real","slug":"an-edge-computing-based-solution-for-real","title":"An Edge Computing-Based Solution for Real-Time Leaf Disease Classification using Thermal Imaging","date":"2024-11-06","arxiv_id":"2411.03835","repositories_listed":1,"syntology":null},{"url":"/paper/privacy-preserving-graph-based-machine","slug":"privacy-preserving-graph-based-machine","title":"Privacy-Preserving Graph-Based Machine Learning with Fully Homomorphic Encryption for Collaborative Anti-Money Laundering","date":"2024-11-05","arxiv_id":"2411.02926","repositories_listed":1,"syntology":{"n":10,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":1,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/privacy-preserving-graph-based-machine#ran","syntology_url":"https://syntology.ai/paper/2411.02926","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.02926"}},"official":{"repos":["fabecode/GraphML-FHE"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/stochastic-monkeys-at-play-random","slug":"stochastic-monkeys-at-play-random","title":"Stochastic Monkeys at Play: Random Augmentations Cheaply Break LLM Safety Alignment","date":"2024-11-05","arxiv_id":"2411.02785","repositories_listed":1,"syntology":null},{"url":"/paper/vq-map-bird-s-eye-view-map-layout-estimation","slug":"vq-map-bird-s-eye-view-map-layout-estimation","title":"VQ-Map: Bird's-Eye-View Map Layout Estimation in Tokenized Discrete Space via Vector Quantization","date":"2024-11-03","arxiv_id":"2411.01618","repositories_listed":1,"syntology":null},{"url":"/paper/conformalized-high-density-quantile","slug":"conformalized-high-density-quantile","title":"Conformalized High-Density Quantile Regression via Dynamic Prototypes-based Probability Density Estimation","date":"2024-11-02","arxiv_id":"2411.01266","repositories_listed":1,"syntology":null},{"url":"/paper/abstracted-shapes-as-tokens-a-generalizable","slug":"abstracted-shapes-as-tokens-a-generalizable","title":"Abstracted Shapes as Tokens -- A Generalizable and Interpretable Model for Time-series Classification","date":"2024-11-01","arxiv_id":"2411.01006","repositories_listed":1,"syntology":{"n":18,"n_ran":12,"n_constructed":0,"n_ran_checked":8,"n_instrument":4,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 4 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/abstracted-shapes-as-tokens-a-generalizable#ran","syntology_url":"https://syntology.ai/paper/2411.01006","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.01006"}},"official":{"repos":["yunshiwen/vqshape"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/bitstack-fine-grained-size-control-for","slug":"bitstack-fine-grained-size-control-for","title":"BitStack: Any-Size Compression of Large Language Models in Variable Memory Environments","date":"2024-10-31","arxiv_id":"2410.23918","repositories_listed":1,"syntology":{"n":10,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":10,"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) · 4 unverified","sample_list":"/paper/bitstack-fine-grained-size-control-for#ran","syntology_url":"https://syntology.ai/paper/2410.23918","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.23918"}},"official":{"repos":["xinghaow99/bitstack"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/data-generation-for-hardware-friendly-post","slug":"data-generation-for-hardware-friendly-post","title":"Data Generation for Hardware-Friendly Post-Training Quantization","date":"2024-10-29","arxiv_id":"2410.22110","repositories_listed":1,"syntology":null},{"url":"/paper/intlora-integral-low-rank-adaptation-of","slug":"intlora-integral-low-rank-adaptation-of","title":"IntLoRA: Integral Low-rank Adaptation of Quantized Diffusion Models","date":"2024-10-29","arxiv_id":"2410.21759","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":1,"n_instrument":6,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":9,"phrase":"7 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; 6 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/intlora-integral-low-rank-adaptation-of#ran","syntology_url":"https://syntology.ai/paper/2410.21759","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.21759"}},"official":{"repos":["csguoh/intlora"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/the-impact-of-inference-acceleration","slug":"the-impact-of-inference-acceleration","title":"The Impact of Inference Acceleration Strategies on Bias of LLMs","date":"2024-10-29","arxiv_id":"2410.22118","repositories_listed":1,"syntology":null},{"url":"/paper/neuzip-memory-efficient-training-and","slug":"neuzip-memory-efficient-training-and","title":"NeuZip: Memory-Efficient Training and Inference with Dynamic Compression of Neural Networks","date":"2024-10-28","arxiv_id":"2410.20650","repositories_listed":1,"syntology":null},{"url":"/paper/unsupervised-panoptic-interpretation-of","slug":"unsupervised-panoptic-interpretation-of","title":"Unsupervised Panoptic Interpretation of Latent Spaces in GANs Using Space-Filling Vector Quantization","date":"2024-10-27","arxiv_id":"2410.20573","repositories_listed":1,"syntology":null},{"url":"/paper/vector-quantization-prompting-for-continual","slug":"vector-quantization-prompting-for-continual","title":"Vector Quantization Prompting for Continual Learning","date":"2024-10-27","arxiv_id":"2410.20444","repositories_listed":1,"syntology":{"n":15,"n_ran":7,"n_constructed":0,"n_ran_checked":5,"n_instrument":2,"n_unverified":8,"n_honours":1,"n_violates":0,"n_no_contract":4,"n_pointer_only":1,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/vector-quantization-prompting-for-continual#ran","syntology_url":"https://syntology.ai/paper/2410.20444","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.20444"}},"official":{"repos":["jiaolifengmi/vq-prompt"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":8,"ran_from_kinds":["official"]}}},{"url":"/paper/dqrm-deep-quantized-recommendation-models","slug":"dqrm-deep-quantized-recommendation-models","title":"DQRM: Deep Quantized Recommendation Models","date":"2024-10-26","arxiv_id":"2410.20046","repositories_listed":1,"syntology":null},{"url":"/paper/coat-compressing-optimizer-states-and","slug":"coat-compressing-optimizer-states-and","title":"COAT: Compressing Optimizer states and Activation for Memory-Efficient FP8 Training","date":"2024-10-25","arxiv_id":"2410.19313","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"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 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) · 1 unverified","sample_list":"/paper/coat-compressing-optimizer-states-and#ran","syntology_url":"https://syntology.ai/paper/2410.19313","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.19313"}},"official":{"repos":["nvlabs/coat"],"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/content-aware-radiance-fields-aligning-model","slug":"content-aware-radiance-fields-aligning-model","title":"Content-Aware Radiance Fields: Aligning Model Complexity with Scene Intricacy Through Learned Bitwidth Quantization","date":"2024-10-25","arxiv_id":"2410.19483","repositories_listed":1,"syntology":null},{"url":"/paper/does-your-llm-truly-unlearn-an-embarrassingly","slug":"does-your-llm-truly-unlearn-an-embarrassingly","title":"Catastrophic Failure of LLM Unlearning via Quantization","date":"2024-10-21","arxiv_id":"2410.16454","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":9,"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/does-your-llm-truly-unlearn-an-embarrassingly#ran","syntology_url":"https://syntology.ai/paper/2410.16454","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.16454"}},"official":{"repos":["zzwjames/failurellmunlearning"],"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/residual-vector-quantization-for-kv-cache","slug":"residual-vector-quantization-for-kv-cache","title":"Residual vector quantization for KV cache compression in large language model","date":"2024-10-21","arxiv_id":"2410.15704","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"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) · 0 unverified","sample_list":"/paper/residual-vector-quantization-for-kv-cache#ran","syntology_url":"https://syntology.ai/paper/2410.15704","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.15704"}},"official":{"repos":["iankur/vqllm"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/evaluating-quantized-large-language-models-1","slug":"evaluating-quantized-large-language-models-1","title":"Evaluating Quantized Large Language Models for Code Generation on Low-Resource Language Benchmarks","date":"2024-10-18","arxiv_id":"2410.14766","repositories_listed":1,"syntology":null},{"url":"/paper/evopress-towards-optimal-dynamic-model","slug":"evopress-towards-optimal-dynamic-model","title":"EvoPress: Towards Optimal Dynamic Model Compression via Evolutionary Search","date":"2024-10-18","arxiv_id":"2410.14649","repositories_listed":1,"syntology":{"n":17,"n_ran":10,"n_constructed":0,"n_ran_checked":5,"n_instrument":5,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"10 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; 5 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/evopress-towards-optimal-dynamic-model#ran","syntology_url":"https://syntology.ai/paper/2410.14649","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.14649"}},"official":{"repos":["ist-daslab/evopress"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/snac-multi-scale-neural-audio-codec","slug":"snac-multi-scale-neural-audio-codec","title":"SNAC: Multi-Scale Neural Audio Codec","date":"2024-10-18","arxiv_id":"2410.14411","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":0,"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/snac-multi-scale-neural-audio-codec#ran","syntology_url":"https://syntology.ai/paper/2410.14411","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.14411"}},"official":{"repos":["hubertsiuzdak/snac"],"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/active-dormant-attention-heads","slug":"active-dormant-attention-heads","title":"Active-Dormant Attention Heads: Mechanistically Demystifying Extreme-Token Phenomena in LLMs","date":"2024-10-17","arxiv_id":"2410.13835","repositories_listed":1,"syntology":{"n":6,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":6,"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) · 5 unverified","sample_list":"/paper/active-dormant-attention-heads#ran","syntology_url":"https://syntology.ai/paper/2410.13835","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.13835"}},"official":{"repos":["guotianyu2000/active-dormant-attention"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/dplm-2-a-multimodal-diffusion-protein","slug":"dplm-2-a-multimodal-diffusion-protein","title":"DPLM-2: A Multimodal Diffusion Protein Language Model","date":"2024-10-17","arxiv_id":"2410.13782","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":1,"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: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/dplm-2-a-multimodal-diffusion-protein#ran","syntology_url":"https://syntology.ai/paper/2410.13782","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.13782"}},"official":null}},{"url":"/paper/learning-graph-quantized-tokenizers-for","slug":"learning-graph-quantized-tokenizers-for","title":"Learning Graph Quantized Tokenizers","date":"2024-10-17","arxiv_id":"2410.13798","repositories_listed":1,"syntology":{"n":13,"n_ran":11,"n_constructed":0,"n_ran_checked":7,"n_instrument":4,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":3,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/learning-graph-quantized-tokenizers-for#ran","syntology_url":"https://syntology.ai/paper/2410.13798","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.13798"}},"official":{"repos":["limei0307/GQT"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/quamba-a-post-training-quantization-recipe","slug":"quamba-a-post-training-quantization-recipe","title":"Quamba: A Post-Training Quantization Recipe for Selective State Space Models","date":"2024-10-17","arxiv_id":"2410.13229","repositories_listed":1,"syntology":{"n":12,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":9,"n_pointer_only":12,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 1 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/quamba-a-post-training-quantization-recipe#ran","syntology_url":"https://syntology.ai/paper/2410.13229","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.13229"}},"official":{"repos":["enyac-group/quamba"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/simlayerkv-a-simple-framework-for-layer-level","slug":"simlayerkv-a-simple-framework-for-layer-level","title":"SimLayerKV: A Simple Framework for Layer-Level KV Cache Reduction","date":"2024-10-17","arxiv_id":"2410.13846","repositories_listed":1,"syntology":{"n":14,"n_ran":12,"n_constructed":0,"n_ran_checked":10,"n_instrument":2,"n_unverified":2,"n_honours":1,"n_violates":1,"n_no_contract":8,"n_pointer_only":14,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 1 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/simlayerkv-a-simple-framework-for-layer-level#ran","syntology_url":"https://syntology.ai/paper/2410.13846","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.13846"}},"official":{"repos":["sail-sg/simlayerkv"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/daq-density-aware-post-training-weight-only","slug":"daq-density-aware-post-training-weight-only","title":"DAQ: Density-Aware Post-Training Weight-Only Quantization For LLMs","date":"2024-10-16","arxiv_id":"2410.12187","repositories_listed":1,"syntology":null},{"url":"/paper/fairglvq-fairness-in-partition-based","slug":"fairglvq-fairness-in-partition-based","title":"FairGLVQ: Fairness in Partition-Based Classification","date":"2024-10-16","arxiv_id":"2410.12452","repositories_listed":1,"syntology":null},{"url":"/paper/efficiera-residual-networks-hardware-friendly","slug":"efficiera-residual-networks-hardware-friendly","title":"Efficiera Residual Networks: Hardware-Friendly Fully Binary Weight with 2-bit Activation Model Achieves Practical ImageNet Accuracy","date":"2024-10-15","arxiv_id":"2410.11553","repositories_listed":1,"syntology":null},{"url":"/paper/error-diffusion-post-training-quantization","slug":"error-diffusion-post-training-quantization","title":"Error Diffusion: Post Training Quantization with Block-Scaled Number Formats for Neural Networks","date":"2024-10-15","arxiv_id":"2410.11203","repositories_listed":1,"syntology":null},{"url":"/paper/latent-action-pretraining-from-videos","slug":"latent-action-pretraining-from-videos","title":"Latent Action Pretraining from Videos","date":"2024-10-15","arxiv_id":"2410.11758","repositories_listed":1,"syntology":{"n":36,"n_ran":30,"n_constructed":0,"n_ran_checked":29,"n_instrument":1,"n_unverified":6,"n_honours":2,"n_violates":2,"n_no_contract":25,"n_pointer_only":4,"phrase":"30 ran (of which 0 constructed an object rather than computing a result; 29 with no instrument failure: 2 honoured, 2 violated, 25 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/latent-action-pretraining-from-videos#ran","syntology_url":"https://syntology.ai/paper/2410.11758","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.11758"}},"official":null}},{"url":"/paper/when-attention-sink-emerges-in-language","slug":"when-attention-sink-emerges-in-language","title":"When Attention Sink Emerges in Language Models: An Empirical View","date":"2024-10-14","arxiv_id":"2410.10781","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/when-attention-sink-emerges-in-language#ran","syntology_url":"https://syntology.ai/paper/2410.10781","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.10781"}},"official":{"repos":["sail-sg/attention-sink"],"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/flatquant-flatness-matters-for-llm","slug":"flatquant-flatness-matters-for-llm","title":"FlatQuant: Flatness Matters for LLM Quantization","date":"2024-10-12","arxiv_id":"2410.09426","repositories_listed":1,"syntology":{"n":22,"n_ran":16,"n_constructed":2,"n_ran_checked":12,"n_instrument":4,"n_unverified":6,"n_honours":3,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"16 ran (of which 2 constructed an object rather than computing a result; 12 with no instrument failure: 3 honoured, 0 violated, 9 with no contract checked; 4 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/flatquant-flatness-matters-for-llm#ran","syntology_url":"https://syntology.ai/paper/2410.09426","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.09426"}},"official":{"repos":["ruikangliu/flatquant"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":2,"n_ran_no_instrument_failure":12,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/slim-one-shot-quantized-sparse-plus-low-rank","slug":"slim-one-shot-quantized-sparse-plus-low-rank","title":"SLiM: One-shot Quantization and Sparsity with Low-rank Approximation for LLM Weight Compression","date":"2024-10-12","arxiv_id":"2410.09615","repositories_listed":1,"syntology":{"n":16,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":8,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/slim-one-shot-quantized-sparse-plus-low-rank#ran","syntology_url":"https://syntology.ai/paper/2410.09615","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.09615"}},"official":{"repos":["mohammad-mozaffari/slim"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":8,"ran_from_kinds":["official"]}}},{"url":"/paper/qeft-quantization-for-efficient-fine-tuning","slug":"qeft-quantization-for-efficient-fine-tuning","title":"QEFT: Quantization for Efficient Fine-Tuning of LLMs","date":"2024-10-11","arxiv_id":"2410.08661","repositories_listed":1,"syntology":null},{"url":"/paper/accept-adaptive-codebook-for-composite-and","slug":"accept-adaptive-codebook-for-composite-and","title":"ACCEPT: Adaptive Codebook for Composite and Efficient Prompt Tuning","date":"2024-10-10","arxiv_id":"2410.12847","repositories_listed":1,"syntology":null},{"url":"/paper/hallo2-long-duration-and-high-resolution","slug":"hallo2-long-duration-and-high-resolution","title":"Hallo2: Long-Duration and High-Resolution Audio-Driven Portrait Image Animation","date":"2024-10-10","arxiv_id":"2410.07718","repositories_listed":1,"syntology":{"n":10,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":1,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/hallo2-long-duration-and-high-resolution#ran","syntology_url":"https://syntology.ai/paper/2410.07718","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.07718"}},"official":{"repos":["fudan-generative-vision/hallo2"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/motionaura-generating-high-quality-and-motion","slug":"motionaura-generating-high-quality-and-motion","title":"MotionAura: Generating High-Quality and Motion Consistent Videos using Discrete Diffusion","date":"2024-10-10","arxiv_id":"2410.07659","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"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) · 0 unverified","sample_list":"/paper/motionaura-generating-high-quality-and-motion#ran","syntology_url":"https://syntology.ai/paper/2410.07659","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.07659"}},"official":{"repos":["CandleLabAI/MotionAura-ICLR-2025"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/q-vlm-post-training-quantization-for-large","slug":"q-vlm-post-training-quantization-for-large","title":"Q-VLM: Post-training Quantization for Large Vision-Language Models","date":"2024-10-10","arxiv_id":"2410.08119","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":2,"n_instrument":4,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/q-vlm-post-training-quantization-for-large#ran","syntology_url":"https://syntology.ai/paper/2410.08119","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.08119"}},"official":{"repos":["changyuanwang17/qvlm"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/jpeg-inspired-deep-learning","slug":"jpeg-inspired-deep-learning","title":"JPEG Inspired Deep Learning","date":"2024-10-09","arxiv_id":"2410.07081","repositories_listed":1,"syntology":null},{"url":"/paper/perceptual-quality-assessment-of-trisoup","slug":"perceptual-quality-assessment-of-trisoup","title":"Perceptual Quality Assessment of Trisoup-Lifting Encoded 3D Point Clouds","date":"2024-10-09","arxiv_id":"2410.06689","repositories_listed":1,"syntology":null},{"url":"/paper/accelerating-error-correction-code","slug":"accelerating-error-correction-code","title":"Accelerating Error Correction Code Transformers","date":"2024-10-08","arxiv_id":"2410.05911","repositories_listed":1,"syntology":null},{"url":"/paper/integrated-encoding-and-quantization-to","slug":"integrated-encoding-and-quantization-to","title":"Integrated Encoding and Quantization to Enhance Quanvolutional Neural Networks","date":"2024-10-08","arxiv_id":"2410.05777","repositories_listed":1,"syntology":null},{"url":"/paper/mc-moe-mixture-compressor-for-mixture-of","slug":"mc-moe-mixture-compressor-for-mixture-of","title":"MC-MoE: Mixture Compressor for Mixture-of-Experts LLMs Gains More","date":"2024-10-08","arxiv_id":"2410.06270","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":9,"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/mc-moe-mixture-compressor-for-mixture-of#ran","syntology_url":"https://syntology.ai/paper/2410.06270","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.06270"}},"official":{"repos":["aaronhuang-778/mc-moe"],"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/qt-dog-quantization-aware-training-for-domain","slug":"qt-dog-quantization-aware-training-for-domain","title":"QT-DoG: Quantization-aware Training for Domain Generalization","date":"2024-10-08","arxiv_id":"2410.06020","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"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) · 0 unverified","sample_list":"/paper/qt-dog-quantization-aware-training-for-domain#ran","syntology_url":"https://syntology.ai/paper/2410.06020","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.06020"}},"official":{"repos":["saqibjaved1/QT-DoG"],"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/prefixquant-static-quantization-beats-dynamic","slug":"prefixquant-static-quantization-beats-dynamic","title":"PrefixQuant: Eliminating Outliers by Prefixed Tokens for Large Language Models Quantization","date":"2024-10-07","arxiv_id":"2410.05265","repositories_listed":1,"syntology":null},{"url":"/paper/arb-llm-alternating-refined-binarizations-for","slug":"arb-llm-alternating-refined-binarizations-for","title":"ARB-LLM: Alternating Refined Binarizations for Large Language Models","date":"2024-10-04","arxiv_id":"2410.03129","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/arb-llm-alternating-refined-binarizations-for#ran","syntology_url":"https://syntology.ai/paper/2410.03129","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.03129"}},"official":{"repos":["zhitengli/arb-llm"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/exaq-exponent-aware-quantization-for-llms","slug":"exaq-exponent-aware-quantization-for-llms","title":"EXAQ: Exponent Aware Quantization For LLMs Acceleration","date":"2024-10-04","arxiv_id":"2410.03185","repositories_listed":1,"syntology":null},{"url":"/paper/mitigating-adversarial-perturbations-for-deep","slug":"mitigating-adversarial-perturbations-for-deep","title":"Mitigating Adversarial Perturbations for Deep Reinforcement Learning via Vector Quantization","date":"2024-10-04","arxiv_id":"2410.03376","repositories_listed":1,"syntology":null},{"url":"/paper/lightweight-diffusion-models-for-resource","slug":"lightweight-diffusion-models-for-resource","title":"Lightweight Diffusion Models for Resource-Constrained Semantic Communication","date":"2024-10-03","arxiv_id":"2410.02491","repositories_listed":1,"syntology":null},{"url":"/paper/sageattention-accurate-8-bit-attention-for","slug":"sageattention-accurate-8-bit-attention-for","title":"SageAttention: Accurate 8-Bit Attention for Plug-and-play Inference Acceleration","date":"2024-10-03","arxiv_id":"2410.02367","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":0,"phrase":"0 ran · 3 unverified","sample_list":"/paper/sageattention-accurate-8-bit-attention-for#ran","syntology_url":"https://syntology.ai/paper/2410.02367","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.02367"}},"official":{"repos":["thu-ml/SageAttention"],"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/a-spark-of-vision-language-intelligence-2","slug":"a-spark-of-vision-language-intelligence-2","title":"A Spark of Vision-Language Intelligence: 2-Dimensional Autoregressive Transformer for Efficient Finegrained Image Generation","date":"2024-10-02","arxiv_id":"2410.01912","repositories_listed":1,"syntology":null},{"url":"/paper/imagefolder-autoregressive-image-generation","slug":"imagefolder-autoregressive-image-generation","title":"ImageFolder: Autoregressive Image Generation with Folded Tokens","date":"2024-10-02","arxiv_id":"2410.01756","repositories_listed":1,"syntology":{"n":5,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":5,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/imagefolder-autoregressive-image-generation#ran","syntology_url":"https://syntology.ai/paper/2410.01756","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.01756"}},"official":{"repos":["lxa9867/imagefolder"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/locret-enhancing-eviction-in-long-context-llm","slug":"locret-enhancing-eviction-in-long-context-llm","title":"Locret: Enhancing Eviction in Long-Context LLM Inference with Trained Retaining Heads on Consumer-Grade Devices","date":"2024-10-02","arxiv_id":"2410.01805","repositories_listed":1,"syntology":null},{"url":"/paper/trainable-pruned-ternary-quantization-for","slug":"trainable-pruned-ternary-quantization-for","title":"Trainable pruned ternary quantization for medical signal classification models","date":"2024-10-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/accelerating-pot-quantization-on-edge-devices","slug":"accelerating-pot-quantization-on-edge-devices","title":"Accelerating PoT Quantization on Edge Devices","date":"2024-09-30","arxiv_id":"2409.20403","repositories_listed":1,"syntology":null},{"url":"/paper/efficient-federated-intrusion-detection-in-5g","slug":"efficient-federated-intrusion-detection-in-5g","title":"Efficient Federated Intrusion Detection in 5G ecosystem using optimized BERT-based model","date":"2024-09-28","arxiv_id":"2409.19390","repositories_listed":1,"syntology":null},{"url":"/paper/digital-and-hybrid-precoding-designs-in","slug":"digital-and-hybrid-precoding-designs-in","title":"Digital and Hybrid Precoding Designs in Massive MIMO with Low-Resolution ADCs","date":"2024-09-26","arxiv_id":"2409.17638","repositories_listed":1,"syntology":null},{"url":"/paper/language-models-as-zero-shot-lossless","slug":"language-models-as-zero-shot-lossless","title":"Language Models as Zero-shot Lossless Gradient Compressors: Towards General Neural Parameter Prior Models","date":"2024-09-26","arxiv_id":"2409.17836","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 2 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/language-models-as-zero-shot-lossless#ran","syntology_url":"https://syntology.ai/paper/2409.17836","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.17836"}},"official":{"repos":["hui-po-wang/LM-GC"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/alignedkv-reducing-memory-access-of-kv-cache","slug":"alignedkv-reducing-memory-access-of-kv-cache","title":"AlignedKV: Reducing Memory Access of KV-Cache with Precision-Aligned Quantization","date":"2024-09-25","arxiv_id":"2409.16546","repositories_listed":1,"syntology":null},{"url":"/paper/bitq-tailoring-block-floating-point-precision","slug":"bitq-tailoring-block-floating-point-precision","title":"BitQ: Tailoring Block Floating Point Precision for Improved DNN Efficiency on Resource-Constrained Devices","date":"2024-09-25","arxiv_id":"2409.17093","repositories_listed":1,"syntology":null},{"url":"/paper/int-flashattention-enabling-flash-attention","slug":"int-flashattention-enabling-flash-attention","title":"INT-FlashAttention: Enabling Flash Attention for INT8 Quantization","date":"2024-09-25","arxiv_id":"2409.16997","repositories_listed":1,"syntology":null},{"url":"/paper/ptq4ris-post-training-quantization-for","slug":"ptq4ris-post-training-quantization-for","title":"PTQ4RIS: Post-Training Quantization for Referring Image Segmentation","date":"2024-09-25","arxiv_id":"2409.17020","repositories_listed":1,"syntology":null},{"url":"/paper/search-for-efficient-large-language-models","slug":"search-for-efficient-large-language-models","title":"Search for Efficient Large Language Models","date":"2024-09-25","arxiv_id":"2409.17372","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/search-for-efficient-large-language-models#ran","syntology_url":"https://syntology.ai/paper/2409.17372","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.17372"}},"official":{"repos":["shawnricecake/search-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/vptq-extreme-low-bit-vector-post-training","slug":"vptq-extreme-low-bit-vector-post-training","title":"VPTQ: Extreme Low-bit Vector Post-Training Quantization for Large Language Models","date":"2024-09-25","arxiv_id":"2409.17066","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_constructed":1,"n_ran_checked":5,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 1 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) · 2 unverified","sample_list":"/paper/vptq-extreme-low-bit-vector-post-training#ran","syntology_url":"https://syntology.ai/paper/2409.17066","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.17066"}},"official":{"repos":["microsoft/vptq"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":1,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/stylesinger-2-zero-shot-singing-voice","slug":"stylesinger-2-zero-shot-singing-voice","title":"TCSinger: Zero-Shot Singing Voice Synthesis with Style Transfer and Multi-Level Style Control","date":"2024-09-24","arxiv_id":"2409.15977","repositories_listed":1,"syntology":null},{"url":"/paper/disentanglement-with-factor-quantized","slug":"disentanglement-with-factor-quantized","title":"Disentanglement with Factor Quantized Variational Autoencoders","date":"2024-09-23","arxiv_id":"2409.14851","repositories_listed":1,"syntology":null},{"url":"/paper/micsim-a-modular-simulator-for-mixed-signal","slug":"micsim-a-modular-simulator-for-mixed-signal","title":"MICSim: A Modular Simulator for Mixed-signal Compute-in-Memory based AI Accelerator","date":"2024-09-23","arxiv_id":"2409.14838","repositories_listed":1,"syntology":null},{"url":"/paper/thinking-in-granularity-dynamic-quantization","slug":"thinking-in-granularity-dynamic-quantization","title":"Thinking in Granularity: Dynamic Quantization for Image Super-Resolution by Intriguing Multi-Granularity Clues","date":"2024-09-22","arxiv_id":"2409.14330","repositories_listed":1,"syntology":null},{"url":"/paper/a-comprehensive-evaluation-of-quantized","slug":"a-comprehensive-evaluation-of-quantized","title":"Exploring the Trade-Offs: Quantization Methods, Task Difficulty, and Model Size in Large Language Models From Edge to Giant","date":"2024-09-17","arxiv_id":"2409.11055","repositories_listed":1,"syntology":null},{"url":"/paper/practical-and-asymptotically-optimal","slug":"practical-and-asymptotically-optimal","title":"Practical and Asymptotically Optimal Quantization of High-Dimensional Vectors in Euclidean Space for Approximate Nearest Neighbor Search","date":"2024-09-16","arxiv_id":"2409.09913","repositories_listed":1,"syntology":null},{"url":"/paper/ditas-quantizing-diffusion-transformers-via","slug":"ditas-quantizing-diffusion-transformers-via","title":"DiTAS: Quantizing Diffusion Transformers via Enhanced Activation Smoothing","date":"2024-09-12","arxiv_id":"2409.07756","repositories_listed":1,"syntology":{"n":19,"n_ran":14,"n_constructed":0,"n_ran_checked":7,"n_instrument":7,"n_unverified":5,"n_honours":4,"n_violates":0,"n_no_contract":3,"n_pointer_only":8,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 4 honoured, 0 violated, 3 with no contract checked; 7 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/ditas-quantizing-diffusion-transformers-via#ran","syntology_url":"https://syntology.ai/paper/2409.07756","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.07756"}},"official":{"repos":["DZY122/DiTAS"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/bigcodec-pushing-the-limits-of-low-bitrate","slug":"bigcodec-pushing-the-limits-of-low-bitrate","title":"BigCodec: Pushing the Limits of Low-Bitrate Neural Speech Codec","date":"2024-09-09","arxiv_id":"2409.05377","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":0,"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/bigcodec-pushing-the-limits-of-low-bitrate#ran","syntology_url":"https://syntology.ai/paper/2409.05377","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.05377"}},"official":{"repos":["Aria-K-Alethia/BigCodec"],"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/bbs-bi-directional-bit-level-sparsity-for","slug":"bbs-bi-directional-bit-level-sparsity-for","title":"BBS: Bi-directional Bit-level Sparsity for Deep Learning Acceleration","date":"2024-09-08","arxiv_id":"2409.05227","repositories_listed":1,"syntology":null},{"url":"/paper/contemporary-model-compression-on-large","slug":"contemporary-model-compression-on-large","title":"Designing Large Foundation Models for Efficient Training and Inference: A Survey","date":"2024-09-03","arxiv_id":"2409.01990","repositories_listed":1,"syntology":null},{"url":"/paper/robust-clustering-on-high-dimensional-data","slug":"robust-clustering-on-high-dimensional-data","title":"Robust Clustering on High-Dimensional Data with Stochastic Quantization","date":"2024-09-03","arxiv_id":"2409.02066","repositories_listed":1,"syntology":null},{"url":"/paper/vq-flow-taming-normalizing-flows-for-multi","slug":"vq-flow-taming-normalizing-flows-for-multi","title":"VQ-Flow: Taming Normalizing Flows for Multi-Class Anomaly Detection via Hierarchical Vector Quantization","date":"2024-09-02","arxiv_id":"2409.00942","repositories_listed":1,"syntology":null},{"url":"/paper/hyper-compression-model-compression-via","slug":"hyper-compression-model-compression-via","title":"Hyper-Compression: Model Compression via Hyperfunction","date":"2024-09-01","arxiv_id":"2409.00592","repositories_listed":1,"syntology":null},{"url":"/paper/tinyagent-function-calling-at-the-edge","slug":"tinyagent-function-calling-at-the-edge","title":"TinyAgent: Function Calling at the Edge","date":"2024-09-01","arxiv_id":"2409.00608","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":0,"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/tinyagent-function-calling-at-the-edge#ran","syntology_url":"https://syntology.ai/paper/2409.00608","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.00608"}},"official":{"repos":["squeezeailab/tinyagent"],"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/codec-does-matter-exploring-the-semantic","slug":"codec-does-matter-exploring-the-semantic","title":"Codec Does Matter: Exploring the Semantic Shortcoming of Codec for Audio Language Model","date":"2024-08-30","arxiv_id":"2408.17175","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/codec-does-matter-exploring-the-semantic#ran","syntology_url":"https://syntology.ai/paper/2408.17175","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.17175"}},"official":{"repos":["zhenye234/xcodec"],"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/identifying-and-clustering-counter","slug":"identifying-and-clustering-counter","title":"Identifying and Clustering Counter Relationships of Team Compositions in PvP Games for Efficient Balance Analysis","date":"2024-08-30","arxiv_id":"2408.17180","repositories_listed":1,"syntology":null},{"url":"/paper/gift-sw-gaussian-noise-injected-fine-tuning","slug":"gift-sw-gaussian-noise-injected-fine-tuning","title":"GIFT-SW: Gaussian noise Injected Fine-Tuning of Salient Weights for LLMs","date":"2024-08-27","arxiv_id":"2408.15300","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":2,"n_pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/gift-sw-gaussian-noise-injected-fine-tuning#ran","syntology_url":"https://syntology.ai/paper/2408.15300","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.15300"}},"official":{"repos":["On-Point-RND/GIFT_SW"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/1-bit-fqt-pushing-the-limit-of-fully","slug":"1-bit-fqt-pushing-the-limit-of-fully","title":"1-Bit FQT: Pushing the Limit of Fully Quantized Training to 1-bit","date":"2024-08-26","arxiv_id":"2408.14267","repositories_listed":1,"syntology":null},{"url":"/paper/on-device-language-models-a-comprehensive","slug":"on-device-language-models-a-comprehensive","title":"On-Device Language Models: A Comprehensive Review","date":"2024-08-26","arxiv_id":"2409.00088","repositories_listed":1,"syntology":null},{"url":"/paper/training-free-activation-sparsity-in-large","slug":"training-free-activation-sparsity-in-large","title":"Training-Free Activation Sparsity in Large Language Models","date":"2024-08-26","arxiv_id":"2408.14690","repositories_listed":1,"syntology":{"n":14,"n_ran":7,"n_constructed":2,"n_ran_checked":2,"n_instrument":5,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"7 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; 5 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/training-free-activation-sparsity-in-large#ran","syntology_url":"https://syntology.ai/paper/2408.14690","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.14690"}},"official":{"repos":["fasterdecoding/teal"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/mobilequant-mobile-friendly-quantization-for","slug":"mobilequant-mobile-friendly-quantization-for","title":"MobileQuant: Mobile-friendly Quantization for On-device Language Models","date":"2024-08-25","arxiv_id":"2408.13933","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 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; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/mobilequant-mobile-friendly-quantization-for#ran","syntology_url":"https://syntology.ai/paper/2408.13933","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.13933"}},"official":{"repos":["saic-fi/mobilequant"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/vision-language-and-large-language-model","slug":"vision-language-and-large-language-model","title":"Vision-Language and Large Language Model Performance in Gastroenterology: GPT, Claude, Llama, Phi, Mistral, Gemma, and Quantized Models","date":"2024-08-25","arxiv_id":"2409.00084","repositories_listed":1,"syntology":null},{"url":"/paper/quantization-free-lossy-image-compression","slug":"quantization-free-lossy-image-compression","title":"Quantization-aware Matrix Factorization for Low Bit Rate Image Compression","date":"2024-08-22","arxiv_id":"2408.12691","repositories_listed":1,"syntology":null},{"url":"/paper/abq-llm-arbitrary-bit-quantized-inference","slug":"abq-llm-arbitrary-bit-quantized-inference","title":"ABQ-LLM: Arbitrary-Bit Quantized Inference Acceleration for Large Language Models","date":"2024-08-16","arxiv_id":"2408.08554","repositories_listed":1,"syntology":null},{"url":"/paper/efficient-autoregressive-audio-modeling-via","slug":"efficient-autoregressive-audio-modeling-via","title":"Efficient Autoregressive Audio Modeling via Next-Scale Prediction","date":"2024-08-16","arxiv_id":"2408.09027","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/efficient-autoregressive-audio-modeling-via#ran","syntology_url":"https://syntology.ai/paper/2408.09027","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.09027"}},"official":{"repos":["qiuk2/aar"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/pqv-mobile-a-combined-pruning-and","slug":"pqv-mobile-a-combined-pruning-and","title":"PQV-Mobile: A Combined Pruning and Quantization Toolkit to Optimize Vision Transformers for Mobile Applications","date":"2024-08-15","arxiv_id":"2408.08437","repositories_listed":1,"syntology":null},{"url":"/paper/advancing-multimodal-large-language-models","slug":"advancing-multimodal-large-language-models","title":"Advancing Multimodal Large Language Models with Quantization-Aware Scale Learning for Efficient Adaptation","date":"2024-08-07","arxiv_id":"2408.03735","repositories_listed":1,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":4,"n_instrument":4,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":2,"n_pointer_only":1,"phrase":"8 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; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/advancing-multimodal-large-language-models#ran","syntology_url":"https://syntology.ai/paper/2408.03735","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.03735"}},"official":{"repos":["xjjxmu/qslaw"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/compact-3d-gaussian-splatting-for-static-and","slug":"compact-3d-gaussian-splatting-for-static-and","title":"Compact 3D Gaussian Splatting for Static and Dynamic Radiance Fields","date":"2024-08-07","arxiv_id":"2408.03822","repositories_listed":1,"syntology":null},{"url":"/paper/2408-02966","slug":"2408-02966","title":"Fast Point Cloud Geometry Compression with Context-based Residual Coding and INR-based Refinement","date":"2024-08-06","arxiv_id":"2408.02966","repositories_listed":1,"syntology":null},{"url":"/paper/2408-02970","slug":"2408-02970","title":"EC-Guide: A Comprehensive E-Commerce Guide for Instruction Tuning and Quantization","date":"2024-08-06","arxiv_id":"2408.02970","repositories_listed":1,"syntology":null},{"url":"/paper/2408-02561","slug":"2408-02561","title":"HQOD: Harmonious Quantization for Object Detection","date":"2024-08-05","arxiv_id":"2408.02561","repositories_listed":1,"syntology":null},{"url":"/paper/a-simple-low-bit-quantization-framework-for","slug":"a-simple-low-bit-quantization-framework-for","title":"A Simple Low-bit Quantization Framework for Video Snapshot Compressive Imaging","date":"2024-07-31","arxiv_id":"2407.21517","repositories_listed":1,"syntology":null}],"record_sha256":"369d6ab8eb5b0b03c763de2430e4a9158781d3a6460cfa7bddad4c8ebc12d11f","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}