{"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/4","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":4,"pages_in_order":50,"rows_per_page":100,"rows":[301,400],"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/3","next":"/task/quantization/papers/5","papers":[{"url":"/paper/cross-modal-epileptic-signal-harmonization","slug":"cross-modal-epileptic-signal-harmonization","title":"Cross-Modal Epileptic Signal Harmonization: Frequency Domain Mapping Quantization for Pre-training a Unified Neurophysiological Transformer","date":"2025-06-20","arxiv_id":"2506.17068","repositories_listed":1,"syntology":null},{"url":"/paper/modulated-diffusion-accelerating-generative","slug":"modulated-diffusion-accelerating-generative","title":"Modulated Diffusion: Accelerating Generative Modeling with Modulated Quantization","date":"2025-06-18","arxiv_id":"2506.22463","repositories_listed":1,"syntology":{"n":32,"n_ran":16,"n_constructed":5,"n_ran_checked":10,"n_instrument":6,"n_unverified":16,"n_honours":1,"n_violates":0,"n_no_contract":9,"n_pointer_only":32,"phrase":"16 ran (of which 5 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 0 violated, 9 with no contract checked; 6 where Syntology's instrument failed) · 16 unverified","sample_list":"/paper/modulated-diffusion-accelerating-generative#ran","syntology_url":"https://syntology.ai/paper/2506.22463","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.22463"}},"official":{"repos":["WeizhiGao/MoDiff"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":5,"n_ran_no_instrument_failure":10,"n_unverified":16,"ran_from_kinds":["official"]}}},{"url":"/paper/detrpose-real-time-end-to-end-transformer","slug":"detrpose-real-time-end-to-end-transformer","title":"DETRPose: Real-time end-to-end transformer model for multi-person pose estimation","date":"2025-06-16","arxiv_id":"2506.13027","repositories_listed":1,"syntology":null},{"url":"/paper/fima-q-post-training-quantization-for-vision-1","slug":"fima-q-post-training-quantization-for-vision-1","title":"FIMA-Q: Post-Training Quantization for Vision Transformers by Fisher Information Matrix Approximation","date":"2025-06-13","arxiv_id":"2506.11543","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/fima-q-post-training-quantization-for-vision-1#ran","syntology_url":"https://syntology.ai/paper/2506.11543","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.11543"}},"official":{"repos":["shihewang/fima-q"],"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/bitvla-1-bit-vision-language-action-models","slug":"bitvla-1-bit-vision-language-action-models","title":"BitVLA: 1-bit Vision-Language-Action Models for Robotics Manipulation","date":"2025-06-09","arxiv_id":"2506.07530","repositories_listed":1,"syntology":null},{"url":"/paper/evaluating-large-language-models-on-the-frame","slug":"evaluating-large-language-models-on-the-frame","title":"Evaluating Large Language Models on the Frame and Symbol Grounding Problems: A Zero-shot Benchmark","date":"2025-06-09","arxiv_id":"2506.07896","repositories_listed":1,"syntology":null},{"url":"/paper/highly-compressed-tokenizer-can-generate","slug":"highly-compressed-tokenizer-can-generate","title":"Highly Compressed Tokenizer Can Generate Without Training","date":"2025-06-09","arxiv_id":"2506.08257","repositories_listed":1,"syntology":null},{"url":"/paper/edgeprofiler-a-fast-profiling-framework-for","slug":"edgeprofiler-a-fast-profiling-framework-for","title":"EdgeProfiler: A Fast Profiling Framework for Lightweight LLMs on Edge Using Analytical Model","date":"2025-06-06","arxiv_id":"2506.09061","repositories_listed":1,"syntology":null},{"url":"/paper/recgpt-a-foundation-model-for-sequential","slug":"recgpt-a-foundation-model-for-sequential","title":"RecGPT: A Foundation Model for Sequential Recommendation","date":"2025-06-06","arxiv_id":"2506.06270","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/recgpt-a-foundation-model-for-sequential#ran","syntology_url":"https://syntology.ai/paper/2506.06270","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.06270"}},"official":{"repos":["hkuds/recgpt"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/star-learning-diverse-robot-skill","slug":"star-learning-diverse-robot-skill","title":"STAR: Learning Diverse Robot Skill Abstractions through Rotation-Augmented Vector Quantization","date":"2025-06-04","arxiv_id":"2506.03863","repositories_listed":1,"syntology":null},{"url":"/paper/flexible-mixed-precision-quantization-for","slug":"flexible-mixed-precision-quantization-for","title":"Flexible Mixed Precision Quantization for Learned Image Compression","date":"2025-06-02","arxiv_id":"2506.01221","repositories_listed":1,"syntology":null},{"url":"/paper/parameter-efficient-fine-tuning-llama-3-1-for","slug":"parameter-efficient-fine-tuning-llama-3-1-for","title":"Parameter Efficient Fine Tuning Llama 3.1 for Answering Arabic Legal Questions: A Case Study on Jordanian Laws","date":"2025-06-02","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/structured-pruning-and-quantization-for","slug":"structured-pruning-and-quantization-for","title":"Structured Pruning and Quantization for Learned Image Compression","date":"2025-06-02","arxiv_id":"2506.01229","repositories_listed":1,"syntology":null},{"url":"/paper/legaleval-q-a-new-benchmark-for-the-quality","slug":"legaleval-q-a-new-benchmark-for-the-quality","title":"LegalEval-Q: A New Benchmark for The Quality Evaluation of LLM-Generated Legal Text","date":"2025-05-30","arxiv_id":"2505.24826","repositories_listed":1,"syntology":null},{"url":"/paper/merge-friendly-post-training-quantization-for","slug":"merge-friendly-post-training-quantization-for","title":"Merge-Friendly Post-Training Quantization for Multi-Target Domain Adaptation","date":"2025-05-29","arxiv_id":"2505.23651","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":4,"phrase":"5 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; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/merge-friendly-post-training-quantization-for#ran","syntology_url":"https://syntology.ai/paper/2505.23651","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.23651"}},"official":{"repos":["ewsn1593/hdrq"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/climate-finance-bench","slug":"climate-finance-bench","title":"Climate Finance Bench","date":"2025-05-28","arxiv_id":"2505.22752","repositories_listed":1,"syntology":null},{"url":"/paper/speculative-decoding-meets-quantization","slug":"speculative-decoding-meets-quantization","title":"Speculative Decoding Meets Quantization: Compatibility Evaluation and Hierarchical Framework Design","date":"2025-05-28","arxiv_id":"2505.22179","repositories_listed":1,"syntology":null},{"url":"/paper/can-compressed-llms-truly-act-an-empirical","slug":"can-compressed-llms-truly-act-an-empirical","title":"Can Compressed LLMs Truly Act? An Empirical Evaluation of Agentic Capabilities in LLM Compression","date":"2025-05-26","arxiv_id":"2505.19433","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_honours":2,"n_violates":1,"n_no_contract":0,"n_pointer_only":2,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/can-compressed-llms-truly-act-an-empirical#ran","syntology_url":"https://syntology.ai/paper/2505.19433","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.19433"}},"official":{"repos":["pprp/acbench"],"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","unlocated"]}}},{"url":"/paper/does-quantization-affect-models-performance","slug":"does-quantization-affect-models-performance","title":"Does quantization affect models' performance on long-context tasks?","date":"2025-05-26","arxiv_id":"2505.20276","repositories_listed":1,"syntology":null},{"url":"/paper/efficient-speech-translation-through-model","slug":"efficient-speech-translation-through-model","title":"Efficient Speech Translation through Model Compression and Knowledge Distillation","date":"2025-05-26","arxiv_id":"2505.20237","repositories_listed":1,"syntology":null},{"url":"/paper/flowse-efficient-and-high-quality-speech","slug":"flowse-efficient-and-high-quality-speech","title":"FlowSE: Efficient and High-Quality Speech Enhancement via Flow Matching","date":"2025-05-26","arxiv_id":"2505.19476","repositories_listed":1,"syntology":null},{"url":"/paper/optimizing-edge-ai-models-on-hpc-systems-with","slug":"optimizing-edge-ai-models-on-hpc-systems-with","title":"Optimizing edge AI models on HPC systems with the edge in the loop","date":"2025-05-26","arxiv_id":"2505.19995","repositories_listed":1,"syntology":null},{"url":"/paper/tailorkv-a-hybrid-framework-for-long-context","slug":"tailorkv-a-hybrid-framework-for-long-context","title":"TailorKV: A Hybrid Framework for Long-Context Inference via Tailored KV Cache Optimization","date":"2025-05-26","arxiv_id":"2505.19586","repositories_listed":1,"syntology":null},{"url":"/paper/communication-efficient-multi-device","slug":"communication-efficient-multi-device","title":"Communication-Efficient Multi-Device Inference Acceleration for Transformer Models","date":"2025-05-25","arxiv_id":"2505.19342","repositories_listed":1,"syntology":null},{"url":"/paper/fp4-all-the-way-fully-quantized-training-of","slug":"fp4-all-the-way-fully-quantized-training-of","title":"FP4 All the Way: Fully Quantized Training of LLMs","date":"2025-05-25","arxiv_id":"2505.19115","repositories_listed":1,"syntology":null},{"url":"/paper/adaptive-prediction-powered-autoeval-with","slug":"adaptive-prediction-powered-autoeval-with","title":"Adaptive Prediction-Powered AutoEval with Reliability and Efficiency Guarantees","date":"2025-05-24","arxiv_id":"2505.18659","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":3,"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/adaptive-prediction-powered-autoeval-with#ran","syntology_url":"https://syntology.ai/paper/2505.18659","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.18659"}},"official":{"repos":["kclip/r_autoeval_plus"],"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/dvd-quant-data-free-video-diffusion","slug":"dvd-quant-data-free-video-diffusion","title":"DVD-Quant: Data-free Video Diffusion Transformers Quantization","date":"2025-05-24","arxiv_id":"2505.18663","repositories_listed":1,"syntology":null},{"url":"/paper/lota-qaf-lossless-ternary-adaptation-for","slug":"lota-qaf-lossless-ternary-adaptation-for","title":"LoTA-QAF: Lossless Ternary Adaptation for Quantization-Aware Fine-Tuning","date":"2025-05-24","arxiv_id":"2505.18724","repositories_listed":1,"syntology":null},{"url":"/paper/mind-the-gap-a-practical-attack-on-gguf","slug":"mind-the-gap-a-practical-attack-on-gguf","title":"Mind the Gap: A Practical Attack on GGUF Quantization","date":"2025-05-24","arxiv_id":"2505.23786","repositories_listed":1,"syntology":{"n":13,"n_ran":7,"n_constructed":6,"n_ran_checked":6,"n_instrument":1,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"7 ran (of which 6 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/mind-the-gap-a-practical-attack-on-gguf#ran","syntology_url":"https://syntology.ai/paper/2505.23786","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.23786"}},"official":{"repos":["eth-sri/llm-quantization-attack"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":6,"n_ran_no_instrument_failure":6,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/pm-kvq-progressive-mixed-precision-kv-cache","slug":"pm-kvq-progressive-mixed-precision-kv-cache","title":"PM-KVQ: Progressive Mixed-precision KV Cache Quantization for Long-CoT LLMs","date":"2025-05-24","arxiv_id":"2505.18610","repositories_listed":1,"syntology":null},{"url":"/paper/reducing-storage-of-pretrained-neural","slug":"reducing-storage-of-pretrained-neural","title":"Reducing Storage of Pretrained Neural Networks by Rate-Constrained Quantization and Entropy Coding","date":"2025-05-24","arxiv_id":"2505.18758","repositories_listed":1,"syntology":null},{"url":"/paper/neuqi-near-optimal-uniform-quantization","slug":"neuqi-near-optimal-uniform-quantization","title":"NeUQI: Near-Optimal Uniform Quantization Parameter Initialization","date":"2025-05-23","arxiv_id":"2505.17595","repositories_listed":1,"syntology":{"n":20,"n_ran":6,"n_constructed":1,"n_ran_checked":3,"n_instrument":3,"n_unverified":14,"n_honours":2,"n_violates":0,"n_no_contract":1,"n_pointer_only":20,"phrase":"6 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 14 unverified","sample_list":"/paper/neuqi-near-optimal-uniform-quantization#ran","syntology_url":"https://syntology.ai/paper/2505.17595","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.17595"}},"official":{"repos":["efsotr/NeUQI"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":1,"n_ran_no_instrument_failure":3,"n_unverified":14,"ran_from_kinds":["official"]}}},{"url":"/paper/duffin-a-dual-level-fingerprinting-framework","slug":"duffin-a-dual-level-fingerprinting-framework","title":"DuFFin: A Dual-Level Fingerprinting Framework for LLMs IP Protection","date":"2025-05-22","arxiv_id":"2505.16530","repositories_listed":1,"syntology":null},{"url":"/paper/fpqvar-floating-point-quantization-for-visual","slug":"fpqvar-floating-point-quantization-for-visual","title":"FPQVAR: Floating Point Quantization for Visual Autoregressive Model with FPGA Hardware Co-design","date":"2025-05-22","arxiv_id":"2505.16335","repositories_listed":1,"syntology":null},{"url":"/paper/dual-precision-quantization-for-efficient-and","slug":"dual-precision-quantization-for-efficient-and","title":"Dual Precision Quantization for Efficient and Accurate Deep Neural Networks Inference","date":"2025-05-20","arxiv_id":"2505.14638","repositories_listed":1,"syntology":null},{"url":"/paper/quaff-quantized-parameter-efficient-fine","slug":"quaff-quantized-parameter-efficient-fine","title":"Quaff: Quantized Parameter-Efficient Fine-Tuning under Outlier Spatial Stability Hypothesis","date":"2025-05-20","arxiv_id":"2505.14742","repositories_listed":1,"syntology":null},{"url":"/paper/an-overview-of-arithmetic-adaptations-for","slug":"an-overview-of-arithmetic-adaptations-for","title":"An Overview of Arithmetic Adaptations for Inference of Convolutional Neural Networks on Re-configurable Hardware","date":"2025-05-19","arxiv_id":"2505.13575","repositories_listed":1,"syntology":null},{"url":"/paper/efficient-speech-language-modeling-via-energy","slug":"efficient-speech-language-modeling-via-energy","title":"Efficient Speech Language Modeling via Energy Distance in Continuous Latent Space","date":"2025-05-19","arxiv_id":"2505.13181","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":3,"n_ran_checked":4,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":5,"phrase":"5 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/efficient-speech-language-modeling-via-energy#ran","syntology_url":"https://syntology.ai/paper/2505.13181","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.13181"}},"official":{"repos":["ictnlp/sled-tts"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":3,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/fine-tuning-quantized-neural-networks-with","slug":"fine-tuning-quantized-neural-networks-with","title":"Fine-tuning Quantized Neural Networks with Zeroth-order Optimization","date":"2025-05-19","arxiv_id":"2505.13430","repositories_listed":1,"syntology":{"n":15,"n_ran":10,"n_constructed":0,"n_ran_checked":9,"n_instrument":1,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":2,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/fine-tuning-quantized-neural-networks-with#ran","syntology_url":"https://syntology.ai/paper/2505.13430","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.13430"}},"official":{"repos":["maifoundations/qzo"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/quads-quantized-distillation-framework-for","slug":"quads-quantized-distillation-framework-for","title":"QUADS: QUAntized Distillation Framework for Efficient Speech Language Understanding","date":"2025-05-19","arxiv_id":"2505.14723","repositories_listed":1,"syntology":null},{"url":"/paper/pmq-ve-progressive-multi-frame-quantization","slug":"pmq-ve-progressive-multi-frame-quantization","title":"PMQ-VE: Progressive Multi-Frame Quantization for Video Enhancement","date":"2025-05-18","arxiv_id":"2505.12266","repositories_listed":1,"syntology":null},{"url":"/paper/2505-10787","slug":"2505-10787","title":"EA-3DGS: Efficient and Adaptive 3D Gaussians with Highly Enhanced Quality for outdoor scenes","date":"2025-05-16","arxiv_id":"2505.10787","repositories_listed":1,"syntology":null},{"url":"/paper/2505-10938","slug":"2505-10938","title":"Accurate KV Cache Quantization with Outlier Tokens Tracing","date":"2025-05-16","arxiv_id":"2505.10938","repositories_listed":1,"syntology":null},{"url":"/paper/2505-10983","slug":"2505-10983","title":"GenoArmory: A Unified Evaluation Framework for Adversarial Attacks on Genomic Foundation Models","date":"2025-05-16","arxiv_id":"2505.10983","repositories_listed":1,"syntology":null},{"url":"/paper/2505-11076","slug":"2505-11076","title":"Addition is almost all you need: Compressing neural networks with double binary factorization","date":"2025-05-16","arxiv_id":"2505.11076","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/2505-11076#ran","syntology_url":"https://syntology.ai/paper/2505.11076","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.11076"}},"official":{"repos":["usamec/double_binary"],"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/transpl-vq-code-transition-matrices-for","slug":"transpl-vq-code-transition-matrices-for","title":"TransPL: VQ-Code Transition Matrices for Pseudo-Labeling of Time Series Unsupervised Domain Adaptation","date":"2025-05-15","arxiv_id":"2505.09955","repositories_listed":1,"syntology":null},{"url":"/paper/analog-foundation-models","slug":"analog-foundation-models","title":"Analog Foundation Models","date":"2025-05-14","arxiv_id":"2505.09663","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 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; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/analog-foundation-models#ran","syntology_url":"https://syntology.ai/paper/2505.09663","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.09663"}},"official":{"repos":["ibm/analog-foundation-models"],"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/efficient-mixed-precision-quantization-in","slug":"efficient-mixed-precision-quantization-in","title":"Efficient Mixed Precision Quantization in Graph Neural Networks","date":"2025-05-14","arxiv_id":"2505.09361","repositories_listed":1,"syntology":null},{"url":"/paper/continuous-visual-autoregressive-generation","slug":"continuous-visual-autoregressive-generation","title":"Continuous Visual Autoregressive Generation via Score Maximization","date":"2025-05-12","arxiv_id":"2505.07812","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":4,"n_ran_checked":4,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":1,"phrase":"4 ran (of which 4 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) · 2 unverified; every one of the 4 samples that ran constructed an object rather than computing a result","sample_list":"/paper/continuous-visual-autoregressive-generation#ran","syntology_url":"https://syntology.ai/paper/2505.07812","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.07812"}},"official":{"repos":["shaochenze/ear"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":4,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/guidedquant-large-language-model-quantization","slug":"guidedquant-large-language-model-quantization","title":"GuidedQuant: Large Language Model Quantization via Exploiting End Loss Guidance","date":"2025-05-11","arxiv_id":"2505.07004","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/guidedquant-large-language-model-quantization#ran","syntology_url":"https://syntology.ai/paper/2505.07004","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.07004"}},"official":{"repos":["snu-mllab/guidedquant"],"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/mxmoe-mixed-precision-quantization-for-moe","slug":"mxmoe-mixed-precision-quantization-for-moe","title":"MxMoE: Mixed-precision Quantization for MoE with Accuracy and Performance Co-Design","date":"2025-05-09","arxiv_id":"2505.05799","repositories_listed":1,"syntology":null},{"url":"/paper/diffusion-model-quantization-a-review","slug":"diffusion-model-quantization-a-review","title":"Diffusion Model Quantization: A Review","date":"2025-05-08","arxiv_id":"2505.05215","repositories_listed":1,"syntology":null},{"url":"/paper/toklip-marry-visual-tokens-to-clip-for","slug":"toklip-marry-visual-tokens-to-clip-for","title":"TokLIP: Marry Visual Tokens to CLIP for Multimodal Comprehension and Generation","date":"2025-05-08","arxiv_id":"2505.05422","repositories_listed":1,"syntology":null},{"url":"/paper/on-device-llm-for-context-aware-wi-fi-roaming","slug":"on-device-llm-for-context-aware-wi-fi-roaming","title":"On-Device LLM for Context-Aware Wi-Fi Roaming","date":"2025-05-07","arxiv_id":"2505.04174","repositories_listed":1,"syntology":null},{"url":"/paper/rgb-event-fusion-with-self-attention-for","slug":"rgb-event-fusion-with-self-attention-for","title":"RGB-Event Fusion with Self-Attention for Collision Prediction","date":"2025-05-07","arxiv_id":"2505.04258","repositories_listed":1,"syntology":null},{"url":"/paper/quantitative-analysis-of-performance-drop-in","slug":"quantitative-analysis-of-performance-drop-in","title":"Quantitative Analysis of Performance Drop in DeepSeek Model Quantization","date":"2025-05-05","arxiv_id":"2505.02390","repositories_listed":1,"syntology":null},{"url":"/paper/an-empirical-study-of-qwen3-quantization","slug":"an-empirical-study-of-qwen3-quantization","title":"An Empirical Study of Qwen3 Quantization","date":"2025-05-04","arxiv_id":"2505.02214","repositories_listed":1,"syntology":{"n":12,"n_ran":7,"n_constructed":0,"n_ran_checked":3,"n_instrument":4,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":5,"phrase":"7 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; 4 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/an-empirical-study-of-qwen3-quantization#ran","syntology_url":"https://syntology.ai/paper/2505.02214","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.02214"}},"official":{"repos":["efficient-ml/qwen3-quantization"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/fast-and-low-cost-genomic-foundation-models","slug":"fast-and-low-cost-genomic-foundation-models","title":"Fast and Low-Cost Genomic Foundation Models via Outlier Removal","date":"2025-05-01","arxiv_id":"2505.00598","repositories_listed":1,"syntology":{"n":10,"n_ran":9,"n_constructed":0,"n_ran_checked":7,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":4,"phrase":"9 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; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/fast-and-low-cost-genomic-foundation-models#ran","syntology_url":"https://syntology.ai/paper/2505.00598","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.00598"}},"official":{"repos":["MAGICS-LAB/GERM"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/optimizing-deep-neural-networks-using-safety","slug":"optimizing-deep-neural-networks-using-safety","title":"Optimizing Deep Neural Networks using Safety-Guided Self Compression","date":"2025-05-01","arxiv_id":"2505.00350","repositories_listed":1,"syntology":null},{"url":"/paper/softpick-no-attention-sink-no-massive","slug":"softpick-no-attention-sink-no-massive","title":"Softpick: No Attention Sink, No Massive Activations with Rectified Softmax","date":"2025-04-29","arxiv_id":"2504.20966","repositories_listed":1,"syntology":null},{"url":"/paper/partition-map-based-fast-block-partitioning","slug":"partition-map-based-fast-block-partitioning","title":"Partition Map-Based Fast Block Partitioning for VVC Inter Coding","date":"2025-04-25","arxiv_id":"2504.18398","repositories_listed":1,"syntology":null},{"url":"/paper/a-lora-based-approach-to-fine-tuning-llms-for","slug":"a-lora-based-approach-to-fine-tuning-llms-for","title":"A LoRA-Based Approach to Fine-Tuning LLMs for Educational Guidance in Resource-Constrained Settings","date":"2025-04-22","arxiv_id":"2504.15610","repositories_listed":1,"syntology":null},{"url":"/paper/nowag-a-unified-framework-for-shape","slug":"nowag-a-unified-framework-for-shape","title":"NoWag: A Unified Framework for Shape Preserving Compression of Large Language Models","date":"2025-04-20","arxiv_id":"2504.14569","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":1,"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/nowag-a-unified-framework-for-shape#ran","syntology_url":"https://syntology.ai/paper/2504.14569","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.14569"}},"official":{"repos":["lawrencerliu/nowag"],"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/chinese-vicuna-a-chinese-instruction","slug":"chinese-vicuna-a-chinese-instruction","title":"Chinese-Vicuna: A Chinese Instruction-following Llama-based Model","date":"2025-04-17","arxiv_id":"2504.12737","repositories_listed":1,"syntology":null},{"url":"/paper/hierarchical-vector-quantized-graph","slug":"hierarchical-vector-quantized-graph","title":"Hierarchical Vector Quantized Graph Autoencoder with Annealing-Based Code Selection","date":"2025-04-17","arxiv_id":"2504.12715","repositories_listed":1,"syntology":null},{"url":"/paper/impart-importance-aware-delta-sparsification","slug":"impart-importance-aware-delta-sparsification","title":"ImPart: Importance-Aware Delta-Sparsification for Improved Model Compression and Merging in LLMs","date":"2025-04-17","arxiv_id":"2504.13237","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":1,"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/impart-importance-aware-delta-sparsification#ran","syntology_url":"https://syntology.ai/paper/2504.13237","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.13237"}},"official":{"repos":["yanyang19/ImPart"],"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/gt-svq-a-linear-time-graph-transformer-for","slug":"gt-svq-a-linear-time-graph-transformer-for","title":"GT-SVQ: A Linear-Time Graph Transformer for Node Classification Using Spiking Vector Quantization","date":"2025-04-16","arxiv_id":"2504.11840","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-autonomous-driving-systems-with-on","slug":"enhancing-autonomous-driving-systems-with-on","title":"Enhancing Autonomous Driving Systems with On-Board Deployed Large Language Models","date":"2025-04-15","arxiv_id":"2504.11514","repositories_listed":1,"syntology":null},{"url":"/paper/task-circuit-quantization-leveraging","slug":"task-circuit-quantization-leveraging","title":"Task-Circuit Quantization: Leveraging Knowledge Localization and Interpretability for Compression","date":"2025-04-10","arxiv_id":"2504.07389","repositories_listed":1,"syntology":null},{"url":"/paper/are-you-getting-what-you-pay-for-auditing","slug":"are-you-getting-what-you-pay-for-auditing","title":"Are You Getting What You Pay For? Auditing Model Substitution in LLM APIs","date":"2025-04-07","arxiv_id":"2504.04715","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":3,"phrase":"4 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; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/are-you-getting-what-you-pay-for-auditing#ran","syntology_url":"https://syntology.ai/paper/2504.04715","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.04715"}},"official":{"repos":["sunblaze-ucb/llm-api-audit"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/prima-cpp-speeding-up-70b-scale-llm-inference","slug":"prima-cpp-speeding-up-70b-scale-llm-inference","title":"PRIMA.CPP: Speeding Up 70B-Scale LLM Inference on Low-Resource Everyday Home Clusters","date":"2025-04-07","arxiv_id":"2504.08791","repositories_listed":1,"syntology":null},{"url":"/paper/quantization-hurts-reasoning-an-empirical","slug":"quantization-hurts-reasoning-an-empirical","title":"Quantization Hurts Reasoning? An Empirical Study on Quantized Reasoning Models","date":"2025-04-07","arxiv_id":"2504.04823","repositories_listed":1,"syntology":null},{"url":"/paper/aphq-vit-post-training-quantization-with","slug":"aphq-vit-post-training-quantization-with","title":"APHQ-ViT: Post-Training Quantization with Average Perturbation Hessian Based Reconstruction for Vision Transformers","date":"2025-04-03","arxiv_id":"2504.02508","repositories_listed":1,"syntology":{"n":9,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"4 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; 3 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/aphq-vit-post-training-quantization-with#ran","syntology_url":"https://syntology.ai/paper/2504.02508","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.02508"}},"official":{"repos":["GoatWu/APHQ-ViT"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/compressing-3d-gaussian-splatting-by-noise","slug":"compressing-3d-gaussian-splatting-by-noise","title":"Compressing 3D Gaussian Splatting by Noise-Substituted Vector Quantization","date":"2025-04-03","arxiv_id":"2504.03059","repositories_listed":1,"syntology":null},{"url":"/paper/milo-efficient-quantized-moe-inference-with","slug":"milo-efficient-quantized-moe-inference-with","title":"MiLo: Efficient Quantized MoE Inference with Mixture of Low-Rank Compensators","date":"2025-04-03","arxiv_id":"2504.02658","repositories_listed":1,"syntology":null},{"url":"/paper/mergevq-a-unified-framework-for-visual","slug":"mergevq-a-unified-framework-for-visual","title":"MergeVQ: A Unified Framework for Visual Generation and Representation with Disentangled Token Merging and Quantization","date":"2025-04-01","arxiv_id":"2504.00999","repositories_listed":1,"syntology":null},{"url":"/paper/a-refined-analysis-of-massive-activations-in","slug":"a-refined-analysis-of-massive-activations-in","title":"A Refined Analysis of Massive Activations in LLMs","date":"2025-03-28","arxiv_id":"2503.22329","repositories_listed":1,"syntology":null},{"url":"/paper/quamba2-a-robust-and-scalable-post-training","slug":"quamba2-a-robust-and-scalable-post-training","title":"Quamba2: A Robust and Scalable Post-training Quantization Framework for Selective State Space Models","date":"2025-03-28","arxiv_id":"2503.22879","repositories_listed":1,"syntology":null},{"url":"/paper/harmonizing-visual-representations-for","slug":"harmonizing-visual-representations-for","title":"Harmonizing Visual Representations for Unified Multimodal Understanding and Generation","date":"2025-03-27","arxiv_id":"2503.21979","repositories_listed":1,"syntology":null},{"url":"/paper/hot-hadamard-based-optimized-training","slug":"hot-hadamard-based-optimized-training","title":"HOT: Hadamard-based Optimized Training","date":"2025-03-27","arxiv_id":"2503.21261","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/hot-hadamard-based-optimized-training#ran","syntology_url":"https://syntology.ai/paper/2503.21261","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.21261"}},"official":{"repos":["sungonuni/HOT"],"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/vadmamba-exploring-state-space-models-for","slug":"vadmamba-exploring-state-space-models-for","title":"VADMamba: Exploring State Space Models for Fast Video Anomaly Detection","date":"2025-03-27","arxiv_id":"2503.21169","repositories_listed":1,"syntology":null},{"url":"/paper/genius-a-generative-framework-for-universal","slug":"genius-a-generative-framework-for-universal","title":"GENIUS: A Generative Framework for Universal Multimodal Search","date":"2025-03-25","arxiv_id":"2503.19868","repositories_listed":1,"syntology":null},{"url":"/paper/logquant-log-distributed-2-bit-quantization","slug":"logquant-log-distributed-2-bit-quantization","title":"LogQuant: Log-Distributed 2-Bit Quantization of KV Cache with Superior Accuracy Preservation","date":"2025-03-25","arxiv_id":"2503.19950","repositories_listed":1,"syntology":null},{"url":"/paper/quad-quantization-and-parameter-efficient","slug":"quad-quantization-and-parameter-efficient","title":"QUAD: Quantization and Parameter-Efficient Tuning of LLM with Activation Decomposition","date":"2025-03-25","arxiv_id":"2503.19353","repositories_listed":1,"syntology":null},{"url":"/paper/bitdecoding-unlocking-tensor-cores-for-long","slug":"bitdecoding-unlocking-tensor-cores-for-long","title":"BitDecoding: Unlocking Tensor Cores for Long-Context LLMs Decoding with Low-Bit KV Cache","date":"2025-03-24","arxiv_id":"2503.18773","repositories_listed":1,"syntology":null},{"url":"/paper/variance-control-via-weight-rescaling-in-llm","slug":"variance-control-via-weight-rescaling-in-llm","title":"Variance Control via Weight Rescaling in LLM Pre-training","date":"2025-03-21","arxiv_id":"2503.17500","repositories_listed":1,"syntology":null},{"url":"/paper/quartdepth-post-training-quantization-for-1","slug":"quartdepth-post-training-quantization-for-1","title":"QuartDepth: Post-Training Quantization for Real-Time Depth Estimation on the Edge","date":"2025-03-20","arxiv_id":"2503.16709","repositories_listed":1,"syntology":{"n":20,"n_ran":8,"n_constructed":0,"n_ran_checked":4,"n_instrument":4,"n_unverified":12,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":20,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 12 unverified","sample_list":"/paper/quartdepth-post-training-quantization-for-1#ran","syntology_url":"https://syntology.ai/paper/2503.16709","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.16709"}},"official":{"repos":["shawnricecake/quart-depth"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":12,"ran_from_kinds":["official"]}}},{"url":"/paper/fp4dit-towards-effective-floating-point","slug":"fp4dit-towards-effective-floating-point","title":"FP4DiT: Towards Effective Floating Point Quantization for Diffusion Transformers","date":"2025-03-19","arxiv_id":"2503.15465","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"3 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; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/fp4dit-towards-effective-floating-point#ran","syntology_url":"https://syntology.ai/paper/2503.15465","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.15465"}},"official":{"repos":["cccrrrccc/fp4dit"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/natural-quantization-of-neural-networks","slug":"natural-quantization-of-neural-networks","title":"Natural Quantization of Neural Networks","date":"2025-03-19","arxiv_id":"2503.15482","repositories_listed":1,"syntology":null},{"url":"/paper/quantization-free-autoregressive-action","slug":"quantization-free-autoregressive-action","title":"Quantization-Free Autoregressive Action Transformer","date":"2025-03-18","arxiv_id":"2503.14259","repositories_listed":1,"syntology":null},{"url":"/paper/quantization-for-openai-s-whisper-models-a","slug":"quantization-for-openai-s-whisper-models-a","title":"Quantization for OpenAI's Whisper Models: A Comparative Analysis","date":"2025-03-12","arxiv_id":"2503.09905","repositories_listed":1,"syntology":null},{"url":"/paper/pcgs-progressive-compression-of-3d-gaussian","slug":"pcgs-progressive-compression-of-3d-gaussian","title":"PCGS: Progressive Compression of 3D Gaussian Splatting","date":"2025-03-11","arxiv_id":"2503.08511","repositories_listed":1,"syntology":null},{"url":"/paper/prism-privacy-preserving-improved-stochastic","slug":"prism-privacy-preserving-improved-stochastic","title":"PRISM: Privacy-Preserving Improved Stochastic Masking for Federated Generative Models","date":"2025-03-11","arxiv_id":"2503.08085","repositories_listed":1,"syntology":null},{"url":"/paper/task-vector-quantization-for-memory-efficient","slug":"task-vector-quantization-for-memory-efficient","title":"Task Vector Quantization for Memory-Efficient Model Merging","date":"2025-03-10","arxiv_id":"2503.06921","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":2,"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/task-vector-quantization-for-memory-efficient#ran","syntology_url":"https://syntology.ai/paper/2503.06921","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.06921"}},"official":null}},{"url":"/paper/quantcache-adaptive-importance-guided","slug":"quantcache-adaptive-importance-guided","title":"QuantCache: Adaptive Importance-Guided Quantization with Hierarchical Latent and Layer Caching for Video Generation","date":"2025-03-09","arxiv_id":"2503.06545","repositories_listed":1,"syntology":null},{"url":"/paper/casp-compression-of-large-multimodal-models","slug":"casp-compression-of-large-multimodal-models","title":"CASP: Compression of Large Multimodal Models Based on Attention Sparsity","date":"2025-03-07","arxiv_id":"2503.05936","repositories_listed":1,"syntology":null},{"url":"/paper/d2gv-deformable-2d-gaussian-splatting-for","slug":"d2gv-deformable-2d-gaussian-splatting-for","title":"D2GV: Deformable 2D Gaussian Splatting for Video Representation in 400FPS","date":"2025-03-07","arxiv_id":"2503.05600","repositories_listed":1,"syntology":null},{"url":"/paper/qartsr-quantization-via-reverse-module-and","slug":"qartsr-quantization-via-reverse-module-and","title":"QArtSR: Quantization via Reverse-Module and Timestep-Retraining in One-Step Diffusion based Image Super-Resolution","date":"2025-03-07","arxiv_id":"2503.05584","repositories_listed":1,"syntology":null},{"url":"/paper/end-to-end-human-pose-reconstruction-from","slug":"end-to-end-human-pose-reconstruction-from","title":"End-to-End Human Pose Reconstruction from Wearable Sensors for 6G Extended Reality Systems","date":"2025-03-06","arxiv_id":"2503.04860","repositories_listed":1,"syntology":null},{"url":"/paper/bhvit-binarized-hybrid-vision-transformer","slug":"bhvit-binarized-hybrid-vision-transformer","title":"BHViT: Binarized Hybrid Vision Transformer","date":"2025-03-04","arxiv_id":"2503.02394","repositories_listed":1,"syntology":{"n":29,"n_ran":16,"n_constructed":13,"n_ran_checked":15,"n_instrument":1,"n_unverified":13,"n_honours":0,"n_violates":0,"n_no_contract":15,"n_pointer_only":0,"phrase":"16 ran (of which 13 constructed an object rather than computing a result; 15 with no instrument failure: 0 honoured, 0 violated, 15 with no contract checked; 1 where Syntology's instrument failed) · 13 unverified","sample_list":"/paper/bhvit-binarized-hybrid-vision-transformer#ran","syntology_url":"https://syntology.ai/paper/2503.02394","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.02394"}},"official":{"repos":["IMRL/BHViT"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":13,"n_ran_no_instrument_failure":15,"n_unverified":13,"ran_from_kinds":["official"]}}}],"record_sha256":"1ae0ea437cf0f82b009ce4acd75063210cb98287314f26f63cca3ff4791bc610","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}