{"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/model-compression/papers/2","list_of":"/task/model-compression","task":"Model Compression","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":2,"pages_in_order":14,"rows_per_page":100,"rows":[101,200],"of":1356,"counts":{"archive_papers_tagged":1356,"with_a_code_link":440,"where_syntology_ran_a_sample":119,"not_listed_spam_title":0,"listed":1356,"listed_where_code_ran":119,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":97,"every_run_a_failure_of_syntologys_instrument":22,"listed_with_a_run_with_no_instrument_failure":97,"listed_every_run_a_failure_of_syntologys_instrument":22,"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/model-compression","prev":"/task/model-compression","next":"/task/model-compression/papers/3","papers":[{"url":"/paper/coa-towards-real-image-dehazing-via","slug":"coa-towards-real-image-dehazing-via","title":"CoA: Towards Real Image Dehazing via Compression-and-Adaptation","date":"2025-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/deepcompress-vit-rethinking-model-compression","slug":"deepcompress-vit-rethinking-model-compression","title":"DeepCompress-ViT: Rethinking Model Compression to Enhance Efficiency of Vision Transformers at the Edge","date":"2025-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/singular-value-scaling-efficient-generative","slug":"singular-value-scaling-efficient-generative","title":"Singular Value Scaling: Efficient Generative Model Compression via Pruned Weights Refinement","date":"2024-12-23","arxiv_id":"2412.17387","repositories_listed":1,"syntology":null},{"url":"/paper/mix-ln-unleashing-the-power-of-deeper-layers","slug":"mix-ln-unleashing-the-power-of-deeper-layers","title":"Mix-LN: Unleashing the Power of Deeper Layers by Combining Pre-LN and Post-LN","date":"2024-12-18","arxiv_id":"2412.13795","repositories_listed":1,"syntology":null},{"url":"/paper/remotetrimmer-adaptive-structural-pruning-for","slug":"remotetrimmer-adaptive-structural-pruning-for","title":"RemoteTrimmer: Adaptive Structural Pruning for Remote Sensing Image Classification","date":"2024-12-17","arxiv_id":"2412.12603","repositories_listed":1,"syntology":null},{"url":"/paper/faithful-label-free-knowledge-distillation","slug":"faithful-label-free-knowledge-distillation","title":"Faithful Label-free Knowledge Distillation","date":"2024-11-22","arxiv_id":"2411.15239","repositories_listed":1,"syntology":null},{"url":"/paper/an-exploration-of-the-effect-of-quantisation","slug":"an-exploration-of-the-effect-of-quantisation","title":"An exploration of the effect of quantisation on energy consumption and inference time of StarCoder2","date":"2024-11-15","arxiv_id":"2411.12758","repositories_listed":1,"syntology":null},{"url":"/paper/owled-outlier-weighed-layerwise-pruning-for","slug":"owled-outlier-weighed-layerwise-pruning-for","title":"OWLed: Outlier-weighed Layerwise Pruning for Efficient Autonomous Driving Framework","date":"2024-11-12","arxiv_id":"2411.07711","repositories_listed":1,"syntology":null},{"url":"/paper/zipnn-lossless-compression-for-ai-models","slug":"zipnn-lossless-compression-for-ai-models","title":"ZipNN: Lossless Compression for AI Models","date":"2024-11-07","arxiv_id":"2411.05239","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":7,"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) · 1 unverified","sample_list":"/paper/zipnn-lossless-compression-for-ai-models#ran","syntology_url":"https://syntology.ai/paper/2411.05239","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.05239"}},"official":{"repos":["zipnn/zipnn"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/change-is-the-only-constant-dynamic-llm","slug":"change-is-the-only-constant-dynamic-llm","title":"Change Is the Only Constant: Dynamic LLM Slicing based on Layer Redundancy","date":"2024-11-05","arxiv_id":"2411.03513","repositories_listed":1,"syntology":null},{"url":"/paper/ml-research-benchmark","slug":"ml-research-benchmark","title":"ML Research Benchmark","date":"2024-10-29","arxiv_id":"2410.22553","repositories_listed":1,"syntology":null},{"url":"/paper/llmcbench-benchmarking-large-language-model","slug":"llmcbench-benchmarking-large-language-model","title":"LLMCBench: Benchmarking Large Language Model Compression for Efficient Deployment","date":"2024-10-28","arxiv_id":"2410.21352","repositories_listed":1,"syntology":{"n":17,"n_ran":14,"n_constructed":0,"n_ran_checked":11,"n_instrument":3,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":1,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/llmcbench-benchmarking-large-language-model#ran","syntology_url":"https://syntology.ai/paper/2410.21352","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.21352"}},"official":{"repos":["aboveparadise/llmcbench"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":3,"ran_from_kinds":["official"]}}},{"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/qianets-quantum-integrated-adaptive-networks","slug":"qianets-quantum-integrated-adaptive-networks","title":"QIANets: Quantum-Integrated Adaptive Networks for Reduced Latency and Improved Inference Times in CNN Models","date":"2024-10-14","arxiv_id":"2410.10318","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":1,"n_ran_checked":3,"n_instrument":1,"n_unverified":1,"n_honours":2,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"4 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; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/qianets-quantum-integrated-adaptive-networks#ran","syntology_url":"https://syntology.ai/paper/2410.10318","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.10318"}},"official":{"repos":["edwardmagongo/quantum-inspired-model-compression"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":1,"n_ran_no_instrument_failure":3,"n_unverified":1,"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/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/basis-sharing-cross-layer-parameter-sharing","slug":"basis-sharing-cross-layer-parameter-sharing","title":"Basis Sharing: Cross-Layer Parameter Sharing for Large Language Model Compression","date":"2024-10-02","arxiv_id":"2410.03765","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/maskllm-learnable-semi-structured-sparsity","slug":"maskllm-learnable-semi-structured-sparsity","title":"MaskLLM: Learnable Semi-Structured Sparsity for Large Language Models","date":"2024-09-26","arxiv_id":"2409.17481","repositories_listed":1,"syntology":{"n":16,"n_ran":5,"n_constructed":1,"n_ran_checked":5,"n_instrument":0,"n_unverified":11,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":16,"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) · 11 unverified","sample_list":"/paper/maskllm-learnable-semi-structured-sparsity#ran","syntology_url":"https://syntology.ai/paper/2409.17481","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.17481"}},"official":{"repos":["nvlabs/maskllm"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":1,"n_ran_no_instrument_failure":5,"n_unverified":11,"ran_from_kinds":["official"]}}},{"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/enhancing-knowledge-distillation-of-large","slug":"enhancing-knowledge-distillation-of-large","title":"Enhancing Knowledge Distillation of Large Language Models through Efficient Multi-Modal Distribution Alignment","date":"2024-09-19","arxiv_id":"2409.12545","repositories_listed":1,"syntology":null},{"url":"/paper/elsa-exploiting-layer-wise-n-m-sparsity-for","slug":"elsa-exploiting-layer-wise-n-m-sparsity-for","title":"ELSA: Exploiting Layer-wise N:M Sparsity for Vision Transformer Acceleration","date":"2024-09-15","arxiv_id":"2409.09708","repositories_listed":1,"syntology":null},{"url":"/paper/application-specific-compression-of-deep","slug":"application-specific-compression-of-deep","title":"Application Specific Compression of Deep Learning Models","date":"2024-09-09","arxiv_id":"2409.05368","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/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/meddet-generative-adversarial-distillation","slug":"meddet-generative-adversarial-distillation","title":"MedDet: Generative Adversarial Distillation for Efficient Cervical Disc Herniation Detection","date":"2024-08-30","arxiv_id":"2409.00204","repositories_listed":1,"syntology":null},{"url":"/paper/pruning-by-explaining-revisited-optimizing","slug":"pruning-by-explaining-revisited-optimizing","title":"Pruning By Explaining Revisited: Optimizing Attribution Methods to Prune CNNs and Transformers","date":"2024-08-22","arxiv_id":"2408.12568","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/computer-vision-model-compression-techniques","slug":"computer-vision-model-compression-techniques","title":"Computer Vision Model Compression Techniques for Embedded Systems: A Survey","date":"2024-08-15","arxiv_id":"2408.08250","repositories_listed":1,"syntology":null},{"url":"/paper/knowledge-distillation-with-refined-logits","slug":"knowledge-distillation-with-refined-logits","title":"Knowledge Distillation with Refined Logits","date":"2024-08-14","arxiv_id":"2408.07703","repositories_listed":1,"syntology":null},{"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/2408-03046","slug":"2408-03046","title":"Comb, Prune, Distill: Towards Unified Pruning for Vision Model Compression","date":"2024-08-06","arxiv_id":"2408.03046","repositories_listed":1,"syntology":null},{"url":"/paper/generalizing-teacher-networks-for-effective","slug":"generalizing-teacher-networks-for-effective","title":"Generalizing Teacher Networks for Effective Knowledge Distillation Across Student Architectures","date":"2024-07-22","arxiv_id":"2407.16040","repositories_listed":1,"syntology":null},{"url":"/paper/minimizing-plm-based-few-shot-intent","slug":"minimizing-plm-based-few-shot-intent","title":"Minimizing PLM-Based Few-Shot Intent Detectors","date":"2024-07-13","arxiv_id":"2407.09943","repositories_listed":1,"syntology":null},{"url":"/paper/composable-interventions-for-language-models","slug":"composable-interventions-for-language-models","title":"Composable Interventions for Language Models","date":"2024-07-09","arxiv_id":"2407.06483","repositories_listed":1,"syntology":{"n":17,"n_ran":8,"n_constructed":0,"n_ran_checked":5,"n_instrument":3,"n_unverified":9,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":17,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 9 unverified","sample_list":"/paper/composable-interventions-for-language-models#ran","syntology_url":"https://syntology.ai/paper/2407.06483","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.06483"}},"official":{"repos":["hartvigsen-group/composable-interventions"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":9,"ran_from_kinds":["official"]}}},{"url":"/paper/beyond-perplexity-multi-dimensional-safety","slug":"beyond-perplexity-multi-dimensional-safety","title":"Beyond Perplexity: Multi-dimensional Safety Evaluation of LLM Compression","date":"2024-07-06","arxiv_id":"2407.04965","repositories_listed":1,"syntology":{"n":16,"n_ran":14,"n_constructed":0,"n_ran_checked":14,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":14,"n_pointer_only":16,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/beyond-perplexity-multi-dimensional-safety#ran","syntology_url":"https://syntology.ai/paper/2407.04965","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.04965"}},"official":{"repos":["zhichaoxu-shufe/beyond-perplexity-compression-safety-eval"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":14,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/q-dit-accurate-post-training-quantization-for","slug":"q-dit-accurate-post-training-quantization-for","title":"Q-DiT: Accurate Post-Training Quantization for Diffusion Transformers","date":"2024-06-25","arxiv_id":"2406.17343","repositories_listed":1,"syntology":{"n":19,"n_ran":17,"n_constructed":0,"n_ran_checked":11,"n_instrument":6,"n_unverified":2,"n_honours":4,"n_violates":0,"n_no_contract":7,"n_pointer_only":19,"phrase":"17 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 4 honoured, 0 violated, 7 with no contract checked; 6 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/q-dit-accurate-post-training-quantization-for#ran","syntology_url":"https://syntology.ai/paper/2406.17343","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.17343"}},"official":{"repos":["juanerx/q-dit"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":2,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/liteyolo-id-a-lightweight-object-detection","slug":"liteyolo-id-a-lightweight-object-detection","title":"LiteYOLO-ID: A Lightweight Object Detection Network for Insulator Defect Detection","date":"2024-06-24","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/pruning-via-merging-compressing-llms-via","slug":"pruning-via-merging-compressing-llms-via","title":"Pruning via Merging: Compressing LLMs via Manifold Alignment Based Layer Merging","date":"2024-06-24","arxiv_id":"2406.16330","repositories_listed":1,"syntology":{"n":13,"n_ran":10,"n_constructed":0,"n_ran_checked":3,"n_instrument":7,"n_unverified":3,"n_honours":3,"n_violates":0,"n_no_contract":0,"n_pointer_only":13,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 7 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/pruning-via-merging-compressing-llms-via#ran","syntology_url":"https://syntology.ai/paper/2406.16330","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.16330"}},"official":{"repos":["sempraety/pruning-via-merging"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/moa-mixture-of-sparse-attention-for-automatic","slug":"moa-mixture-of-sparse-attention-for-automatic","title":"MoA: Mixture of Sparse Attention for Automatic Large Language Model Compression","date":"2024-06-21","arxiv_id":"2406.14909","repositories_listed":1,"syntology":{"n":22,"n_ran":19,"n_constructed":0,"n_ran_checked":19,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":19,"n_pointer_only":0,"phrase":"19 ran (of which 0 constructed an object rather than computing a result; 19 with no instrument failure: 0 honoured, 0 violated, 19 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/moa-mixture-of-sparse-attention-for-automatic#ran","syntology_url":"https://syntology.ai/paper/2406.14909","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.14909"}},"official":{"repos":["thu-nics/moa"],"state":"official (archive's flag): 19 ran","n_ran":19,"n_constructed":0,"n_ran_no_instrument_failure":19,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/reinforced-knowledge-distillation-for-time","slug":"reinforced-knowledge-distillation-for-time","title":"Reinforced Knowledge Distillation for Time Series Regression","date":"2024-06-21","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/flocora-federated-learning-compression-with","slug":"flocora-federated-learning-compression-with","title":"FLoCoRA: Federated learning compression with low-rank adaptation","date":"2024-06-20","arxiv_id":"2406.14082","repositories_listed":1,"syntology":null},{"url":"/paper/examining-post-training-quantization-for","slug":"examining-post-training-quantization-for","title":"Examining Post-Training Quantization for Mixture-of-Experts: A Benchmark","date":"2024-06-12","arxiv_id":"2406.08155","repositories_listed":1,"syntology":{"n":6,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/examining-post-training-quantization-for#ran","syntology_url":"https://syntology.ai/paper/2406.08155","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.08155"}},"official":{"repos":["unites-lab/moe-quantization"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/enhancing-in-context-learning-performance","slug":"enhancing-in-context-learning-performance","title":"Enhancing In-Context Learning Performance with just SVD-Based Weight Pruning: A Theoretical Perspective","date":"2024-06-06","arxiv_id":"2406.03768","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/enhancing-in-context-learning-performance#ran","syntology_url":"https://syntology.ai/paper/2406.03768","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.03768"}},"official":{"repos":["chen123ctrls/enhancingicl_svdpruning"],"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/slicing-mutual-information-generalization","slug":"slicing-mutual-information-generalization","title":"Slicing Mutual Information Generalization Bounds for Neural Networks","date":"2024-06-06","arxiv_id":"2406.04047","repositories_listed":1,"syntology":null},{"url":"/paper/robust-knowledge-distillation-based-on","slug":"robust-knowledge-distillation-based-on","title":"Robust Knowledge Distillation Based on Feature Variance Against Backdoored Teacher Model","date":"2024-06-01","arxiv_id":"2406.03409","repositories_listed":1,"syntology":null},{"url":"/paper/occam-gradient-descent","slug":"occam-gradient-descent","title":"Occam Gradient Descent","date":"2024-05-30","arxiv_id":"2405.20194","repositories_listed":1,"syntology":null},{"url":"/paper/submfl-compatiple-submodel-generation-for","slug":"submfl-compatiple-submodel-generation-for","title":"subMFL: Compatiple subModel Generation for Federated Learning in Device Heterogenous Environment","date":"2024-05-30","arxiv_id":"2405.20014","repositories_listed":1,"syntology":null},{"url":"/paper/trio-vit-post-training-quantization-and","slug":"trio-vit-post-training-quantization-and","title":"Trio-ViT: Post-Training Quantization and Acceleration for Softmax-Free Efficient Vision Transformer","date":"2024-05-06","arxiv_id":"2405.03882","repositories_listed":1,"syntology":null},{"url":"/paper/iterative-filter-pruning-for-concatenation","slug":"iterative-filter-pruning-for-concatenation","title":"Iterative Filter Pruning for Concatenation-based CNN Architectures","date":"2024-05-04","arxiv_id":"2405.03715","repositories_listed":1,"syntology":null},{"url":"/paper/torch2chip-an-end-to-end-customizable-deep","slug":"torch2chip-an-end-to-end-customizable-deep","title":"Torch2Chip: An End-to-end Customizable Deep Neural Network Compression and Deployment Toolkit for Prototype Hardware Accelerator Design","date":"2024-05-02","arxiv_id":"2405.01775","repositories_listed":1,"syntology":null},{"url":"/paper/data-free-knowledge-distillation-for-fine-1","slug":"data-free-knowledge-distillation-for-fine-1","title":"Data-free Knowledge Distillation for Fine-grained Visual Categorization","date":"2024-04-18","arxiv_id":"2404.12037","repositories_listed":1,"syntology":null},{"url":"/paper/transferable-and-principled-efficiency-for","slug":"transferable-and-principled-efficiency-for","title":"Transferable and Principled Efficiency for Open-Vocabulary Segmentation","date":"2024-04-11","arxiv_id":"2404.07448","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":3,"n_violates":0,"n_no_contract":1,"n_pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 3 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/transferable-and-principled-efficiency-for#ran","syntology_url":"https://syntology.ai/paper/2404.07448","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.07448"}},"official":{"repos":["xujxyang/opentrans"],"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/multilingual-brain-surgeon-large-language","slug":"multilingual-brain-surgeon-large-language","title":"Multilingual Brain Surgeon: Large Language Models Can be Compressed Leaving No Language Behind","date":"2024-04-06","arxiv_id":"2404.04748","repositories_listed":1,"syntology":null},{"url":"/paper/compressing-large-language-models-by","slug":"compressing-large-language-models-by","title":"Streamlining Redundant Layers to Compress Large Language Models","date":"2024-03-28","arxiv_id":"2403.19135","repositories_listed":1,"syntology":null},{"url":"/paper/is-modularity-transferable-a-case-study","slug":"is-modularity-transferable-a-case-study","title":"Is Modularity Transferable? A Case Study through the Lens of Knowledge Distillation","date":"2024-03-27","arxiv_id":"2403.18804","repositories_listed":1,"syntology":null},{"url":"/paper/are-compressed-language-models-less-subgroup","slug":"are-compressed-language-models-less-subgroup","title":"Are Compressed Language Models Less Subgroup Robust?","date":"2024-03-26","arxiv_id":"2403.17811","repositories_listed":1,"syntology":null},{"url":"/paper/tiny-models-are-the-computational-saver-for","slug":"tiny-models-are-the-computational-saver-for","title":"Tiny Models are the Computational Saver for Large Models","date":"2024-03-26","arxiv_id":"2403.17726","repositories_listed":1,"syntology":null},{"url":"/paper/pyra-parallel-yielding-re-activation-for","slug":"pyra-parallel-yielding-re-activation-for","title":"PYRA: Parallel Yielding Re-Activation for Training-Inference Efficient Task Adaptation","date":"2024-03-14","arxiv_id":"2403.09192","repositories_listed":1,"syntology":{"n":16,"n_ran":16,"n_constructed":0,"n_ran_checked":13,"n_instrument":3,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":11,"n_pointer_only":1,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 2 honoured, 0 violated, 11 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/pyra-parallel-yielding-re-activation-for#ran","syntology_url":"https://syntology.ai/paper/2403.09192","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.09192"}},"official":{"repos":["thu-mig/pyra"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/svd-llm-truncation-aware-singular-value","slug":"svd-llm-truncation-aware-singular-value","title":"SVD-LLM: Truncation-aware Singular Value Decomposition for Large Language Model Compression","date":"2024-03-12","arxiv_id":"2403.07378","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/svd-llm-truncation-aware-singular-value#ran","syntology_url":"https://syntology.ai/paper/2403.07378","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.07378"}},"official":{"repos":["aiot-mlsys-lab/svd-llm"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/bit-mask-robust-contrastive-knowledge","slug":"bit-mask-robust-contrastive-knowledge","title":"Bit-mask Robust Contrastive Knowledge Distillation for Unsupervised Semantic Hashing","date":"2024-03-10","arxiv_id":"2403.06071","repositories_listed":1,"syntology":null},{"url":"/paper/dyce-dynamic-configurable-exiting-for-deep","slug":"dyce-dynamic-configurable-exiting-for-deep","title":"DyCE: Dynamically Configurable Exiting for Deep Learning Compression and Real-time Scaling","date":"2024-03-04","arxiv_id":"2403.01695","repositories_listed":1,"syntology":null},{"url":"/paper/differentially-private-knowledge-distillation","slug":"differentially-private-knowledge-distillation","title":"Differentially Private Knowledge Distillation via Synthetic Text Generation","date":"2024-03-01","arxiv_id":"2403.00932","repositories_listed":1,"syntology":null},{"url":"/paper/lossless-compression-of-deep-neural-networks-1","slug":"lossless-compression-of-deep-neural-networks-1","title":"\"Lossless\" Compression of Deep Neural Networks: A High-dimensional Neural Tangent Kernel Approach","date":"2024-03-01","arxiv_id":"2403.00258","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/lossless-compression-of-deep-neural-networks-1#ran","syntology_url":"https://syntology.ai/paper/2403.00258","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.00258"}},"official":{"repos":["model-compression/lossless_compression"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/promptmm-multi-modal-knowledge-distillation","slug":"promptmm-multi-modal-knowledge-distillation","title":"PromptMM: Multi-Modal Knowledge Distillation for Recommendation with Prompt-Tuning","date":"2024-02-27","arxiv_id":"2402.17188","repositories_listed":1,"syntology":{"n":11,"n_ran":10,"n_constructed":0,"n_ran_checked":9,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":1,"n_no_contract":7,"n_pointer_only":11,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 1 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/promptmm-multi-modal-knowledge-distillation#ran","syntology_url":"https://syntology.ai/paper/2402.17188","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.17188"}},"official":{"repos":["hkuds/promptmm"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/a-survey-on-knowledge-distillation-of-large","slug":"a-survey-on-knowledge-distillation-of-large","title":"A Survey on Knowledge Distillation of Large Language Models","date":"2024-02-20","arxiv_id":"2402.13116","repositories_listed":1,"syntology":null},{"url":"/paper/promptkd-distilling-student-friendly","slug":"promptkd-distilling-student-friendly","title":"PromptKD: Distilling Student-Friendly Knowledge for Generative Language Models via Prompt Tuning","date":"2024-02-20","arxiv_id":"2402.12842","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":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) · 2 unverified","sample_list":"/paper/promptkd-distilling-student-friendly#ran","syntology_url":"https://syntology.ai/paper/2402.12842","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.12842"}},"official":{"repos":["gmkim-ai/promptkd"],"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/fast-vocabulary-transfer-for-language-model","slug":"fast-vocabulary-transfer-for-language-model","title":"Fast Vocabulary Transfer for Language Model Compression","date":"2024-02-15","arxiv_id":"2402.09977","repositories_listed":1,"syntology":null},{"url":"/paper/quest-low-bit-diffusion-model-quantization","slug":"quest-low-bit-diffusion-model-quantization","title":"QuEST: Low-bit Diffusion Model Quantization via Efficient Selective Finetuning","date":"2024-02-06","arxiv_id":"2402.03666","repositories_listed":1,"syntology":{"n":11,"n_ran":11,"n_constructed":0,"n_ran_checked":3,"n_instrument":8,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":2,"n_pointer_only":11,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 8 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/quest-low-bit-diffusion-model-quantization#ran","syntology_url":"https://syntology.ai/paper/2402.03666","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.03666"}},"official":{"repos":["hatchetProject/QuEST"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/faster-and-lighter-llms-a-survey-on-current","slug":"faster-and-lighter-llms-a-survey-on-current","title":"Faster and Lighter LLMs: A Survey on Current Challenges and Way Forward","date":"2024-02-02","arxiv_id":"2402.01799","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":0,"n_no_contract":1,"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, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/faster-and-lighter-llms-a-survey-on-current#ran","syntology_url":"https://syntology.ai/paper/2402.01799","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.01799"}},"official":{"repos":["nyunai/faster-llm-survey"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/lidar-ptq-post-training-quantization-for","slug":"lidar-ptq-post-training-quantization-for","title":"LiDAR-PTQ: Post-Training Quantization for Point Cloud 3D Object Detection","date":"2024-01-29","arxiv_id":"2401.15865","repositories_listed":1,"syntology":null},{"url":"/paper/tqcompressor-improving-tensor-decomposition","slug":"tqcompressor-improving-tensor-decomposition","title":"TQCompressor: improving tensor decomposition methods in neural networks via permutations","date":"2024-01-29","arxiv_id":"2401.16367","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":2,"phrase":"2 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; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/tqcompressor-improving-tensor-decomposition#ran","syntology_url":"https://syntology.ai/paper/2401.16367","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.16367"}},"official":{"repos":["terra-quantum-public/tqcompressedgpt2"],"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"]}}},{"url":"/paper/communication-efficient-federated-learning-23","slug":"communication-efficient-federated-learning-23","title":"Communication-Efficient Federated Learning through Adaptive Weight Clustering and Server-Side Distillation","date":"2024-01-25","arxiv_id":"2401.14211","repositories_listed":1,"syntology":null},{"url":"/paper/pruning-for-protection-increasing-jailbreak","slug":"pruning-for-protection-increasing-jailbreak","title":"Pruning for Protection: Increasing Jailbreak Resistance in Aligned LLMs Without Fine-Tuning","date":"2024-01-19","arxiv_id":"2401.10862","repositories_listed":1,"syntology":null},{"url":"/paper/model-compression-techniques-in-biometrics","slug":"model-compression-techniques-in-biometrics","title":"Model Compression Techniques in Biometrics Applications: A Survey","date":"2024-01-18","arxiv_id":"2401.10139","repositories_listed":1,"syntology":null},{"url":"/paper/symbolnet-neural-symbolic-regression-with","slug":"symbolnet-neural-symbolic-regression-with","title":"SymbolNet: Neural Symbolic Regression with Adaptive Dynamic Pruning for Compression","date":"2024-01-18","arxiv_id":"2401.09949","repositories_listed":1,"syntology":null},{"url":"/paper/dynamic-dnns-and-runtime-management-for","slug":"dynamic-dnns-and-runtime-management-for","title":"Dynamic DNNs and Runtime Management for Efficient Inference on Mobile/Embedded Devices","date":"2024-01-17","arxiv_id":"2401.08965","repositories_listed":1,"syntology":null},{"url":"/paper/knowledge-translation-a-new-pathway-for-model","slug":"knowledge-translation-a-new-pathway-for-model","title":"Knowledge Translation: A New Pathway for Model Compression","date":"2024-01-11","arxiv_id":"2401.05772","repositories_listed":1,"syntology":null},{"url":"/paper/retraining-free-model-quantization-via-one","slug":"retraining-free-model-quantization-via-one","title":"Retraining-free Model Quantization via One-Shot Weight-Coupling Learning","date":"2024-01-03","arxiv_id":"2401.01543","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/retraining-free-model-quantization-via-one#ran","syntology_url":"https://syntology.ai/paper/2401.01543","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.01543"}},"official":{"repos":["1hunters/retraining-free-quantization"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/generative-model-based-feature-knowledge","slug":"generative-model-based-feature-knowledge","title":"Generative Model-based Feature Knowledge Distillation for Action Recognition","date":"2023-12-14","arxiv_id":"2312.08644","repositories_listed":1,"syntology":null},{"url":"/paper/rethinking-compression-reduced-order","slug":"rethinking-compression-reduced-order","title":"Rethinking Compression: Reduced Order Modelling of Latent Features in Large Language Models","date":"2023-12-12","arxiv_id":"2312.07046","repositories_listed":1,"syntology":null},{"url":"/paper/understanding-the-effect-of-model-compression","slug":"understanding-the-effect-of-model-compression","title":"Understanding the Effect of Model Compression on Social Bias in Large Language Models","date":"2023-12-09","arxiv_id":"2312.05662","repositories_listed":1,"syntology":null},{"url":"/paper/language-model-knowledge-distillation-for","slug":"language-model-knowledge-distillation-for","title":"Language Model Knowledge Distillation for Efficient Question Answering in Spanish","date":"2023-12-07","arxiv_id":"2312.04193","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":2,"phrase":"2 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; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/language-model-knowledge-distillation-for#ran","syntology_url":"https://syntology.ai/paper/2312.04193","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.04193"}},"official":{"repos":["adrianbzg/tinyroberta-distillation-qa-es"],"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"]}}},{"url":"/paper/physics-inspired-criterion-for-pruning","slug":"physics-inspired-criterion-for-pruning","title":"Physics Inspired Criterion for Pruning-Quantization Joint Learning","date":"2023-12-01","arxiv_id":"2312.00851","repositories_listed":1,"syntology":null},{"url":"/paper/towards-higher-ranks-via-adversarial-weight-1","slug":"towards-higher-ranks-via-adversarial-weight-1","title":"Towards Higher Ranks via Adversarial Weight Pruning","date":"2023-11-29","arxiv_id":"2311.17493","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/towards-higher-ranks-via-adversarial-weight-1#ran","syntology_url":"https://syntology.ai/paper/2311.17493","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.17493"}},"official":{"repos":["huawei-noah/Efficient-Computing"],"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/compact-3d-gaussian-representation-for","slug":"compact-3d-gaussian-representation-for","title":"Compact 3D Gaussian Representation for Radiance Field","date":"2023-11-22","arxiv_id":"2311.13681","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":4,"n_pointer_only":7,"phrase":"5 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; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/compact-3d-gaussian-representation-for#ran","syntology_url":"https://syntology.ai/paper/2311.13681","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.13681"}},"official":{"repos":["maincold2/Compact-3DGS"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/lq-lora-low-rank-plus-quantized-matrix","slug":"lq-lora-low-rank-plus-quantized-matrix","title":"LQ-LoRA: Low-rank Plus Quantized Matrix Decomposition for Efficient Language Model Finetuning","date":"2023-11-20","arxiv_id":"2311.12023","repositories_listed":1,"syntology":{"n":12,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"9 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; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/lq-lora-low-rank-plus-quantized-matrix#ran","syntology_url":"https://syntology.ai/paper/2311.12023","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.12023"}},"official":{"repos":["hanguo97/lq-lora"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/a-corrected-expected-improvement-acquisition","slug":"a-corrected-expected-improvement-acquisition","title":"A Corrected Expected Improvement Acquisition Function Under Noisy Observations","date":"2023-10-08","arxiv_id":"2310.05166","repositories_listed":1,"syntology":null},{"url":"/paper/training-dynamic-models-using-early-exits-for","slug":"training-dynamic-models-using-early-exits-for","title":"Training dynamic models using early exits for automatic speech recognition on resource-constrained devices","date":"2023-09-18","arxiv_id":"2309.09546","repositories_listed":1,"syntology":null},{"url":"/paper/compressing-vision-transformers-for-low","slug":"compressing-vision-transformers-for-low","title":"Compressing Vision Transformers for Low-Resource Visual Learning","date":"2023-09-05","arxiv_id":"2309.02617","repositories_listed":1,"syntology":null},{"url":"/paper/an-empirical-study-of-clip-for-text-based","slug":"an-empirical-study-of-clip-for-text-based","title":"An Empirical Study of CLIP for Text-based Person Search","date":"2023-08-19","arxiv_id":"2308.10045","repositories_listed":1,"syntology":null},{"url":"/paper/diffusion-models-for-image-restoration-and","slug":"diffusion-models-for-image-restoration-and","title":"Diffusion Models for Image Restoration and Enhancement -- A Comprehensive Survey","date":"2023-08-18","arxiv_id":"2308.09388","repositories_listed":1,"syntology":null},{"url":"/paper/resource-constrained-model-compression-via","slug":"resource-constrained-model-compression-via","title":"Resource Constrained Model Compression via Minimax Optimization for Spiking Neural Networks","date":"2023-08-09","arxiv_id":"2308.04672","repositories_listed":1,"syntology":null},{"url":"/paper/knowledge-preserving-pruning-for-pre-trained","slug":"knowledge-preserving-pruning-for-pre-trained","title":"Accurate Retraining-free Pruning for Pretrained Encoder-based Language Models","date":"2023-08-07","arxiv_id":"2308.03449","repositories_listed":1,"syntology":{"n":16,"n_ran":12,"n_constructed":0,"n_ran_checked":12,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":16,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/knowledge-preserving-pruning-for-pre-trained#ran","syntology_url":"https://syntology.ai/paper/2308.03449","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.03449"}},"official":{"repos":["snudm-starlab/k-prune"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/cpet-effective-parameter-efficient-tuning-for","slug":"cpet-effective-parameter-efficient-tuning-for","title":"CA-LoRA: Adapting Existing LoRA for Compressed LLMs to Enable Efficient Multi-Tasking on Personal Devices","date":"2023-07-15","arxiv_id":"2307.07705","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":7,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/cpet-effective-parameter-efficient-tuning-for#ran","syntology_url":"https://syntology.ai/paper/2307.07705","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.07705"}},"official":{"repos":["thunlp/ca-lora"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/distilled-pruning-using-synthetic-data-to-win","slug":"distilled-pruning-using-synthetic-data-to-win","title":"Distilled Pruning: Using Synthetic Data to Win the Lottery","date":"2023-07-07","arxiv_id":"2307.03364","repositories_listed":1,"syntology":null},{"url":"/paper/distilling-universal-and-joint-knowledge-for","slug":"distilling-universal-and-joint-knowledge-for","title":"Distilling Universal and Joint Knowledge for Cross-Domain Model Compression on Time Series Data","date":"2023-07-07","arxiv_id":"2307.03347","repositories_listed":1,"syntology":null},{"url":"/paper/an-efficient-sparse-inference-software","slug":"an-efficient-sparse-inference-software","title":"An Efficient Sparse Inference Software Accelerator for Transformer-based Language Models on CPUs","date":"2023-06-28","arxiv_id":"2306.16601","repositories_listed":1,"syntology":null},{"url":"/paper/constraint-aware-and-ranking-distilled-token","slug":"constraint-aware-and-ranking-distilled-token","title":"Constraint-aware and Ranking-distilled Token Pruning for Efficient Transformer Inference","date":"2023-06-26","arxiv_id":"2306.14393","repositories_listed":1,"syntology":null},{"url":"/paper/data-free-backbone-fine-tuning-for-pruned","slug":"data-free-backbone-fine-tuning-for-pruned","title":"Data-Free Backbone Fine-Tuning for Pruned Neural Networks","date":"2023-06-22","arxiv_id":"2306.12881","repositories_listed":1,"syntology":null}],"record_sha256":"799ae5c04a0c608f3fb75e2a103dabe4f6ba75497bedbb7db321e45692d0d742","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}