{"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/knowledge-distillation/papers/20","list_of":"/task/knowledge-distillation","task":"Knowledge Distillation","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":20,"pages_in_order":43,"rows_per_page":100,"rows":[1901,2000],"of":4240,"counts":{"archive_papers_tagged":4240,"with_a_code_link":1740,"where_syntology_ran_a_sample":451,"not_listed_spam_title":0,"listed":4240,"listed_where_code_ran":451,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":380,"every_run_a_failure_of_syntologys_instrument":71,"listed_with_a_run_with_no_instrument_failure":380,"listed_every_run_a_failure_of_syntologys_instrument":71,"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/knowledge-distillation","prev":"/task/knowledge-distillation/papers/19","next":"/task/knowledge-distillation/papers/21","papers":[{"url":null,"slug":"city2scene-improving-acoustic-scene","title":"Improving Acoustic Scene Classification with City Features","date":"2025-03-21","arxiv_id":"2503.16862","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-intent-based-filtering-for-multi","title":"Efficient Intent-Based Filtering for Multi-Party Conversations Using Knowledge Distillation from LLMs","date":"2025-03-21","arxiv_id":"2503.17336","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-knowledge-distillation-via","title":"Efficient Knowledge Distillation via Curriculum Extraction","date":"2025-03-21","arxiv_id":"2503.17494","repositories_listed":0,"syntology":null},{"url":null,"slug":"inhibidistilbert-knowledge-distillation-for-a","title":"InhibiDistilbert: Knowledge Distillation for a ReLU and Addition-based Transformer","date":"2025-03-20","arxiv_id":"2503.15983","repositories_listed":0,"syntology":null},{"url":null,"slug":"advancing-deep-learning-through-probability","title":"Advancing Deep Learning through Probability Engineering: A Pragmatic Paradigm for Modern AI","date":"2025-03-19","arxiv_id":"2503.18958","repositories_listed":0,"syntology":null},{"url":null,"slug":"distilling-3d-distinctive-local-descriptors","title":"Distilling 3D distinctive local descriptors for 6D pose estimation","date":"2025-03-19","arxiv_id":"2503.15106","repositories_listed":0,"syntology":null},{"url":null,"slug":"kogner-a-novel-framework-for-knowledge-graph","title":"KoGNER: A Novel Framework for Knowledge Graph Distillation on Biomedical Named Entity Recognition","date":"2025-03-19","arxiv_id":"2503.15737","repositories_listed":0,"syntology":null},{"url":null,"slug":"ensemble-knowledge-distillation-for-machine","title":"Ensemble Knowledge Distillation for Machine Learning Interatomic Potentials","date":"2025-03-18","arxiv_id":"2503.14293","repositories_listed":0,"syntology":null},{"url":null,"slug":"scjd-sparse-correlation-and-joint","title":"SCJD: Sparse Correlation and Joint Distillation for Efficient 3D Human Pose Estimation","date":"2025-03-18","arxiv_id":"2503.14097","repositories_listed":0,"syntology":null},{"url":null,"slug":"uncertainty-aware-knowledge-distillation-for","title":"Uncertainty-Aware Knowledge Distillation for Compact and Efficient 6DoF Pose Estimation","date":"2025-03-17","arxiv_id":"2503.13053","repositories_listed":0,"syntology":null},{"url":null,"slug":"creating-a-good-teacher-for-knowledge","title":"Creating a Good Teacher for Knowledge Distillation in Acoustic Scene Classification","date":"2025-03-14","arxiv_id":"2503.11363","repositories_listed":0,"syntology":null},{"url":null,"slug":"enabling-weak-client-participation-via-on","title":"Enabling Weak Client Participation via On-device Knowledge Distillation in Heterogenous Federated Learning","date":"2025-03-14","arxiv_id":"2503.11151","repositories_listed":0,"syntology":null},{"url":null,"slug":"cleverdistiller-simple-and-spatially","title":"CleverDistiller: Simple and Spatially Consistent Cross-modal Distillation","date":"2025-03-12","arxiv_id":"2503.09878","repositories_listed":0,"syntology":null},{"url":null,"slug":"unified-locomotion-transformer-with","title":"Unified Locomotion Transformer with Simultaneous Sim-to-Real Transfer for Quadrupeds","date":"2025-03-12","arxiv_id":"2503.08997","repositories_listed":0,"syntology":null},{"url":null,"slug":"vi-lad-vision-language-attention-distillation","title":"Vi-LAD: Vision-Language Attention Distillation for Socially-Aware Robot Navigation in Dynamic Environments","date":"2025-03-12","arxiv_id":"2503.09820","repositories_listed":0,"syntology":null},{"url":null,"slug":"xvlm2vec-adapting-lvlm-based-embedding-models","title":"xVLM2Vec: Adapting LVLM-based embedding models to multilinguality using Self-Knowledge Distillation","date":"2025-03-12","arxiv_id":"2503.09313","repositories_listed":0,"syntology":null},{"url":null,"slug":"adroit-a-self-supervised-framework-for","title":"ADROIT: A Self-Supervised Framework for Learning Robust Representations for Active Learning","date":"2025-03-10","arxiv_id":"2503.07506","repositories_listed":0,"syntology":null},{"url":null,"slug":"cot-drive-efficient-motion-forecasting-for","title":"CoT-Drive: Efficient Motion Forecasting for Autonomous Driving with LLMs and Chain-of-Thought Prompting","date":"2025-03-10","arxiv_id":"2503.07234","repositories_listed":0,"syntology":null},{"url":null,"slug":"distilling-knowledge-into-quantum-vision","title":"Distilling Knowledge into Quantum Vision Transformers for Biomedical Image Classification","date":"2025-03-10","arxiv_id":"2503.07294","repositories_listed":0,"syntology":null},{"url":null,"slug":"ptms-tscil-pre-trained-models-based-class","title":"PTMs-TSCIL Pre-Trained Models Based Class-Incremental Learning","date":"2025-03-10","arxiv_id":"2503.07153","repositories_listed":0,"syntology":null},{"url":null,"slug":"task-specific-knowledge-distillation-from-the","title":"Task-Specific Knowledge Distillation from the Vision Foundation Model for Enhanced Medical Image Segmentation","date":"2025-03-10","arxiv_id":"2503.06976","repositories_listed":0,"syntology":null},{"url":null,"slug":"training-domain-draft-models-for-speculative","title":"Training Domain Draft Models for Speculative Decoding: Best Practices and Insights","date":"2025-03-10","arxiv_id":"2503.07807","repositories_listed":0,"syntology":null},{"url":null,"slug":"asymmetric-decision-making-in-online","title":"Asymmetric Decision-Making in Online Knowledge Distillation:Unifying Consensus and Divergence","date":"2025-03-09","arxiv_id":"2503.06685","repositories_listed":0,"syntology":null},{"url":null,"slug":"causality-enhanced-origin-destination-flow","title":"Causality Enhanced Origin-Destination Flow Prediction in Data-Scarce Cities","date":"2025-03-09","arxiv_id":"2503.06398","repositories_listed":0,"syntology":null},{"url":null,"slug":"hfedckd-toward-robust-heterogeneous-federated","title":"HFedCKD: Toward Robust Heterogeneous Federated Learning via Data-free Knowledge Distillation and Two-way Contrast","date":"2025-03-09","arxiv_id":"2503.06511","repositories_listed":0,"syntology":null},{"url":null,"slug":"small-vision-language-models-a-survey-on","title":"Small Vision-Language Models: A Survey on Compact Architectures and Techniques","date":"2025-03-09","arxiv_id":"2503.10665","repositories_listed":0,"syntology":null},{"url":null,"slug":"acam-kd-adaptive-and-cooperative-attention","title":"ACAM-KD: Adaptive and Cooperative Attention Masking for Knowledge Distillation","date":"2025-03-08","arxiv_id":"2503.06307","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-sam-for-camouflaged-object","title":"Improving SAM for Camouflaged Object Detection via Dual Stream Adapters","date":"2025-03-08","arxiv_id":"2503.06042","repositories_listed":0,"syntology":null},{"url":null,"slug":"no-forgetting-learning-memory-free-continual","title":"No Forgetting Learning: Memory-free Continual Learning","date":"2025-03-06","arxiv_id":"2503.04638","repositories_listed":0,"syntology":null},{"url":null,"slug":"rd-efficient-fpga-deployment-of-learned-image","title":"Lightweight Embedded FPGA Deployment of Learned Image Compression with Knowledge Distillation and Hybrid Quantization","date":"2025-03-05","arxiv_id":"2503.04832","repositories_listed":0,"syntology":null},{"url":"/paper/temporal-separation-with-entropy","slug":"temporal-separation-with-entropy","title":"Temporal Separation with Entropy Regularization for Knowledge Distillation in Spiking Neural Networks","date":"2025-03-05","arxiv_id":"2503.03144","repositories_listed":0,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":1,"n_honours":0,"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; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/temporal-separation-with-entropy#ran","syntology_url":"https://syntology.ai/paper/2503.03144","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.03144"}},"official":null}},{"url":null,"slug":"semantic-prior-distillation-with-vision","title":"Rapid Bone Scintigraphy Enhancement via Semantic Prior Distillation from Segment Anything Model","date":"2025-03-04","arxiv_id":"2503.02321","repositories_listed":0,"syntology":null},{"url":null,"slug":"dilemma-joint-llm-quantization-and","title":"DILEMMA: Joint LLM Quantization and Distributed LLM Inference Over Edge Computing Systems","date":"2025-03-03","arxiv_id":"2503.01704","repositories_listed":0,"syntology":null},{"url":null,"slug":"mamba-base-pkd-for-efficient-knowledge","title":"Mamba base PKD for efficient knowledge compression","date":"2025-03-03","arxiv_id":"2503.01727","repositories_listed":0,"syntology":null},{"url":"/paper/2502-20760","slug":"2502-20760","title":"VRM: Knowledge Distillation via Virtual Relation Matching","date":"2025-02-28","arxiv_id":"2502.20760","repositories_listed":0,"syntology":{"n":3,"n_ran":3,"n_constructed":1,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":1,"n_pointer_only":3,"phrase":"3 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/2502-20760#ran","syntology_url":"https://syntology.ai/paper/2502.20760","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.20760"}},"official":null}},{"url":null,"slug":"beyond-the-tip-of-efficiency-uncovering-the","title":"Beyond the Tip of Efficiency: Uncovering the Submerged Threats of Jailbreak Attacks in Small Language Models","date":"2025-02-27","arxiv_id":"2502.19883","repositories_listed":0,"syntology":null},{"url":null,"slug":"granite-embedding-models","title":"Granite Embedding Models","date":"2025-02-27","arxiv_id":"2502.20204","repositories_listed":0,"syntology":null},{"url":null,"slug":"investigating-and-enhancing-vision-audio","title":"Investigating and Enhancing Vision-Audio Capability in Omnimodal Large Language Models","date":"2025-02-27","arxiv_id":"2503.00059","repositories_listed":0,"syntology":null},{"url":null,"slug":"lightweight-contrastive-distilled-hashing-for","title":"Lightweight Contrastive Distilled Hashing for Online Cross-modal Retrieval","date":"2025-02-27","arxiv_id":"2502.19751","repositories_listed":0,"syntology":null},{"url":null,"slug":"seki-self-evolution-and-knowledge-inspiration","title":"SEKI: Self-Evolution and Knowledge Inspiration based Neural Architecture Search via Large Language Models","date":"2025-02-27","arxiv_id":"2502.20422","repositories_listed":0,"syntology":null},{"url":null,"slug":"xcomps-a-multilingual-benchmark-of-conceptual","title":"XCOMPS: A Multilingual Benchmark of Conceptual Minimal Pairs","date":"2025-02-27","arxiv_id":"2502.19737","repositories_listed":0,"syntology":null},{"url":null,"slug":"winning-big-with-small-models-knowledge","title":"Winning Big with Small Models: Knowledge Distillation vs. Self-Training for Reducing Hallucination in QA Agents","date":"2025-02-26","arxiv_id":"2502.19545","repositories_listed":0,"syntology":null},{"url":null,"slug":"afroxlmr-comet-multilingual-knowledge","title":"AfroXLMR-Comet: Multilingual Knowledge Distillation with Attention Matching for Low-Resource languages","date":"2025-02-25","arxiv_id":"2502.18020","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-transformer-in-transformer-network","title":"A Transformer-in-Transformer Network Utilizing Knowledge Distillation for Image Recognition","date":"2025-02-24","arxiv_id":"2502.16762","repositories_listed":0,"syntology":null},{"url":null,"slug":"cot2align-cross-chain-of-thought-distillation","title":"CoT2Align: Cross-Chain of Thought Distillation via Optimal Transport Alignment for Language Models with Different Tokenizers","date":"2025-02-24","arxiv_id":"2502.16806","repositories_listed":0,"syntology":null},{"url":null,"slug":"implicit-word-reordering-with-knowledge","title":"Implicit Word Reordering with Knowledge Distillation for Cross-Lingual Dependency Parsing","date":"2025-02-24","arxiv_id":"2502.17308","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-the-transferability-of-adversarial-9","title":"Improving the Transferability of Adversarial Examples by Inverse Knowledge Distillation","date":"2025-02-24","arxiv_id":"2502.17003","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-distillation-with-training-wheels","title":"Knowledge Distillation with Training Wheels","date":"2025-02-24","arxiv_id":"2502.17717","repositories_listed":0,"syntology":null},{"url":null,"slug":"pqdast-depth-aware-arbitrary-style-transfer","title":"PQDAST: Depth-Aware Arbitrary Style Transfer for Games via Perceptual Quality-Guided Distillation","date":"2025-02-24","arxiv_id":"2502.16996","repositories_listed":0,"syntology":null},{"url":null,"slug":"edocnet-efficient-datasheet-layout-analysis","title":"EDocNet: Efficient Datasheet Layout Analysis Based on Focus and Global Knowledge Distillation","date":"2025-02-23","arxiv_id":"2502.16541","repositories_listed":0,"syntology":null},{"url":null,"slug":"ppc-gpt-federated-task-specific-compression","title":"PPC-GPT: Federated Task-Specific Compression of Large Language Models via Pruning and Chain-of-Thought Distillation","date":"2025-02-21","arxiv_id":"2502.15857","repositories_listed":0,"syntology":null},{"url":null,"slug":"designing-parameter-and-compute-efficient","title":"Designing Parameter and Compute Efficient Diffusion Transformers using Distillation","date":"2025-02-20","arxiv_id":"2502.14226","repositories_listed":0,"syntology":null},{"url":"/paper/efficient-ai-in-practice-training-and","slug":"efficient-ai-in-practice-training-and","title":"Efficient AI in Practice: Training and Deployment of Efficient LLMs for Industry Applications","date":"2025-02-20","arxiv_id":"2502.14305","repositories_listed":0,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/efficient-ai-in-practice-training-and#ran","syntology_url":"https://syntology.ai/paper/2502.14305","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.14305"}},"official":null}},{"url":null,"slug":"modifying-final-splits-of-classification-tree","title":"Modifying Final Splits of Classification Tree for Fine-tuning Subpopulation Target in Policy Making","date":"2025-02-20","arxiv_id":"2502.15072","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-supervised-monocular-depth-estimation-7","title":"Self-supervised Monocular Depth Estimation Robust to Reflective Surface Leveraged by Triplet Mining","date":"2025-02-20","arxiv_id":"2502.14573","repositories_listed":0,"syntology":null},{"url":null,"slug":"timedistill-efficient-long-term-time-series","title":"TimeDistill: Efficient Long-Term Time Series Forecasting with MLP via Cross-Architecture Distillation","date":"2025-02-20","arxiv_id":"2502.15016","repositories_listed":0,"syntology":null},{"url":null,"slug":"vision-foundation-models-in-medical-image","title":"Vision Foundation Models in Medical Image Analysis: Advances and Challenges","date":"2025-02-20","arxiv_id":"2502.14584","repositories_listed":0,"syntology":null},{"url":null,"slug":"capturing-rich-behavior-representations-a","title":"Capturing Rich Behavior Representations: A Dynamic Action Semantic-Aware Graph Transformer for Video Captioning","date":"2025-02-19","arxiv_id":"2502.13754","repositories_listed":0,"syntology":null},{"url":null,"slug":"dynamic-activation-with-knowledge","title":"Dynamic Activation with Knowledge Distillation for Energy-Efficient Spiking NN Ensembles","date":"2025-02-19","arxiv_id":"2502.14023","repositories_listed":0,"syntology":null},{"url":null,"slug":"mambalitesr-image-super-resolution-with-low","title":"MambaLiteSR: Image Super-Resolution with Low-Rank Mamba using Knowledge Distillation","date":"2025-02-19","arxiv_id":"2502.14090","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-semi-supervised-learning-with-zero","title":"Enhancing Semi-supervised Learning with Zero-shot Pseudolabels","date":"2025-02-18","arxiv_id":"2502.12584","repositories_listed":0,"syntology":null},{"url":null,"slug":"every-expert-matters-towards-effective","title":"Every Expert Matters: Towards Effective Knowledge Distillation for Mixture-of-Experts Language Models","date":"2025-02-18","arxiv_id":"2502.12947","repositories_listed":0,"syntology":null},{"url":null,"slug":"integrating-arithmetic-learning-improves","title":"Integrating Arithmetic Learning Improves Mathematical Reasoning in Smaller Models","date":"2025-02-18","arxiv_id":"2502.12855","repositories_listed":0,"syntology":null},{"url":null,"slug":"naturalreasoning-reasoning-in-the-wild-with-2","title":"NaturalReasoning: Reasoning in the Wild with 2.8M Challenging Questions","date":"2025-02-18","arxiv_id":"2502.13124","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-conditional-mutual-information-to","title":"Leveraging Conditional Mutual Information to Improve Large Language Model Fine-Tuning For Classification","date":"2025-02-16","arxiv_id":"2502.11258","repositories_listed":0,"syntology":null},{"url":null,"slug":"smoothing-out-hallucinations-mitigating-llm","title":"Smoothing Out Hallucinations: Mitigating LLM Hallucination with Smoothed Knowledge Distillation","date":"2025-02-16","arxiv_id":"2502.11306","repositories_listed":0,"syntology":null},{"url":null,"slug":"clockdistill-consistent-location-and-context","title":"CLoCKDistill: Consistent Location-and-Context-aware Knowledge Distillation for DETRs","date":"2025-02-15","arxiv_id":"2502.10683","repositories_listed":0,"syntology":null},{"url":null,"slug":"llm-driven-knowledge-distillation-for-dynamic","title":"LLM-driven Knowledge Distillation for Dynamic Text-Attributed Graphs","date":"2025-02-15","arxiv_id":"2502.10914","repositories_listed":0,"syntology":null},{"url":null,"slug":"aide-agentically-improve-visual-language","title":"AIDE: Agentically Improve Visual Language Model with Domain Experts","date":"2025-02-13","arxiv_id":"2502.09051","repositories_listed":0,"syntology":null},{"url":null,"slug":"llm-pretraining-with-continuous-concepts","title":"LLM Pretraining with Continuous Concepts","date":"2025-02-12","arxiv_id":"2502.08524","repositories_listed":0,"syntology":null},{"url":null,"slug":"life-code-central-dogma-modeling-with-multi","title":"Life-Code: Central Dogma Modeling with Multi-Omics Sequence Unification","date":"2025-02-11","arxiv_id":"2502.07299","repositories_listed":0,"syntology":null},{"url":null,"slug":"optimizing-knowledge-distillation-in","title":"Optimizing Knowledge Distillation in Transformers: Enabling Multi-Head Attention without Alignment Barriers","date":"2025-02-11","arxiv_id":"2502.07436","repositories_listed":0,"syntology":null},{"url":null,"slug":"vision-language-models-for-edge-networks-a","title":"Vision-Language Models for Edge Networks: A Comprehensive Survey","date":"2025-02-11","arxiv_id":"2502.07855","repositories_listed":0,"syntology":null},{"url":null,"slug":"progressive-collaborative-and-semantic","title":"Progressive Collaborative and Semantic Knowledge Fusion for Generative Recommendation","date":"2025-02-10","arxiv_id":"2502.06269","repositories_listed":0,"syntology":null},{"url":null,"slug":"rationalization-models-for-text-to-sql","title":"Rationalization Models for Text-to-SQL","date":"2025-02-10","arxiv_id":"2502.06759","repositories_listed":0,"syntology":null},{"url":null,"slug":"contrastive-representation-distillation-via","title":"Contrastive Representation Distillation via Multi-Scale Feature Decoupling","date":"2025-02-09","arxiv_id":"2502.05835","repositories_listed":0,"syntology":null},{"url":null,"slug":"synergistic-effects-of-knowledge-distillation","title":"Synergistic Effects of Knowledge Distillation and Structured Pruning for Self-Supervised Speech Models","date":"2025-02-09","arxiv_id":"2502.05837","repositories_listed":0,"syntology":null},{"url":"/paper/2502-05567","slug":"2502-05567","title":"ATLAS: Autoformalizing Theorems through Lifting, Augmentation, and Synthesis of Data","date":"2025-02-08","arxiv_id":"2502.05567","repositories_listed":0,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/2502-05567#ran","syntology_url":"https://syntology.ai/paper/2502.05567","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.05567"}},"official":null}},{"url":null,"slug":"demystifying-catastrophic-forgetting-in-two","title":"Demystifying Catastrophic Forgetting in Two-Stage Incremental Object Detector","date":"2025-02-08","arxiv_id":"2502.05540","repositories_listed":0,"syntology":null},{"url":null,"slug":"bolt-bootstrap-long-chain-of-thought-in","title":"BOLT: Bootstrap Long Chain-of-Thought in Language Models without Distillation","date":"2025-02-06","arxiv_id":"2502.03860","repositories_listed":0,"syntology":null},{"url":null,"slug":"revisiting-intermediate-layer-matching-in","title":"Revisiting Intermediate-Layer Matching in Knowledge Distillation: Layer-Selection Strategy Doesn't Matter (Much)","date":"2025-02-06","arxiv_id":"2502.04499","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-unified-knowledge-distillation-and-semi","title":"A Unified Knowledge-Distillation and Semi-Supervised Learning Framework to Improve Industrial Ads Delivery Systems","date":"2025-02-05","arxiv_id":"2502.06834","repositories_listed":0,"syntology":null},{"url":null,"slug":"training-an-llm-as-a-judge-model-pipeline","title":"Training an LLM-as-a-Judge Model: Pipeline, Insights, and Practical Lessons","date":"2025-02-05","arxiv_id":"2502.02988","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-framework-for-double-blind-federated","title":"A Framework for Double-Blind Federated Adaptation of Foundation Models","date":"2025-02-03","arxiv_id":"2502.01289","repositories_listed":0,"syntology":null},{"url":null,"slug":"mind-modality-informed-knowledge-distillation","title":"MIND: Modality-Informed Knowledge Distillation Framework for Multimodal Clinical Prediction Tasks","date":"2025-02-03","arxiv_id":"2502.01158","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-method-for-estimating-forest-carbon-storage","title":"A method for estimating forest carbon storage distribution density via artificial intelligence generated content model","date":"2025-02-02","arxiv_id":"2502.00783","repositories_listed":0,"syntology":null},{"url":null,"slug":"role-of-mixup-in-topological-persistence","title":"Role of Mixup in Topological Persistence Based Knowledge Distillation for Wearable Sensor Data","date":"2025-02-02","arxiv_id":"2502.00779","repositories_listed":0,"syntology":null},{"url":null,"slug":"vlm-assisted-continual-learning-for-visual","title":"VLM-Assisted Continual learning for Visual Question Answering in Self-Driving","date":"2025-02-02","arxiv_id":"2502.00843","repositories_listed":0,"syntology":null},{"url":"/paper/mini-resemotenet-leveraging-knowledge","slug":"mini-resemotenet-leveraging-knowledge","title":"Mini-ResEmoteNet: Leveraging Knowledge Distillation for Human-Centered Design","date":"2025-01-30","arxiv_id":"2501.18538","repositories_listed":0,"syntology":null},{"url":null,"slug":"rethinking-the-upsampling-layer-in","title":"Rethinking the Upsampling Layer in Hyperspectral Image Super Resolution","date":"2025-01-30","arxiv_id":"2501.18664","repositories_listed":0,"syntology":null},{"url":null,"slug":"rl-based-query-rewriting-with-distilled-llm","title":"RL-based Query Rewriting with Distilled LLM for online E-Commerce Systems","date":"2025-01-29","arxiv_id":"2501.18056","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-contrastive-teacher-student-framework-for","title":"A Contrastive Teacher-Student Framework for Novelty Detection under Style Shifts","date":"2025-01-28","arxiv_id":"2501.17289","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-knowledge-distillation-of-sam-for","title":"Efficient Knowledge Distillation of SAM for Medical Image Segmentation","date":"2025-01-28","arxiv_id":"2501.16740","repositories_listed":0,"syntology":null},{"url":null,"slug":"fedefm-federated-endovascular-foundation","title":"FedEFM: Federated Endovascular Foundation Model with Unseen Data","date":"2025-01-28","arxiv_id":"2501.16992","repositories_listed":0,"syntology":null},{"url":null,"slug":"heterogeneity-aware-personalized-federated","title":"Heterogeneity-aware Personalized Federated Learning via Adaptive Dual-Agent Reinforcement Learning","date":"2025-01-28","arxiv_id":"2501.16966","repositories_listed":0,"syntology":null},{"url":null,"slug":"taid-temporally-adaptive-interpolated","title":"TAID: Temporally Adaptive Interpolated Distillation for Efficient Knowledge Transfer in Language Models","date":"2025-01-28","arxiv_id":"2501.16937","repositories_listed":0,"syntology":null},{"url":null,"slug":"target-driven-self-distillation-for-partial","title":"Target-driven Self-Distillation for Partial Observed Trajectories Forecasting","date":"2025-01-28","arxiv_id":"2501.16767","repositories_listed":0,"syntology":null},{"url":null,"slug":"pisco-pretty-simple-compression-for-retrieval","title":"PISCO: Pretty Simple Compression for Retrieval-Augmented Generation","date":"2025-01-27","arxiv_id":"2501.16075","repositories_listed":0,"syntology":null},{"url":null,"slug":"scaling-large-vision-language-models-for","title":"Scaling Large Vision-Language Models for Enhanced Multimodal Comprehension In Biomedical Image Analysis","date":"2025-01-26","arxiv_id":"2501.15370","repositories_listed":0,"syntology":null},{"url":null,"slug":"graph-based-cross-domain-knowledge","title":"Graph-Based Cross-Domain Knowledge Distillation for Cross-Dataset Text-to-Image Person Retrieval","date":"2025-01-25","arxiv_id":"2501.15052","repositories_listed":0,"syntology":null}],"record_sha256":"f6acd33935e2763dd2f24e20cafe75e803d2d8db79782fe66496506e88cd12f3","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}