{"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":"/method/knowledge-distillation/papers/3","list_of":"/method/knowledge-distillation","method":"Knowledge Distillation","archive":{"snapshot":"2025-07-28"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"date (newest first), then slug","page":3,"pages_in_order":31,"rows_per_page":100,"rows":[201,300],"of":3071,"counts":{"archive_papers_tagged":3071,"with_a_code_link":1258,"where_syntology_ran_a_sample":320,"not_listed_spam_title":0,"listed":3071,"listed_where_code_ran":320,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":276,"every_run_a_failure_of_syntologys_instrument":44,"listed_with_a_run_with_no_instrument_failure":276,"listed_every_run_a_failure_of_syntologys_instrument":44,"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":"/method/knowledge-distillation","prev":"/method/knowledge-distillation/papers/2","next":"/method/knowledge-distillation/papers/4","papers":[{"paper":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","n_code_links":0,"syntology":null},{"paper":null,"slug":"mamba-base-pkd-for-efficient-knowledge","title":"Mamba base PKD for efficient knowledge compression","date":"2025-03-03","arxiv_id":"2503.01727","n_code_links":0,"syntology":null},{"paper":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","n_code_links":0,"syntology":null},{"paper":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","n_code_links":0,"syntology":null},{"paper":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","n_code_links":0,"syntology":null},{"paper":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","n_code_links":0,"syntology":null},{"paper":"/paper/advantage-guided-distillation-for-preference","slug":"advantage-guided-distillation-for-preference","title":"Advantage-Guided Distillation for Preference Alignment in Small Language Models","date":"2025-02-25","arxiv_id":"2502.17927","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"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","official":{"repos":["slit-ai/adpa"],"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"]}}},{"paper":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","n_code_links":0,"syntology":null},{"paper":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","n_code_links":0,"syntology":null},{"paper":"/paper/climb-3d-continual-learning-for-imbalanced-3d","slug":"climb-3d-continual-learning-for-imbalanced-3d","title":"CLIMB-3D: Continual Learning for Imbalanced 3D Instance Segmentation","date":"2025-02-24","arxiv_id":"2502.17429","n_code_links":1,"syntology":null},{"paper":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","n_code_links":0,"syntology":null},{"paper":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","n_code_links":0,"syntology":null},{"paper":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","n_code_links":0,"syntology":null},{"paper":null,"slug":"knowledge-distillation-with-training-wheels","title":"Knowledge Distillation with Training Wheels","date":"2025-02-24","arxiv_id":"2502.17717","n_code_links":0,"syntology":null},{"paper":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","n_code_links":0,"syntology":null},{"paper":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","n_code_links":0,"syntology":null},{"paper":"/paper/a-knowledge-distillation-based-approach-to","slug":"a-knowledge-distillation-based-approach-to","title":"A Knowledge Distillation-Based Approach to Enhance Transparency of Classifier Models","date":"2025-02-21","arxiv_id":"2502.15959","n_code_links":1,"syntology":null},{"paper":"/paper/scaling-sparse-and-dense-retrieval-in-decoder","slug":"scaling-sparse-and-dense-retrieval-in-decoder","title":"Scaling Sparse and Dense Retrieval in Decoder-Only LLMs","date":"2025-02-21","arxiv_id":"2502.15526","n_code_links":2,"syntology":null},{"paper":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","n_code_links":0,"syntology":null},{"paper":"/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","n_code_links":0,"syntology":{"ran":3,"of":5,"n_ran_checked":3,"n_instrument":0,"unverified":2,"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","official":null}},{"paper":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","n_code_links":0,"syntology":null},{"paper":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","n_code_links":0,"syntology":null},{"paper":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","n_code_links":0,"syntology":null},{"paper":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","n_code_links":0,"syntology":null},{"paper":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","n_code_links":0,"syntology":null},{"paper":"/paper/jl1-cd-a-new-benchmark-for-remote-sensing","slug":"jl1-cd-a-new-benchmark-for-remote-sensing","title":"JL1-CD: A New Benchmark for Remote Sensing Change Detection and a Robust Multi-Teacher Knowledge Distillation Framework","date":"2025-02-19","arxiv_id":"2502.13407","n_code_links":1,"syntology":null},{"paper":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","n_code_links":0,"syntology":null},{"paper":"/paper/towards-vector-optimization-on-low","slug":"towards-vector-optimization-on-low","title":"Towards Vector Optimization on Low-Dimensional Vector Symbolic Architecture","date":"2025-02-19","arxiv_id":"2502.14075","n_code_links":1,"syntology":null},{"paper":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","n_code_links":0,"syntology":null},{"paper":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","n_code_links":0,"syntology":null},{"paper":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","n_code_links":0,"syntology":null},{"paper":"/paper/can-llm-watermarks-robustly-prevent","slug":"can-llm-watermarks-robustly-prevent","title":"Can LLM Watermarks Robustly Prevent Unauthorized Knowledge Distillation?","date":"2025-02-17","arxiv_id":"2502.11598","n_code_links":1,"syntology":{"ran":0,"of":3,"n_ran_checked":0,"n_instrument":0,"unverified":3,"pointer_only":3,"phrase":"0 ran · 3 unverified","official":{"repos":["thu-bpm/watermark-radioactivity-attack"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":[]}}},{"paper":"/paper/leave-no-one-behind-enhancing-diversity-while","slug":"leave-no-one-behind-enhancing-diversity-while","title":"Leave No One Behind: Enhancing Diversity While Maintaining Accuracy in Social Recommendation","date":"2025-02-17","arxiv_id":"2502.11374","n_code_links":1,"syntology":null},{"paper":"/paper/warmup-distill-bridge-the-distribution","slug":"warmup-distill-bridge-the-distribution","title":"Warmup-Distill: Bridge the Distribution Mismatch between Teacher and Student before Knowledge Distillation","date":"2025-02-17","arxiv_id":"2502.11766","n_code_links":1,"syntology":null},{"paper":"/paper/davimnet-ssms-based-domain-adaptive-object","slug":"davimnet-ssms-based-domain-adaptive-object","title":"DA-Mamba: Domain Adaptive Hybrid Mamba-Transformer Based One-Stage Object Detection","date":"2025-02-16","arxiv_id":"2502.11178","n_code_links":2,"syntology":null},{"paper":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","n_code_links":0,"syntology":null},{"paper":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","n_code_links":0,"syntology":null},{"paper":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","n_code_links":0,"syntology":null},{"paper":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","n_code_links":0,"syntology":null},{"paper":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","n_code_links":0,"syntology":null},{"paper":null,"slug":"llm-pretraining-with-continuous-concepts","title":"LLM Pretraining with Continuous Concepts","date":"2025-02-12","arxiv_id":"2502.08524","n_code_links":0,"syntology":null},{"paper":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","n_code_links":0,"syntology":null},{"paper":"/paper/drop-poison-dilution-via-knowledge","slug":"drop-poison-dilution-via-knowledge","title":"DROP: Poison Dilution via Knowledge Distillation for Federated Learning","date":"2025-02-10","arxiv_id":"2502.07011","n_code_links":1,"syntology":null},{"paper":null,"slug":"progressive-collaborative-and-semantic","title":"Progressive Collaborative and Semantic Knowledge Fusion for Generative Recommendation","date":"2025-02-10","arxiv_id":"2502.06269","n_code_links":0,"syntology":null},{"paper":null,"slug":"rationalization-models-for-text-to-sql","title":"Rationalization Models for Text-to-SQL","date":"2025-02-10","arxiv_id":"2502.06759","n_code_links":0,"syntology":null},{"paper":"/paper/audio-visual-representation-learning-via","slug":"audio-visual-representation-learning-via","title":"Audio-Visual Representation Learning via Knowledge Distillation from Speech Foundation Models","date":"2025-02-09","arxiv_id":"2502.05766","n_code_links":1,"syntology":null},{"paper":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","n_code_links":0,"syntology":null},{"paper":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","n_code_links":0,"syntology":null},{"paper":"/paper/event-stream-based-visual-object-tracking","slug":"event-stream-based-visual-object-tracking","title":"Event Stream-based Visual Object Tracking: HDETrack V2 and A High-Definition Benchmark","date":"2025-02-08","arxiv_id":"2502.05574","n_code_links":1,"syntology":null},{"paper":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","n_code_links":0,"syntology":null},{"paper":"/paper/multilingual-non-autoregressive-machine","slug":"multilingual-non-autoregressive-machine","title":"Multilingual Non-Autoregressive Machine Translation without Knowledge Distillation","date":"2025-02-06","arxiv_id":"2502.04537","n_code_links":1,"syntology":null},{"paper":"/paper/towards-unified-music-emotion-recognition","slug":"towards-unified-music-emotion-recognition","title":"Towards Unified Music Emotion Recognition across Dimensional and Categorical Models","date":"2025-02-06","arxiv_id":"2502.03979","n_code_links":1,"syntology":{"ran":4,"of":5,"n_ran_checked":4,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["AMAAI-Lab/Music2Emotion"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":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","n_code_links":0,"syntology":null},{"paper":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","n_code_links":0,"syntology":null},{"paper":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","n_code_links":0,"syntology":null},{"paper":"/paper/fedhpd-heterogeneous-federated-reinforcement","slug":"fedhpd-heterogeneous-federated-reinforcement","title":"FedHPD: Heterogeneous Federated Reinforcement Learning via Policy Distillation","date":"2025-02-02","arxiv_id":"2502.00870","n_code_links":1,"syntology":null},{"paper":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","n_code_links":0,"syntology":null},{"paper":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","n_code_links":0,"syntology":null},{"paper":"/paper/robust-knowledge-distillation-in-federated","slug":"robust-knowledge-distillation-in-federated","title":"Robust Knowledge Distillation in Federated Learning: Counteracting Backdoor Attacks","date":"2025-02-01","arxiv_id":"2502.00587","n_code_links":1,"syntology":null},{"paper":"/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","n_code_links":0,"syntology":null},{"paper":"/paper/distilling-knowledge-for-designing","slug":"distilling-knowledge-for-designing","title":"Distilling Knowledge for Designing Computational Imaging Systems","date":"2025-01-29","arxiv_id":"2501.17898","n_code_links":1,"syntology":null},{"paper":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","n_code_links":0,"syntology":null},{"paper":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","n_code_links":0,"syntology":null},{"paper":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","n_code_links":0,"syntology":null},{"paper":null,"slug":"fedefm-federated-endovascular-foundation","title":"FedEFM: Federated Endovascular Foundation Model with Unseen Data","date":"2025-01-28","arxiv_id":"2501.16992","n_code_links":0,"syntology":null},{"paper":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","n_code_links":0,"syntology":null},{"paper":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","n_code_links":0,"syntology":null},{"paper":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","n_code_links":0,"syntology":null},{"paper":"/paper/return-of-the-encoder-maximizing-parameter","slug":"return-of-the-encoder-maximizing-parameter","title":"Return of the Encoder: Maximizing Parameter Efficiency for SLMs","date":"2025-01-27","arxiv_id":"2501.16273","n_code_links":1,"syntology":null},{"paper":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","n_code_links":0,"syntology":null},{"paper":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","n_code_links":0,"syntology":null},{"paper":null,"slug":"pre-trained-model-guided-mixture-knowledge","title":"Pre-trained Model Guided Mixture Knowledge Distillation for Adversarial Federated Learning","date":"2025-01-25","arxiv_id":"2501.15257","n_code_links":0,"syntology":null},{"paper":null,"slug":"remining-hard-negatives-for-generative-pseudo","title":"Remining Hard Negatives for Generative Pseudo Labeled Domain Adaptation","date":"2025-01-24","arxiv_id":"2501.14434","n_code_links":0,"syntology":null},{"paper":"/paper/multi-aspect-knowledge-distillation-with","slug":"multi-aspect-knowledge-distillation-with","title":"Multi-aspect Knowledge Distillation with Large Language Model","date":"2025-01-23","arxiv_id":"2501.13341","n_code_links":1,"syntology":null},{"paper":null,"slug":"unlearning-clients-features-and-samples-in","title":"Unlearning Clients, Features and Samples in Vertical Federated Learning","date":"2025-01-23","arxiv_id":"2501.13683","n_code_links":0,"syntology":null},{"paper":null,"slug":"extracting-general-use-transformers-for-low","title":"Extracting General-use Transformers for Low-resource Languages via Knowledge Distillation","date":"2025-01-22","arxiv_id":"2501.12660","n_code_links":0,"syntology":null},{"paper":null,"slug":"lit-delving-into-a-simplified-linear","title":"LiT: Delving into a Simplified Linear Diffusion Transformer for Image Generation","date":"2025-01-22","arxiv_id":"2501.12976","n_code_links":0,"syntology":null},{"paper":null,"slug":"toward-model-centric-heterogeneous-federated","title":"Toward Model-centric Heterogeneous Federated Graph Learning: A Knowledge-driven Approach","date":"2025-01-22","arxiv_id":"2501.12624","n_code_links":0,"syntology":null},{"paper":null,"slug":"dna-1-0-technical-report","title":"DNA 1.0 Technical Report","date":"2025-01-18","arxiv_id":"2501.10648","n_code_links":0,"syntology":null},{"paper":"/paper/class-incremental-fault-diagnosis-under","slug":"class-incremental-fault-diagnosis-under","title":"Class Incremental Fault Diagnosis under Limited Fault Data via Supervised Contrastive Knowledge Distillation","date":"2025-01-16","arxiv_id":"2501.09525","n_code_links":1,"syntology":null},{"paper":null,"slug":"enhancing-generalization-in-chain-of-thought","title":"Enhancing Generalization in Chain of Thought Reasoning for Smaller Models","date":"2025-01-16","arxiv_id":"2501.09804","n_code_links":0,"syntology":null},{"paper":null,"slug":"knowledge-distillation-for-image-restoration","title":"Knowledge Distillation for Image Restoration : Simultaneous Learning from Degraded and Clean Images","date":"2025-01-16","arxiv_id":"2501.09268","n_code_links":0,"syntology":null},{"paper":null,"slug":"soft-knowledge-distillation-with-multi","title":"Soft Knowledge Distillation with Multi-Dimensional Cross-Net Attention for Image Restoration Models Compression","date":"2025-01-16","arxiv_id":"2501.09321","n_code_links":0,"syntology":null},{"paper":"/paper/efficient-traffic-prediction-through-spatio","slug":"efficient-traffic-prediction-through-spatio","title":"Efficient Traffic Prediction Through Spatio-Temporal Distillation","date":"2025-01-15","arxiv_id":"2501.10459","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":1,"phrase":"0 ran · 1 unverified","official":{"repos":["lizzyhku/TP"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":"/paper/induced-model-matching-restricted-models-help","slug":"induced-model-matching-restricted-models-help","title":"Induced Model Matching: Restricted Models Help Train Full-Featured Models","date":"2025-01-15","arxiv_id":null,"n_code_links":3,"syntology":null},{"paper":"/paper/towards-fast-specialized-machine-learning","slug":"towards-fast-specialized-machine-learning","title":"Towards Fast, Specialized Machine Learning Force Fields: Distilling Foundation Models via Energy Hessians","date":"2025-01-15","arxiv_id":"2501.09009","n_code_links":1,"syntology":null},{"paper":"/paper/vect-gan-a-variationally-encoded-generative","slug":"vect-gan-a-variationally-encoded-generative","title":"VECT-GAN: A variationally encoded generative model for overcoming data scarcity in pharmaceutical science","date":"2025-01-15","arxiv_id":"2501.08995","n_code_links":1,"syntology":null},{"paper":null,"slug":"balance-divergence-for-knowledge-distillation","title":"Balance Divergence for Knowledge Distillation","date":"2025-01-14","arxiv_id":"2501.07804","n_code_links":0,"syntology":null},{"paper":"/paper/self-attentive-spatio-temporal-calibration","slug":"self-attentive-spatio-temporal-calibration","title":"Self-Attentive Spatio-Temporal Calibration for Precise Intermediate Layer Matching in ANN-to-SNN Distillation","date":"2025-01-14","arxiv_id":"2501.08049","n_code_links":1,"syntology":null},{"paper":null,"slug":"dual-scale-aware-adaptive-masked-knowledge","title":"Dual Scale-aware Adaptive Masked Knowledge Distillation for Object Detection","date":"2025-01-13","arxiv_id":"2501.07101","n_code_links":0,"syntology":null},{"paper":null,"slug":"knowledge-distillation-and-enhanced-subdomain","title":"Knowledge Distillation and Enhanced Subdomain Adaptation Using Graph Convolutional Network for Resource-Constrained Bearing Fault Diagnosis","date":"2025-01-13","arxiv_id":"2501.07173","n_code_links":0,"syntology":null},{"paper":null,"slug":"research-on-the-online-update-method-for","title":"Research on the Online Update Method for Retrieval-Augmented Generation (RAG) Model with Incremental Learning","date":"2025-01-13","arxiv_id":"2501.07063","n_code_links":0,"syntology":null},{"paper":null,"slug":"rethinking-knowledge-in-distillation-an-in","title":"Rethinking Knowledge in Distillation: An In-context Sample Retrieval Perspective","date":"2025-01-13","arxiv_id":"2501.07040","n_code_links":0,"syntology":null},{"paper":null,"slug":"application-of-vision-language-model-to","title":"Application of Vision-Language Model to Pedestrians Behavior and Scene Understanding in Autonomous Driving","date":"2025-01-12","arxiv_id":"2501.06680","n_code_links":0,"syntology":null},{"paper":"/paper/from-my-view-to-yours-ego-augmented-learning","slug":"from-my-view-to-yours-ego-augmented-learning","title":"From My View to Yours: Ego-Augmented Learning in Large Vision Language Models for Understanding Exocentric Daily Living Activities","date":"2025-01-10","arxiv_id":"2501.05711","n_code_links":1,"syntology":null},{"paper":null,"slug":"overcoming-language-priors-for-visual","title":"Overcoming Language Priors for Visual Question Answering Based on Knowledge Distillation","date":"2025-01-10","arxiv_id":"2501.05690","n_code_links":0,"syntology":null},{"paper":"/paper/llmquoter-enhancing-rag-capabilities-through","slug":"llmquoter-enhancing-rag-capabilities-through","title":"LLMQuoter: Enhancing RAG Capabilities Through Efficient Quote Extraction From Large Contexts","date":"2025-01-09","arxiv_id":"2501.05554","n_code_links":1,"syntology":null},{"paper":null,"slug":"federated-fine-tuning-of-llms-framework","title":"Federated Fine-Tuning of LLMs: Framework Comparison and Research Directions","date":"2025-01-08","arxiv_id":"2501.04436","n_code_links":0,"syntology":null},{"paper":"/paper/a-diversity-enhanced-knowledge-distillation","slug":"a-diversity-enhanced-knowledge-distillation","title":"A Diversity-Enhanced Knowledge Distillation Model for Practical Math Word Problem Solving","date":"2025-01-07","arxiv_id":"2501.03670","n_code_links":1,"syntology":null},{"paper":"/paper/concealgs-concealing-invisible-copyright","slug":"concealgs-concealing-invisible-copyright","title":"ConcealGS: Concealing Invisible Copyright Information in 3D Gaussian Splatting","date":"2025-01-07","arxiv_id":"2501.03605","n_code_links":1,"syntology":null}],"record_sha256":"5b842a77b6370106770563193b317e7f1f64d1d389a1959115189f1648e580ef","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}