{"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/5","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":5,"pages_in_order":31,"rows_per_page":100,"rows":[401,500],"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/4","next":"/method/knowledge-distillation/papers/6","papers":[{"paper":"/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","n_code_links":1,"syntology":null},{"paper":null,"slug":"information-extraction-from-heterogenous","title":"Information Extraction from Heterogeneous Documents without Ground Truth Labels using Synthetic Label Generation and Knowledge Distillation","date":"2024-11-22","arxiv_id":"2411.14957","n_code_links":0,"syntology":null},{"paper":null,"slug":"rankbygene-gene-guided-histopathology","title":"RankByGene: Gene-Guided Histopathology Representation Learning Through Cross-Modal Ranking Consistency","date":"2024-11-22","arxiv_id":"2411.15076","n_code_links":0,"syntology":null},{"paper":null,"slug":"simplifying-clip-unleashing-the-power-of","title":"Simplifying CLIP: Unleashing the Power of Large-Scale Models on Consumer-level Computers","date":"2024-11-22","arxiv_id":"2411.14789","n_code_links":0,"syntology":null},{"paper":"/paper/biomedcoop-learning-to-prompt-for-biomedical","slug":"biomedcoop-learning-to-prompt-for-biomedical","title":"BiomedCoOp: Learning to Prompt for Biomedical Vision-Language Models","date":"2024-11-21","arxiv_id":"2411.15232","n_code_links":1,"syntology":null},{"paper":null,"slug":"clface-a-scalable-and-resource-efficient","title":"CLFace: A Scalable and Resource-Efficient Continual Learning Framework for Lifelong Face Recognition","date":"2024-11-21","arxiv_id":"2411.13886","n_code_links":0,"syntology":null},{"paper":"/paper/teaching-mlps-to-master-heterogeneous-graph","slug":"teaching-mlps-to-master-heterogeneous-graph","title":"Teaching MLPs to Master Heterogeneous Graph-Structured Knowledge for Efficient and Accurate Inference","date":"2024-11-21","arxiv_id":"2411.14035","n_code_links":1,"syntology":null},{"paper":null,"slug":"explainable-llm-driven-multi-dimensional","title":"Explainable LLM-driven Multi-dimensional Distillation for E-Commerce Relevance Learning","date":"2024-11-20","arxiv_id":"2411.13045","n_code_links":0,"syntology":null},{"paper":null,"slug":"rtsr-a-real-time-super-resolution-model-for","title":"RTSR: A Real-Time Super-Resolution Model for AV1 Compressed Content","date":"2024-11-20","arxiv_id":"2411.13362","n_code_links":0,"syntology":null},{"paper":null,"slug":"just-kiddin-knowledge-infusion-and","title":"Just KIDDIN: Knowledge Infusion and Distillation for Detection of INdecent Memes","date":"2024-11-19","arxiv_id":"2411.12174","n_code_links":0,"syntology":null},{"paper":null,"slug":"reward-modeling-with-ordinal-feedback-wisdom","title":"Reward Modeling with Ordinal Feedback: Wisdom of the Crowd","date":"2024-11-19","arxiv_id":"2411.12843","n_code_links":0,"syntology":null},{"paper":"/paper/federated-incremental-named-entity","slug":"federated-incremental-named-entity","title":"Federated Incremental Named Entity Recognition","date":"2024-11-18","arxiv_id":"2411.11623","n_code_links":1,"syntology":null},{"paper":"/paper/exploring-feature-based-knowledge","slug":"exploring-feature-based-knowledge","title":"Exploring Feature-based Knowledge Distillation for Recommender System: A Frequency Perspective","date":"2024-11-16","arxiv_id":"2411.10676","n_code_links":1,"syntology":{"ran":4,"of":6,"n_ran_checked":4,"n_instrument":0,"unverified":2,"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) · 2 unverified","official":{"repos":["woriazzc/kds"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/hybrid-attention-model-using-feature","slug":"hybrid-attention-model-using-feature","title":"Hybrid Attention Model Using Feature Decomposition and Knowledge Distillation for Glucose Forecasting","date":"2024-11-16","arxiv_id":"2411.10703","n_code_links":1,"syntology":null},{"paper":null,"slug":"multi-perspective-contrastive-logit","title":"Multi-perspective Contrastive Logit Distillation","date":"2024-11-16","arxiv_id":"2411.10693","n_code_links":0,"syntology":null},{"paper":null,"slug":"evidential-federated-learning-for-skin-lesion","title":"Evidential Federated Learning for Skin Lesion Image Classification","date":"2024-11-15","arxiv_id":"2411.10071","n_code_links":0,"syntology":null},{"paper":null,"slug":"mono2stereo-monocular-knowledge-transfer-for","title":"Mono2Stereo: Monocular Knowledge Transfer for Enhanced Stereo Matching","date":"2024-11-14","arxiv_id":"2411.09151","n_code_links":0,"syntology":null},{"paper":null,"slug":"vpbsd-vessel-pattern-based-semi-supervised","title":"VPBSD:Vessel-Pattern-Based Semi-Supervised Distillation for Efficient 3D Microscopic Cerebrovascular Segmentation","date":"2024-11-14","arxiv_id":"2411.09567","n_code_links":0,"syntology":null},{"paper":null,"slug":"dual-head-knowledge-distillation-enhancing","title":"Dual-Head Knowledge Distillation: Enhancing Logits Utilization with an Auxiliary Head","date":"2024-11-13","arxiv_id":"2411.08937","n_code_links":0,"syntology":null},{"paper":null,"slug":"uiformer-a-unified-transformer-based","title":"UIFormer: A Unified Transformer-based Framework for Incremental Few-Shot Object Detection and Instance Segmentation","date":"2024-11-13","arxiv_id":"2411.08569","n_code_links":0,"syntology":null},{"paper":null,"slug":"feature-interaction-fusion-self-distillation","title":"Feature Interaction Fusion Self-Distillation Network For CTR Prediction","date":"2024-11-12","arxiv_id":"2411.07508","n_code_links":0,"syntology":null},{"paper":null,"slug":"joint-diffusion-models-in-continual-learning","title":"Joint Diffusion models in Continual Learning","date":"2024-11-12","arxiv_id":"2411.08224","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-with-less-knowledge-distillation","title":"Learning with Less: Knowledge Distillation from Large Language Models via Unlabeled Data","date":"2024-11-12","arxiv_id":"2411.08028","n_code_links":0,"syntology":null},{"paper":null,"slug":"query-optimization-for-parametric-knowledge","title":"Query Optimization for Parametric Knowledge Refinement in Retrieval-Augmented Large Language Models","date":"2024-11-12","arxiv_id":"2411.07820","n_code_links":0,"syntology":null},{"paper":"/paper/an-efficient-memory-module-for-graph-few-shot","slug":"an-efficient-memory-module-for-graph-few-shot","title":"An Efficient Memory Module for Graph Few-Shot Class-Incremental Learning","date":"2024-11-11","arxiv_id":"2411.06659","n_code_links":1,"syntology":null},{"paper":"/paper/llm-neo-parameter-efficient-knowledge","slug":"llm-neo-parameter-efficient-knowledge","title":"LLM-Neo: Parameter Efficient Knowledge Distillation for Large Language Models","date":"2024-11-11","arxiv_id":"2411.06839","n_code_links":2,"syntology":{"ran":12,"of":12,"n_ran_checked":10,"n_instrument":2,"unverified":0,"pointer_only":1,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":"/paper/scalekd-strong-vision-transformers-could-be","slug":"scalekd-strong-vision-transformers-could-be","title":"ScaleKD: Strong Vision Transformers Could Be Excellent Teachers","date":"2024-11-11","arxiv_id":"2411.06786","n_code_links":1,"syntology":null},{"paper":null,"slug":"cull-mt-compression-using-language-and-layer","title":"CULL-MT: Compression Using Language and Layer pruning for Machine Translation","date":"2024-11-10","arxiv_id":"2411.06506","n_code_links":0,"syntology":null},{"paper":"/paper/over-parameterized-student-model-via-tensor","slug":"over-parameterized-student-model-via-tensor","title":"Over-parameterized Student Model via Tensor Decomposition Boosted Knowledge Distillation","date":"2024-11-10","arxiv_id":"2411.06448","n_code_links":1,"syntology":{"ran":4,"of":7,"n_ran_checked":1,"n_instrument":3,"unverified":3,"pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","official":{"repos":["intell-sci-comput/opdf"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"dynamic-textual-prompt-for-rehearsal-free","title":"Dynamic Textual Prompt For Rehearsal-free Lifelong Person Re-identification","date":"2024-11-09","arxiv_id":"2411.06023","n_code_links":0,"syntology":null},{"paper":null,"slug":"asterisk-keep-it-simple","title":"Asterisk*: Keep it Simple","date":"2024-11-08","arxiv_id":"2411.05691","n_code_links":0,"syntology":null},{"paper":null,"slug":"knowledge-distillation-neural-network-for","title":"Knowledge Distillation Neural Network for Predicting Car-following Behaviour of Human-driven and Autonomous Vehicles","date":"2024-11-08","arxiv_id":"2411.05618","n_code_links":0,"syntology":null},{"paper":null,"slug":"mitigating-hallucination-with-zerog-an","title":"Mitigating Hallucination with ZeroG: An Advanced Knowledge Management Engine","date":"2024-11-08","arxiv_id":"2411.05936","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-document-financial-question-answering","title":"Multi-Document Financial Question Answering using LLMs","date":"2024-11-08","arxiv_id":"2411.07264","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-lifelong-few-shot-customization-of","title":"Towards Lifelong Few-Shot Customization of Text-to-Image Diffusion","date":"2024-11-08","arxiv_id":"2411.05544","n_code_links":0,"syntology":null},{"paper":null,"slug":"gazegen-gaze-driven-user-interaction-for","title":"GazeGen: Gaze-Driven User Interaction for Visual Content Generation","date":"2024-11-07","arxiv_id":"2411.04335","n_code_links":0,"syntology":null},{"paper":null,"slug":"performance-guided-llm-knowledge-distillation","title":"Performance-Guided LLM Knowledge Distillation for Efficient Text Classification at Scale","date":"2024-11-07","arxiv_id":"2411.05045","n_code_links":0,"syntology":null},{"paper":"/paper/towards-competitive-search-relevance-for","slug":"towards-competitive-search-relevance-for","title":"Towards Competitive Search Relevance For Inference-Free Learned Sparse Retrievers","date":"2024-11-07","arxiv_id":"2411.04403","n_code_links":1,"syntology":null},{"paper":null,"slug":"centerness-based-instance-aware-knowledge","title":"Centerness-based Instance-aware Knowledge Distillation with Task-wise Mutual Lifting for Object Detection on Drone Imagery","date":"2024-11-05","arxiv_id":"2411.02861","n_code_links":0,"syntology":null},{"paper":null,"slug":"multimodal-commonsense-knowledge-distillation","title":"Multimodal Commonsense Knowledge Distillation for Visual Question Answering","date":"2024-11-05","arxiv_id":"2411.02722","n_code_links":0,"syntology":null},{"paper":null,"slug":"transformer-based-fault-tolerant-control-for","title":"Transformer-Based Fault-Tolerant Control for Fixed-Wing UAVs Using Knowledge Distillation and In-Context Adaptation","date":"2024-11-05","arxiv_id":"2411.02975","n_code_links":0,"syntology":null},{"paper":"/paper/training-on-the-test-model-contamination-in","slug":"training-on-the-test-model-contamination-in","title":"Training on the Test Model: Contamination in Ranking Distillation","date":"2024-11-04","arxiv_id":"2411.02284","n_code_links":1,"syntology":{"ran":4,"of":8,"n_ran_checked":4,"n_instrument":0,"unverified":4,"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) · 4 unverified","official":{"repos":["Parry-Parry/ContaminatedDistillation"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"adapting-while-learning-grounding-llms-for","title":"Adapting While Learning: Grounding LLMs for Scientific Problems with Intelligent Tool Usage Adaptation","date":"2024-11-01","arxiv_id":"2411.00412","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-building-secure-uav-navigation-with","title":"Towards Building Secure UAV Navigation with FHE-aware Knowledge Distillation","date":"2024-11-01","arxiv_id":"2411.00403","n_code_links":0,"syntology":null},{"paper":"/paper/semantic-knowledge-distillation-for-onboard","slug":"semantic-knowledge-distillation-for-onboard","title":"Semantic Knowledge Distillation for Onboard Satellite Earth Observation Image Classification","date":"2024-10-31","arxiv_id":"2411.00209","n_code_links":1,"syntology":null},{"paper":null,"slug":"the-graph-s-apprentice-teaching-an-llm-low","title":"The Graph's Apprentice: Teaching an LLM Low Level Knowledge for Circuit Quality Estimation","date":"2024-10-30","arxiv_id":"2411.00843","n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-learning-for-medical-text-processing","title":"Deep Learning for Medical Text Processing: BERT Model Fine-Tuning and Comparative Study","date":"2024-10-28","arxiv_id":"2410.20792","n_code_links":0,"syntology":null},{"paper":"/paper/kd-lora-a-hybrid-approach-to-efficient-fine","slug":"kd-lora-a-hybrid-approach-to-efficient-fine","title":"KD-LoRA: A Hybrid Approach to Efficient Fine-Tuning with LoRA and Knowledge Distillation","date":"2024-10-28","arxiv_id":"2410.20777","n_code_links":1,"syntology":null},{"paper":null,"slug":"knowledge-distillation-for-real-time","title":"Knowledge Distillation for Real-Time Classification of Early Media in Voice Communications","date":"2024-10-28","arxiv_id":"2410.21478","n_code_links":0,"syntology":null},{"paper":null,"slug":"relaxed-recursive-transformers-effective","title":"Relaxed Recursive Transformers: Effective Parameter Sharing with Layer-wise LoRA","date":"2024-10-28","arxiv_id":"2410.20672","n_code_links":0,"syntology":null},{"paper":null,"slug":"unveiling-context-aware-criteria-in-self","title":"Unveiling Context-Aware Criteria in Self-Assessing LLMs","date":"2024-10-28","arxiv_id":"2410.21545","n_code_links":0,"syntology":null},{"paper":null,"slug":"switch-studying-with-teacher-for-knowledge","title":"SWITCH: Studying with Teacher for Knowledge Distillation of Large Language Models","date":"2024-10-25","arxiv_id":"2410.19503","n_code_links":0,"syntology":null},{"paper":null,"slug":"aligncap-aligning-speech-emotion-captioning","title":"AlignCap: Aligning Speech Emotion Captioning to Human Preferences","date":"2024-10-24","arxiv_id":"2410.19134","n_code_links":0,"syntology":null},{"paper":null,"slug":"high-dimensional-analysis-of-knowledge","title":"High-dimensional Analysis of Knowledge Distillation: Weak-to-Strong Generalization and Scaling Laws","date":"2024-10-24","arxiv_id":"2410.18837","n_code_links":0,"syntology":null},{"paper":null,"slug":"knowledge-distillation-using-frontier-open","title":"Knowledge Distillation Using Frontier Open-source LLMs: Generalizability and the Role of Synthetic Data","date":"2024-10-24","arxiv_id":"2410.18588","n_code_links":0,"syntology":null},{"paper":"/paper/siked-self-guided-iterative-knowledge","slug":"siked-self-guided-iterative-knowledge","title":"SIKeD: Self-guided Iterative Knowledge Distillation for mathematical reasoning","date":"2024-10-24","arxiv_id":"2410.18574","n_code_links":1,"syntology":null},{"paper":null,"slug":"elaichi-enhancing-low-resource-tts-by","title":"ELAICHI: Enhancing Low-resource TTS by Addressing Infrequent and Low-frequency Character Bigrams","date":"2024-10-23","arxiv_id":"2410.17901","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-active-participant-centric-vertical","title":"Towards Active Participant-Centric Vertical Federated Learning: Some Representations May Be All You Need","date":"2024-10-23","arxiv_id":"2410.17648","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-effective-data-free-knowledge","title":"Towards Effective Data-Free Knowledge Distillation via Diverse Diffusion Augmentation","date":"2024-10-23","arxiv_id":"2410.17606","n_code_links":0,"syntology":null},{"paper":"/paper/attriprompter-auto-prompting-with-attribute","slug":"attriprompter-auto-prompting-with-attribute","title":"AttriPrompter: Auto-Prompting with Attribute Semantics for Zero-shot Nuclei Detection via Visual-Language Pre-trained Models","date":"2024-10-22","arxiv_id":"2410.16820","n_code_links":1,"syntology":null},{"paper":null,"slug":"ck4gen-a-knowledge-distillation-framework-for","title":"CK4Gen: A Knowledge Distillation Framework for Generating High-Utility Synthetic Survival Datasets in Healthcare","date":"2024-10-22","arxiv_id":"2410.16872","n_code_links":0,"syntology":null},{"paper":null,"slug":"model-mimic-attack-knowledge-distillation-for","title":"Model Mimic Attack: Knowledge Distillation for Provably Transferable Adversarial Examples","date":"2024-10-21","arxiv_id":"2410.15889","n_code_links":0,"syntology":null},{"paper":"/paper/gssf-generalized-structural-sparse-function","slug":"gssf-generalized-structural-sparse-function","title":"GSSF: Generalized Structural Sparse Function for Deep Cross-modal Metric Learning","date":"2024-10-20","arxiv_id":"2410.15266","n_code_links":1,"syntology":null},{"paper":null,"slug":"llava-ultra-large-chinese-language-and-vision","title":"LLaVA-Ultra: Large Chinese Language and Vision Assistant for Ultrasound","date":"2024-10-19","arxiv_id":"2410.15074","n_code_links":0,"syntology":null},{"paper":null,"slug":"preview-based-category-contrastive-learning","title":"Preview-based Category Contrastive Learning for Knowledge Distillation","date":"2024-10-18","arxiv_id":"2410.14143","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-active-learning-framework-for-inclusive","title":"An Active Learning Framework for Inclusive Generation by Large Language Models","date":"2024-10-17","arxiv_id":"2410.13641","n_code_links":0,"syntology":null},{"paper":null,"slug":"cakd-a-correlation-aware-knowledge","title":"CAKD: A Correlation-Aware Knowledge Distillation Framework Based on Decoupling Kullback-Leibler Divergence","date":"2024-10-17","arxiv_id":"2410.14741","n_code_links":0,"syntology":null},{"paper":null,"slug":"leveraging-fine-tuned-language-models-for","title":"FTSmartAudit: A Knowledge Distillation-Enhanced Framework for Automated Smart Contract Auditing Using Fine-Tuned LLMs","date":"2024-10-17","arxiv_id":"2410.13918","n_code_links":0,"syntology":null},{"paper":null,"slug":"optimizing-yolov5s-object-detection-through","title":"Optimizing YOLOv5s Object Detection through Knowledge Distillation algorithm","date":"2024-10-16","arxiv_id":"2410.12259","n_code_links":0,"syntology":null},{"paper":null,"slug":"sam-guided-masked-token-prediction-for-3d","title":"SAM-Guided Masked Token Prediction for 3D Scene Understanding","date":"2024-10-16","arxiv_id":"2410.12158","n_code_links":0,"syntology":null},{"paper":null,"slug":"tas-distilling-arbitrary-teacher-and-student","title":"TAS: Distilling Arbitrary Teacher and Student via a Hybrid Assistant","date":"2024-10-16","arxiv_id":"2410.12342","n_code_links":0,"syntology":null},{"paper":"/paper/breaking-modality-gap-in-rgbt-tracking","slug":"breaking-modality-gap-in-rgbt-tracking","title":"Breaking Modality Gap in RGBT Tracking: Coupled Knowledge Distillation","date":"2024-10-15","arxiv_id":"2410.11586","n_code_links":1,"syntology":null},{"paper":null,"slug":"learning-from-imperfect-data-towards","title":"Learning from Imperfect Data: Towards Efficient Knowledge Distillation of Autoregressive Language Models for Text-to-SQL","date":"2024-10-15","arxiv_id":"2410.11371","n_code_links":0,"syntology":null},{"paper":null,"slug":"speculative-knowledge-distillation-bridging","title":"Speculative Knowledge Distillation: Bridging the Teacher-Student Gap Through Interleaved Sampling","date":"2024-10-15","arxiv_id":"2410.11325","n_code_links":0,"syntology":null},{"paper":"/paper/rehrseg-unleashing-the-power-of-self","slug":"rehrseg-unleashing-the-power-of-self","title":"REHRSeg: Unleashing the Power of Self-Supervised Super-Resolution for Resource-Efficient 3D MRI Segmentation","date":"2024-10-14","arxiv_id":"2410.10097","n_code_links":1,"syntology":null},{"paper":"/paper/rosar-an-adversarial-re-training-framework","slug":"rosar-an-adversarial-re-training-framework","title":"ROSAR: An Adversarial Re-Training Framework for Robust Side-Scan Sonar Object Detection","date":"2024-10-14","arxiv_id":"2410.10554","n_code_links":1,"syntology":null},{"paper":null,"slug":"temperature-centric-investigation-of","title":"Temperature-Centric Investigation of Speculative Decoding with Knowledge Distillation","date":"2024-10-14","arxiv_id":"2410.10141","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-model-for-small-data-foundation-model","title":"Large Model for Small Data: Foundation Model for Cross-Modal RF Human Activity Recognition","date":"2024-10-13","arxiv_id":"2410.19766","n_code_links":0,"syntology":null},{"paper":"/paper/declarative-knowledge-distillation-from-large","slug":"declarative-knowledge-distillation-from-large","title":"Declarative Knowledge Distillation from Large Language Models for Visual Question Answering Datasets","date":"2024-10-12","arxiv_id":"2410.09428","n_code_links":1,"syntology":null},{"paper":"/paper/mentor-kd-making-small-language-models-better","slug":"mentor-kd-making-small-language-models-better","title":"Mentor-KD: Making Small Language Models Better Multi-step Reasoners","date":"2024-10-11","arxiv_id":"2410.09037","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["2hojae/mentor-kd"],"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"]}}},{"paper":null,"slug":"transforming-in-vehicle-network-intrusion","title":"Transforming In-Vehicle Network Intrusion Detection: VAE-based Knowledge Distillation Meets Explainable AI","date":"2024-10-11","arxiv_id":"2410.09043","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-lightweight-target-driven-network-of-stereo","title":"A Lightweight Target-Driven Network of Stereo Matching for Inland Waterways","date":"2024-10-10","arxiv_id":"2410.07915","n_code_links":0,"syntology":null},{"paper":"/paper/relational-diffusion-distillation-for","slug":"relational-diffusion-distillation-for","title":"Relational Diffusion Distillation for Efficient Image Generation","date":"2024-10-10","arxiv_id":"2410.07679","n_code_links":1,"syntology":{"ran":6,"of":6,"n_ran_checked":1,"n_instrument":5,"unverified":0,"pointer_only":2,"phrase":"6 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; 5 where Syntology's instrument failed) · 0 unverified","official":{"repos":["cantbebetter2/rdd"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/snn-par-energy-efficient-pedestrian-attribute","slug":"snn-par-energy-efficient-pedestrian-attribute","title":"SNN-PAR: Energy Efficient Pedestrian Attribute Recognition via Spiking Neural Networks","date":"2024-10-10","arxiv_id":"2410.07857","n_code_links":1,"syntology":null},{"paper":null,"slug":"what-is-left-after-distillation-how-knowledge","title":"What is Left After Distillation? How Knowledge Transfer Impacts Fairness and Bias","date":"2024-10-10","arxiv_id":"2410.08407","n_code_links":0,"syntology":null},{"paper":null,"slug":"efficient-and-robust-knowledge-distillation","title":"Efficient and Robust Knowledge Distillation from A Stronger Teacher Based on Correlation Matching","date":"2024-10-09","arxiv_id":"2410.06561","n_code_links":0,"syntology":null},{"paper":null,"slug":"accelerating-diffusion-models-with-one-to","title":"Accelerating Diffusion Models with One-to-Many Knowledge Distillation","date":"2024-10-05","arxiv_id":"2410.04191","n_code_links":0,"syntology":null},{"paper":null,"slug":"dockd-knowledge-distillation-from-llms-for","title":"DocKD: Knowledge Distillation from LLMs for Open-World Document Understanding Models","date":"2024-10-04","arxiv_id":"2410.03061","n_code_links":0,"syntology":null},{"paper":"/paper/enhance-reasoning-by-learning-from-mistakes","slug":"enhance-reasoning-by-learning-from-mistakes","title":"Learning from Committee: Reasoning Distillation from a Mixture of Teachers with Peer-Review","date":"2024-10-04","arxiv_id":"2410.03663","n_code_links":1,"syntology":null},{"paper":null,"slug":"self-supervised-keypoint-detection-with","title":"Self-Supervised Keypoint Detection with Distilled Depth Keypoint Representation","date":"2024-10-04","arxiv_id":"2410.14700","n_code_links":0,"syntology":null},{"paper":"/paper/dataset-distillation-via-knowledge","slug":"dataset-distillation-via-knowledge","title":"Dataset Distillation via Knowledge Distillation: Towards Efficient Self-Supervised Pre-Training of Deep Networks","date":"2024-10-03","arxiv_id":"2410.02116","n_code_links":1,"syntology":{"ran":14,"of":17,"n_ran_checked":12,"n_instrument":2,"unverified":3,"pointer_only":17,"phrase":"14 ran (of which 4 constructed an object rather than computing a result; 12 with no instrument failure: 1 honoured, 0 violated, 11 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","official":{"repos":["bigml-cs-ucla/mkdt"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":4,"n_ran_no_instrument_failure":12,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/no-matter-what-you-do-mitigating-backdoor","slug":"no-matter-what-you-do-mitigating-backdoor","title":"\"No Matter What You Do\": Purifying GNN Models via Backdoor Unlearning","date":"2024-10-02","arxiv_id":"2410.01272","n_code_links":1,"syntology":null},{"paper":"/paper/pairdistill-pairwise-relevance-distillation","slug":"pairdistill-pairwise-relevance-distillation","title":"PairDistill: Pairwise Relevance Distillation for Dense Retrieval","date":"2024-10-02","arxiv_id":"2410.01383","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":3,"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","official":{"repos":["miulab/pairdistill"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/phi-s-distribution-balancing-for-label-free","slug":"phi-s-distribution-balancing-for-label-free","title":"PHI-S: Distribution Balancing for Label-Free Multi-Teacher Distillation","date":"2024-10-02","arxiv_id":"2410.01680","n_code_links":1,"syntology":null},{"paper":null,"slug":"advancing-medical-radiograph-representation","title":"Advancing Medical Radiograph Representation Learning: A Hybrid Pre-training Paradigm with Multilevel Semantic Granularity","date":"2024-10-01","arxiv_id":"2410.00448","n_code_links":0,"syntology":null},{"paper":"/paper/amr-evol-adaptive-modular-response-evolution","slug":"amr-evol-adaptive-modular-response-evolution","title":"AMR-Evol: Adaptive Modular Response Evolution Elicits Better Knowledge Distillation for Large Language Models in Code Generation","date":"2024-10-01","arxiv_id":"2410.00558","n_code_links":1,"syntology":null},{"paper":null,"slug":"compressing-recurrent-neural-networks-for","title":"Compressing Recurrent Neural Networks for FPGA-accelerated Implementation in Fluorescence Lifetime Imaging","date":"2024-10-01","arxiv_id":"2410.00948","n_code_links":0,"syntology":null},{"paper":null,"slug":"efficient-technical-term-translation-a","title":"Efficient Technical Term Translation: A Knowledge Distillation Approach for Parenthetical Terminology Translation","date":"2024-10-01","arxiv_id":"2410.00683","n_code_links":0,"syntology":null},{"paper":null,"slug":"local-to-global-self-supervised","title":"Local-to-Global Self-Supervised Representation Learning for Diabetic Retinopathy Grading","date":"2024-10-01","arxiv_id":"2410.00779","n_code_links":0,"syntology":null},{"paper":null,"slug":"self-updatable-large-language-models-with","title":"Self-Updatable Large Language Models with Parameter Integration","date":"2024-10-01","arxiv_id":"2410.00487","n_code_links":0,"syntology":null}],"record_sha256":"eef7961cad4cb4f6a7876f3541aedf38928c38cecb3a2c1d13969ae576d57f3a","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}