{"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/24","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":24,"pages_in_order":43,"rows_per_page":100,"rows":[2301,2400],"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/23","next":"/task/knowledge-distillation/papers/25","papers":[{"url":null,"slug":"lakd-activation-mapping-distillation-based-on","title":"LAKD-Activation Mapping Distillation Based on Local Learning","date":"2024-08-21","arxiv_id":"2408.11478","repositories_listed":0,"syntology":null},{"url":null,"slug":"adaptive-knowledge-distillation-for","title":"Adaptive Knowledge Distillation for Classification of Hand Images using Explainable Vision Transformers","date":"2024-08-20","arxiv_id":"2408.10503","repositories_listed":0,"syntology":null},{"url":null,"slug":"generating-synthetic-fair-syntax-agnostic","title":"Generating Synthetic Fair Syntax-agnostic Data by Learning and Distilling Fair Representation","date":"2024-08-20","arxiv_id":"2408.10755","repositories_listed":0,"syntology":null},{"url":null,"slug":"sam-cod-sam-guided-unified-framework-for","title":"SAM-COD: SAM-guided Unified Framework for Weakly-Supervised Camouflaged Object Detection","date":"2024-08-20","arxiv_id":"2408.10760","repositories_listed":0,"syntology":null},{"url":null,"slug":"clip-cid-efficient-clip-distillation-via","title":"CLIP-CID: Efficient CLIP Distillation via Cluster-Instance Discrimination","date":"2024-08-18","arxiv_id":"2408.09441","repositories_listed":0,"syntology":null},{"url":null,"slug":"medmap-promoting-incomplete-multi-modal-brain","title":"MedMAP: Promoting Incomplete Multi-modal Brain Tumor Segmentation with Alignment","date":"2024-08-18","arxiv_id":"2408.09465","repositories_listed":0,"syntology":null},{"url":null,"slug":"v2x-vlm-end-to-end-v2x-cooperative-autonomous","title":"V2X-VLM: End-to-End V2X Cooperative Autonomous Driving Through Large Vision-Language Models","date":"2024-08-17","arxiv_id":"2408.09251","repositories_listed":0,"syntology":null},{"url":null,"slug":"fedquit-on-device-federated-unlearning-via-a","title":"FedQUIT: On-Device Federated Unlearning via a Quasi-Competent Virtual Teacher","date":"2024-08-14","arxiv_id":"2408.07587","repositories_listed":0,"syntology":null},{"url":null,"slug":"using-advanced-llms-to-enhance-smaller-llms","title":"Using Advanced LLMs to Enhance Smaller LLMs: An Interpretable Knowledge Distillation Approach","date":"2024-08-13","arxiv_id":"2408.07238","repositories_listed":0,"syntology":null},{"url":null,"slug":"optimizing-vision-transformers-with-data-free","title":"Optimizing Vision Transformers with Data-Free Knowledge Transfer","date":"2024-08-12","arxiv_id":"2408.05952","repositories_listed":0,"syntology":null},{"url":null,"slug":"low-dimensional-federated-knowledge-graph","title":"Low-Dimensional Federated Knowledge Graph Embedding via Knowledge Distillation","date":"2024-08-11","arxiv_id":"2408.05748","repositories_listed":0,"syntology":null},{"url":null,"slug":"comkd-clip-comprehensive-knowledge","title":"ComKD-CLIP: Comprehensive Knowledge Distillation for Contrastive Language-Image Pre-traning Model","date":"2024-08-08","arxiv_id":"2408.04145","repositories_listed":0,"syntology":null},{"url":null,"slug":"ladimo-layer-wise-distillation-inspired","title":"LaDiMo: Layer-wise Distillation Inspired MoEfier","date":"2024-08-08","arxiv_id":"2408.04278","repositories_listed":0,"syntology":null},{"url":"/paper/dual-modeling-decouple-distillation-for","slug":"dual-modeling-decouple-distillation-for","title":"Dual-Modeling Decouple Distillation for Unsupervised Anomaly Detection","date":"2024-08-07","arxiv_id":"2408.03888","repositories_listed":0,"syntology":null},{"url":null,"slug":"2408-02888","title":"VizECGNet: Visual ECG Image Network for Cardiovascular Diseases Classification with Multi-Modal Training and Knowledge Distillation","date":"2024-08-06","arxiv_id":"2408.02888","repositories_listed":0,"syntology":null},{"url":null,"slug":"2408-03130","title":"Inference Optimizations for Large Language Models: Effects, Challenges, and Practical Considerations","date":"2024-08-06","arxiv_id":"2408.03130","repositories_listed":0,"syntology":null},{"url":null,"slug":"2408-02341","title":"An approach to optimize inference of the DIART speaker diarization pipeline","date":"2024-08-05","arxiv_id":"2408.02341","repositories_listed":0,"syntology":null},{"url":null,"slug":"2408-00205","title":"Sentence-wise Speech Summarization: Task, Datasets, and End-to-End Modeling with LM Knowledge Distillation","date":"2024-08-01","arxiv_id":"2408.00205","repositories_listed":0,"syntology":null},{"url":null,"slug":"2408-00337","title":"DistillGrasp: Integrating Features Correlation with Knowledge Distillation for Depth Completion of Transparent Objects","date":"2024-08-01","arxiv_id":"2408.00337","repositories_listed":0,"syntology":null},{"url":null,"slug":"2407-21416","title":"VIPeR: Visual Incremental Place Recognition with Adaptive Mining and Continual Learning","date":"2024-07-31","arxiv_id":"2407.21416","repositories_listed":0,"syntology":null},{"url":null,"slug":"2407-21515","title":"Learning Effective Representations for Retrieval Using Self-Distillation with Adaptive Relevance Margins","date":"2024-07-31","arxiv_id":"2407.21515","repositories_listed":0,"syntology":null},{"url":null,"slug":"2407-21687","title":"Dynamic Object Queries for Transformer-based Incremental Object Detection","date":"2024-07-31","arxiv_id":"2407.21687","repositories_listed":0,"syntology":null},{"url":null,"slug":"2408-00118","title":"Gemma 2: Improving Open Language Models at a Practical Size","date":"2024-07-31","arxiv_id":"2408.00118","repositories_listed":0,"syntology":null},{"url":null,"slug":"2408-00150","title":"StyleRF-VolVis: Style Transfer of Neural Radiance Fields for Expressive Volume Visualization","date":"2024-07-31","arxiv_id":"2408.00150","repositories_listed":0,"syntology":null},{"url":null,"slug":"lifelong-person-search","title":"Lifelong Person Search","date":"2024-07-31","arxiv_id":"2407.21252","repositories_listed":0,"syntology":null},{"url":null,"slug":"activityclip-enhancing-group-activity","title":"ActivityCLIP: Enhancing Group Activity Recognition by Mining Complementary Information from Text to Supplement Image Modality","date":"2024-07-29","arxiv_id":"2407.19820","repositories_listed":0,"syntology":null},{"url":null,"slug":"llavadi-what-matters-for-multimodal-large","title":"LLAVADI: What Matters For Multimodal Large Language Models Distillation","date":"2024-07-28","arxiv_id":"2407.19409","repositories_listed":0,"syntology":null},{"url":null,"slug":"logic-distillation-learning-from-code","title":"Logic Distillation: Learning from Code Function by Function for Planning and Decision-making","date":"2024-07-28","arxiv_id":"2407.19405","repositories_listed":0,"syntology":null},{"url":null,"slug":"sewer-image-super-resolution-with-depth","title":"Sewer Image Super-Resolution with Depth Priors and Its Lightweight Network","date":"2024-07-27","arxiv_id":"2407.19271","repositories_listed":0,"syntology":null},{"url":null,"slug":"fedud-exploiting-unaligned-data-for-cross","title":"FedUD: Exploiting Unaligned Data for Cross-Platform Federated Click-Through Rate Prediction","date":"2024-07-26","arxiv_id":"2407.18472","repositories_listed":0,"syntology":null},{"url":null,"slug":"peak-controlled-logits-poisoning-attack-in","title":"Peak-Controlled Logits Poisoning Attack in Federated Distillation","date":"2024-07-25","arxiv_id":"2407.18039","repositories_listed":0,"syntology":null},{"url":null,"slug":"separating-novel-features-for-logical-anomaly","title":"Separating Novel Features for Logical Anomaly Detection: A Straightforward yet Effective Approach","date":"2024-07-25","arxiv_id":"2407.17909","repositories_listed":0,"syntology":null},{"url":null,"slug":"ddk-distilling-domain-knowledge-for-efficient","title":"DDK: Distilling Domain Knowledge for Efficient Large Language Models","date":"2024-07-23","arxiv_id":"2407.16154","repositories_listed":0,"syntology":null},{"url":null,"slug":"comprehensive-study-on-performance-evaluation","title":"Comprehensive Study on Performance Evaluation and Optimization of Model Compression: Bridging Traditional Deep Learning and Large Language Models","date":"2024-07-22","arxiv_id":"2407.15904","repositories_listed":0,"syntology":null},{"url":null,"slug":"synthetic-image-learning-preserving","title":"Synthetic Image Learning: Preserving Performance and Preventing Membership Inference Attacks","date":"2024-07-22","arxiv_id":"2407.15526","repositories_listed":0,"syntology":null},{"url":null,"slug":"distilling-vision-language-foundation-models","title":"Distilling Vision-Language Foundation Models: A Data-Free Approach via Prompt Diversification","date":"2024-07-21","arxiv_id":"2407.15155","repositories_listed":0,"syntology":null},{"url":null,"slug":"continual-distillation-learning","title":"Continual Distillation Learning: Knowledge Distillation in Prompt-based Continual Learning","date":"2024-07-18","arxiv_id":"2407.13911","repositories_listed":0,"syntology":null},{"url":null,"slug":"dfmsd-dual-feature-masking-stage-wise","title":"DFMSD: Dual Feature Masking Stage-wise Knowledge Distillation for Object Detection","date":"2024-07-18","arxiv_id":"2407.13147","repositories_listed":0,"syntology":null},{"url":"/paper/open-vocabulary-3d-scene-understanding-via","slug":"open-vocabulary-3d-scene-understanding-via","title":"Open Vocabulary 3D Scene Understanding via Geometry Guided Self-Distillation","date":"2024-07-18","arxiv_id":"2407.13362","repositories_listed":0,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":9,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/open-vocabulary-3d-scene-understanding-via#ran","syntology_url":"https://syntology.ai/paper/2407.13362","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.13362"}},"official":null}},{"url":null,"slug":"a-foundation-model-approach-to-guide","title":"Discovery of novel antimicrobial peptides with notable antibacterial potency by a LLM-based foundation model","date":"2024-07-17","arxiv_id":"2407.12296","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-modality-agnostic-representation-for","title":"Learning Modality-agnostic Representation for Semantic Segmentation from Any Modalities","date":"2024-07-16","arxiv_id":"2407.11351","repositories_listed":0,"syntology":null},{"url":null,"slug":"mapdistill-boosting-efficient-camera-based-hd","title":"MapDistill: Boosting Efficient Camera-based HD Map Construction via Camera-LiDAR Fusion Model Distillation","date":"2024-07-16","arxiv_id":"2407.11682","repositories_listed":0,"syntology":null},{"url":null,"slug":"don-t-throw-away-data-better-sequence","title":"Don't Throw Away Data: Better Sequence Knowledge Distillation","date":"2024-07-15","arxiv_id":"2407.10456","repositories_listed":0,"syntology":null},{"url":null,"slug":"leave-no-knowledge-behind-during-knowledge","title":"Leave No Knowledge Behind During Knowledge Distillation: Towards Practical and Effective Knowledge Distillation for Code-Switching ASR Using Realistic Data","date":"2024-07-15","arxiv_id":"2407.10603","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-granularity-semantic-revision-for-large","title":"Multi-Granularity Semantic Revision for Large Language Model Distillation","date":"2024-07-14","arxiv_id":"2407.10068","repositories_listed":0,"syntology":null},{"url":null,"slug":"background-adaptation-with-residual-modeling","title":"Background Adaptation with Residual Modeling for Exemplar-Free Class-Incremental Semantic Segmentation","date":"2024-07-13","arxiv_id":"2407.09838","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-survey-on-symbolic-knowledge-distillation","title":"A Survey on Symbolic Knowledge Distillation of Large Language Models","date":"2024-07-12","arxiv_id":"2408.10210","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-easy-to-hard-learning-curricular-shape","title":"From Easy to Hard: Learning Curricular Shape-aware Features for Robust Panoptic Scene Graph Generation","date":"2024-07-12","arxiv_id":"2407.09191","repositories_listed":0,"syntology":null},{"url":null,"slug":"uplifting-range-view-based-3d-semantic","title":"Uplifting Range-View-based 3D Semantic Segmentation in Real-Time with Multi-Sensor Fusion","date":"2024-07-12","arxiv_id":"2407.09697","repositories_listed":0,"syntology":null},{"url":null,"slug":"adaptive-deep-iris-feature-extractor-at","title":"Adaptive Deep Iris Feature Extractor at Arbitrary Resolutions","date":"2024-07-11","arxiv_id":"2407.08341","repositories_listed":0,"syntology":null},{"url":null,"slug":"lokilm-technical-report","title":"LokiLM: Technical Report","date":"2024-07-10","arxiv_id":"2407.07370","repositories_listed":0,"syntology":null},{"url":null,"slug":"mixsumm-topic-based-data-augmentation-using","title":"A Guide To Effectively Leveraging LLMs for Low-Resource Text Summarization: Data Augmentation and Semi-supervised Approaches","date":"2024-07-10","arxiv_id":"2407.07341","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-low-resource-nmt-with-a","title":"Enhancing Low-Resource NMT with a Multilingual Encoder and Knowledge Distillation: A Case Study","date":"2024-07-09","arxiv_id":"2407.06538","repositories_listed":0,"syntology":null},{"url":null,"slug":"less-is-more-efficient-brain-inspired","title":"Less is More: Efficient Brain-Inspired Learning for Autonomous Driving Trajectory Prediction","date":"2024-07-09","arxiv_id":"2407.07020","repositories_listed":0,"syntology":null},{"url":null,"slug":"deps-delayed-e-shrinking-for-faster-once-for","title":"DεpS: Delayed ε-Shrinking for Faster Once-For-All Training","date":"2024-07-08","arxiv_id":"2407.06167","repositories_listed":0,"syntology":null},{"url":null,"slug":"federated-knowledge-transfer-fine-tuning","title":"Federated Knowledge Transfer Fine-tuning Large Server Model with Resource-Constrained IoT Clients","date":"2024-07-07","arxiv_id":"2407.05268","repositories_listed":0,"syntology":null},{"url":null,"slug":"topological-persistence-guided-knowledge","title":"Topological Persistence Guided Knowledge Distillation for Wearable Sensor Data","date":"2024-07-07","arxiv_id":"2407.05315","repositories_listed":0,"syntology":null},{"url":null,"slug":"amd-automatic-multi-step-distillation-of","title":"AMD: Automatic Multi-step Distillation of Large-scale Vision Models","date":"2024-07-05","arxiv_id":"2407.04208","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-knowledge-distillation-in-transfer","title":"Improving Knowledge Distillation in Transfer Learning with Layer-wise Learning Rates","date":"2024-07-05","arxiv_id":"2407.04871","repositories_listed":0,"syntology":null},{"url":null,"slug":"understanding-the-gains-from-repeated-self","title":"Understanding the Gains from Repeated Self-Distillation","date":"2024-07-05","arxiv_id":"2407.04600","repositories_listed":0,"syntology":null},{"url":null,"slug":"fully-fine-tuned-clip-models-are-efficient","title":"Fully Fine-tuned CLIP Models are Efficient Few-Shot Learners","date":"2024-07-04","arxiv_id":"2407.04003","repositories_listed":0,"syntology":null},{"url":null,"slug":"edge-ai-enabled-chicken-health-detection","title":"Edge AI-Enabled Chicken Health Detection Based on Enhanced FCOS-Lite and Knowledge Distillation","date":"2024-07-03","arxiv_id":"2407.09562","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-conversational-abilities-of","title":"Improving Conversational Abilities of Quantized Large Language Models via Direct Preference Alignment","date":"2024-07-03","arxiv_id":"2407.03051","repositories_listed":0,"syntology":null},{"url":null,"slug":"mlkd-bert-multi-level-knowledge-distillation","title":"MLKD-BERT: Multi-level Knowledge Distillation for Pre-trained Language Models","date":"2024-07-03","arxiv_id":"2407.02775","repositories_listed":0,"syntology":null},{"url":null,"slug":"supporting-cross-language-cross-project-bug","title":"Supporting Cross-language Cross-project Bug Localization Using Pre-trained Language Models","date":"2024-07-03","arxiv_id":"2407.02732","repositories_listed":0,"syntology":null},{"url":null,"slug":"unified-anomaly-detection-methods-on-edge","title":"Unified Anomaly Detection methods on Edge Device using Knowledge Distillation and Quantization","date":"2024-07-03","arxiv_id":"2407.02968","repositories_listed":0,"syntology":null},{"url":null,"slug":"ecat-a-entire-space-continual-and-adaptive","title":"ECAT: A Entire space Continual and Adaptive Transfer Learning Framework for Cross-Domain Recommendation","date":"2024-07-02","arxiv_id":"2407.02542","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-cooperation-knowledge-distillation-for","title":"Self-Cooperation Knowledge Distillation for Novel Class Discovery","date":"2024-07-02","arxiv_id":"2407.01930","repositories_listed":0,"syntology":null},{"url":null,"slug":"survey-on-knowledge-distillation-for-large","title":"Survey on Knowledge Distillation for Large Language Models: Methods, Evaluation, and Application","date":"2024-07-02","arxiv_id":"2407.01885","repositories_listed":0,"syntology":null},{"url":null,"slug":"bapo-base-anchored-preference-optimization","title":"BAPO: Base-Anchored Preference Optimization for Overcoming Forgetting in Large Language Models Personalization","date":"2024-06-30","arxiv_id":"2407.00693","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-accuracy-and-parameter-efficiency","title":"Enhancing Accuracy and Parameter-Efficiency of Neural Representations for Network Parameterization","date":"2024-06-29","arxiv_id":"2407.00356","repositories_listed":0,"syntology":null},{"url":null,"slug":"direct-preference-knowledge-distillation-for","title":"Direct Preference Knowledge Distillation for Large Language Models","date":"2024-06-28","arxiv_id":"2406.19774","repositories_listed":0,"syntology":null},{"url":null,"slug":"aligning-teacher-with-student-preferences-for","title":"Aligning Teacher with Student Preferences for Tailored Training Data Generation","date":"2024-06-27","arxiv_id":"2406.19227","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-reducing-activity-with-distillation-and","title":"On Reducing Activity with Distillation and Regularization for Energy Efficient Spiking Neural Networks","date":"2024-06-26","arxiv_id":"2406.18350","repositories_listed":0,"syntology":null},{"url":null,"slug":"highly-constrained-coded-aperture-imaging","title":"Highly Constrained Coded Aperture Imaging Systems Design Via a Knowledge Distillation Approach","date":"2024-06-25","arxiv_id":"2406.17970","repositories_listed":0,"syntology":null},{"url":null,"slug":"inficond-interactive-no-code-fine-tuning-with","title":"InFiConD: Interactive No-code Fine-tuning with Concept-based Knowledge Distillation","date":"2024-06-25","arxiv_id":"2406.17838","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-distillation-in-automated","title":"Knowledge Distillation in Automated Annotation: Supervised Text Classification with LLM-Generated Training Labels","date":"2024-06-25","arxiv_id":"2406.17633","repositories_listed":0,"syntology":null},{"url":null,"slug":"preserving-node-distinctness-in-graph","title":"Preserving Node Distinctness in Graph Autoencoders via Similarity Distillation","date":"2024-06-25","arxiv_id":"2406.17517","repositories_listed":0,"syntology":null},{"url":null,"slug":"sequential-editing-for-lifelong-training-of","title":"Sequential Editing for Lifelong Training of Speech Recognition Models","date":"2024-06-25","arxiv_id":"2406.17935","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-optimal-trade-offs-in-knowledge","title":"Towards Optimal Trade-offs in Knowledge Distillation for CNNs and Vision Transformers at the Edge","date":"2024-06-25","arxiv_id":"2407.12808","repositories_listed":0,"syntology":null},{"url":null,"slug":"wave-weight-template-for-adaptive","title":"WAVE: Weight Template for Adaptive Initialization of Variable-sized Models","date":"2024-06-25","arxiv_id":"2406.17503","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-compressibility-of-transformer","title":"Exploring compressibility of transformer based text-to-music (TTM) models","date":"2024-06-24","arxiv_id":"2406.17159","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-knowledge-distillation-for-1","title":"Leveraging Knowledge Distillation for Lightweight Skin Cancer Classification: Balancing Accuracy and Computational Efficiency","date":"2024-06-24","arxiv_id":"2406.17051","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-privileged-students-on-the-value-of","title":"The Privileged Students: On the Value of Initialization in Multilingual Knowledge Distillation","date":"2024-06-24","arxiv_id":"2406.16524","repositories_listed":0,"syntology":null},{"url":null,"slug":"continual-learning-with-diffusion-based","title":"Continual Learning with Diffusion-based Generative Replay for Industrial Streaming Data","date":"2024-06-22","arxiv_id":"2406.15766","repositories_listed":0,"syntology":null},{"url":null,"slug":"fair-text-to-medical-image-diffusion-model","title":"Fair Text to Medical Image Diffusion Model with Subgroup Distribution Aligned Tuning","date":"2024-06-21","arxiv_id":"2406.14847","repositories_listed":0,"syntology":null},{"url":null,"slug":"apprenticeship-inspired-elegance-synergistic","title":"Apprenticeship-Inspired Elegance: Synergistic Knowledge Distillation Empowers Spiking Neural Networks for Efficient Single-Eye Emotion Recognition","date":"2024-06-20","arxiv_id":"2407.09521","repositories_listed":0,"syntology":null},{"url":null,"slug":"factual-dialogue-summarization-via-learning","title":"Factual Dialogue Summarization via Learning from Large Language Models","date":"2024-06-20","arxiv_id":"2406.14709","repositories_listed":0,"syntology":null},{"url":null,"slug":"failure-resilient-distributed-inference-with","title":"Failure-Resilient Distributed Inference with Model Compression over Heterogeneous Edge Devices","date":"2024-06-20","arxiv_id":"2406.14185","repositories_listed":0,"syntology":null},{"url":null,"slug":"secokd-aligning-large-language-models-for-in","title":"SeCoKD: Aligning Large Language Models for In-Context Learning with Fewer Shots","date":"2024-06-20","arxiv_id":"2406.14208","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-low-rank-knowledge-distillation-in-llms","title":"Can Low-Rank Knowledge Distillation in LLMs be Useful for Microelectronic Reasoning?","date":"2024-06-19","arxiv_id":"2406.13808","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-single-slice-segmentation-with-3d","title":"Enhancing Single-Slice Segmentation with 3D-to-2D Unpaired Scan Distillation","date":"2024-06-18","arxiv_id":"2406.12254","repositories_listed":0,"syntology":null},{"url":null,"slug":"intermediate-distillation-data-efficient","title":"Intermediate Distillation: Data-Efficient Distillation from Black-Box LLMs for Information Retrieval","date":"2024-06-18","arxiv_id":"2406.12169","repositories_listed":0,"syntology":null},{"url":null,"slug":"vernacular-i-barely-know-her-challenges-with","title":"Vernacular? I Barely Know Her: Challenges with Style Control and Stereotyping","date":"2024-06-18","arxiv_id":"2406.12679","repositories_listed":0,"syntology":null},{"url":null,"slug":"mutual-learning-for-finetuning-click-through","title":"Mutual Learning for Finetuning Click-Through Rate Prediction Models","date":"2024-06-17","arxiv_id":"2406.12087","repositories_listed":0,"syntology":null},{"url":null,"slug":"nldf-neural-light-dynamic-fields-for","title":"NLDF: Neural Light Dynamic Fields for Efficient 3D Talking Head Generation","date":"2024-06-17","arxiv_id":"2406.11259","repositories_listed":0,"syntology":null},{"url":null,"slug":"steve-series-step-by-step-construction-of","title":"STEVE Series: Step-by-Step Construction of Agent Systems in Minecraft","date":"2024-06-17","arxiv_id":"2406.11247","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-distillation-in-federated-learning","title":"Knowledge Distillation in Federated Learning: a Survey on Long Lasting Challenges and New Solutions","date":"2024-06-16","arxiv_id":"2406.10861","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-knowledge-distillation-for-learning","title":"Self-Knowledge Distillation for Learning Ambiguity","date":"2024-06-14","arxiv_id":"2406.09719","repositories_listed":0,"syntology":null},{"url":null,"slug":"contextual-distillation-model-for-diversified","title":"Contextual Distillation Model for Diversified Recommendation","date":"2024-06-13","arxiv_id":"2406.09021","repositories_listed":0,"syntology":null}],"record_sha256":"83108039eefb7a0c893f7b5c0fd3e5bd9db16cdd0b811e9bade89cfe980595a8","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}