{"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/8","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":8,"pages_in_order":31,"rows_per_page":100,"rows":[701,800],"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/7","next":"/method/knowledge-distillation/papers/9","papers":[{"paper":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","n_code_links":0,"syntology":null},{"paper":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","n_code_links":0,"syntology":null},{"paper":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","n_code_links":0,"syntology":null},{"paper":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","n_code_links":0,"syntology":null},{"paper":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","n_code_links":0,"syntology":null},{"paper":"/paper/oaml-outlier-aware-metric-learning-for-ood","slug":"oaml-outlier-aware-metric-learning-for-ood","title":"Enhancing OOD Detection Using Latent Diffusion","date":"2024-06-24","arxiv_id":"2406.16525","n_code_links":1,"syntology":null},{"paper":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","n_code_links":0,"syntology":null},{"paper":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","n_code_links":0,"syntology":null},{"paper":"/paper/reinforced-knowledge-distillation-for-time","slug":"reinforced-knowledge-distillation-for-time","title":"Reinforced Knowledge Distillation for Time Series Regression","date":"2024-06-21","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":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","n_code_links":0,"syntology":null},{"paper":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","n_code_links":0,"syntology":null},{"paper":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","n_code_links":0,"syntology":null},{"paper":"/paper/learning-to-plan-for-retrieval-augmented","slug":"learning-to-plan-for-retrieval-augmented","title":"Learning to Plan for Retrieval-Augmented Large Language Models from Knowledge Graphs","date":"2024-06-20","arxiv_id":"2406.14282","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["zjukg/lpkg"],"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":"/paper/bild-bi-directional-logits-difference-loss","slug":"bild-bi-directional-logits-difference-loss","title":"BiLD: Bi-directional Logits Difference Loss for Large Language Model Distillation","date":"2024-06-19","arxiv_id":"2406.13555","n_code_links":1,"syntology":null},{"paper":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","n_code_links":0,"syntology":null},{"paper":"/paper/multi-stage-balanced-distillation-addressing","slug":"multi-stage-balanced-distillation-addressing","title":"Multi-Stage Balanced Distillation: Addressing Long-Tail Challenges in Sequence-Level Knowledge Distillation","date":"2024-06-19","arxiv_id":"2406.13114","n_code_links":1,"syntology":null},{"paper":"/paper/watermono-teacher-guided-anomaly-masking-and","slug":"watermono-teacher-guided-anomaly-masking-and","title":"WaterMono: Teacher-Guided Anomaly Masking and Enhancement Boosting for Robust Underwater Self-Supervised Monocular Depth Estimation","date":"2024-06-19","arxiv_id":"2406.13344","n_code_links":1,"syntology":null},{"paper":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","n_code_links":0,"syntology":null},{"paper":"/paper/federated-learning-with-a-single-shared-image","slug":"federated-learning-with-a-single-shared-image","title":"Federated Learning with a Single Shared Image","date":"2024-06-18","arxiv_id":"2406.12658","n_code_links":1,"syntology":null},{"paper":"/paper/from-instance-training-to-instruction","slug":"from-instance-training-to-instruction","title":"From Instance Training to Instruction Learning: Task Adapters Generation from Instructions","date":"2024-06-18","arxiv_id":"2406.12382","n_code_links":2,"syntology":{"ran":8,"of":10,"n_ran_checked":8,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"8 ran (of which 2 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["Xnhyacinth/TAGI"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"paper":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","n_code_links":0,"syntology":null},{"paper":"/paper/graph-knowledge-distillation-to-mixture-of","slug":"graph-knowledge-distillation-to-mixture-of","title":"Graph Knowledge Distillation to Mixture of Experts","date":"2024-06-17","arxiv_id":"2406.11919","n_code_links":1,"syntology":null},{"paper":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","n_code_links":0,"syntology":null},{"paper":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","n_code_links":0,"syntology":null},{"paper":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","n_code_links":0,"syntology":null},{"paper":null,"slug":"contextual-distillation-model-for-diversified","title":"Contextual Distillation Model for Diversified Recommendation","date":"2024-06-13","arxiv_id":"2406.09021","n_code_links":0,"syntology":null},{"paper":null,"slug":"distildoc-knowledge-distillation-for-visually","title":"DistilDoc: Knowledge Distillation for Visually-Rich Document Applications","date":"2024-06-12","arxiv_id":"2406.08226","n_code_links":0,"syntology":null},{"paper":null,"slug":"gendistiller-distilling-pre-trained-language-1","title":"GenDistiller: Distilling Pre-trained Language Models based on an Autoregressive Generative Model","date":"2024-06-12","arxiv_id":"2406.09444","n_code_links":0,"syntology":null},{"paper":"/paper/guiding-frame-level-ctc-alignments-using-self","slug":"guiding-frame-level-ctc-alignments-using-self","title":"Guiding Frame-Level CTC Alignments Using Self-knowledge Distillation","date":"2024-06-12","arxiv_id":"2406.07909","n_code_links":1,"syntology":null},{"paper":null,"slug":"self-distillation-learning-based-on-temporal","title":"Self-Distillation Learning Based on Temporal-Spatial Consistency for Spiking Neural Networks","date":"2024-06-12","arxiv_id":"2406.07862","n_code_links":0,"syntology":null},{"paper":"/paper/small-scale-data-free-knowledge-distillation-1","slug":"small-scale-data-free-knowledge-distillation-1","title":"Small Scale Data-Free Knowledge Distillation","date":"2024-06-12","arxiv_id":"2406.07876","n_code_links":1,"syntology":null},{"paper":null,"slug":"unveiling-incomplete-modality-brain-tumor","title":"Unveiling Incomplete Modality Brain Tumor Segmentation: Leveraging Masked Predicted Auto-Encoder and Divergence Learning","date":"2024-06-12","arxiv_id":"2406.08634","n_code_links":0,"syntology":null},{"paper":"/paper/fastast-accelerating-audio-spectrogram","slug":"fastast-accelerating-audio-spectrogram","title":"FastAST: Accelerating Audio Spectrogram Transformer via Token Merging and Cross-Model Knowledge Distillation","date":"2024-06-11","arxiv_id":"2406.07676","n_code_links":1,"syntology":null},{"paper":"/paper/hydra-mdp-end-to-end-multimodal-planning-with","slug":"hydra-mdp-end-to-end-multimodal-planning-with","title":"Hydra-MDP: End-to-end Multimodal Planning with Multi-target Hydra-Distillation","date":"2024-06-11","arxiv_id":"2406.06978","n_code_links":3,"syntology":null},{"paper":null,"slug":"ternaryllm-ternarized-large-language-model","title":"TernaryLLM: Ternarized Large Language Model","date":"2024-06-11","arxiv_id":"2406.07177","n_code_links":0,"syntology":null},{"paper":null,"slug":"bs-plcnet-2-two-stage-band-split-packet-loss","title":"BS-PLCNet 2: Two-stage Band-split Packet Loss Concealment Network with Intra-model Knowledge Distillation","date":"2024-06-10","arxiv_id":"2406.05961","n_code_links":0,"syntology":null},{"paper":"/paper/dkdl-net-a-lightweight-bearing-fault","slug":"dkdl-net-a-lightweight-bearing-fault","title":"DKDL-Net: A Lightweight Bearing Fault Detection Model via Decoupled Knowledge Distillation and Low-Rank Adaptation Fine-tuning","date":"2024-06-10","arxiv_id":"2406.06653","n_code_links":1,"syntology":null},{"paper":null,"slug":"weighted-kl-divergence-for-document-ranking","title":"Weighted KL-Divergence for Document Ranking Model Refinement","date":"2024-06-10","arxiv_id":"2406.05977","n_code_links":0,"syntology":null},{"paper":null,"slug":"egor-efficient-generated-objects-replay-for","title":"IOR: Inversed Objects Replay for Incremental Object Detection","date":"2024-06-07","arxiv_id":"2406.04829","n_code_links":0,"syntology":null},{"paper":"/paper/lenslessface-an-end-to-end-optimized-lensless","slug":"lenslessface-an-end-to-end-optimized-lensless","title":"LenslessFace: An End-to-End Optimized Lensless System for Privacy-Preserving Face Verification","date":"2024-06-06","arxiv_id":"2406.04129","n_code_links":1,"syntology":null},{"paper":null,"slug":"step-out-and-seek-around-on-warm-start","title":"Step Out and Seek Around: On Warm-Start Training with Incremental Data","date":"2024-06-06","arxiv_id":"2406.04484","n_code_links":0,"syntology":null},{"paper":"/paper/multi-task-multi-scale-contrastive-knowledge","slug":"multi-task-multi-scale-contrastive-knowledge","title":"Multi-Task Multi-Scale Contrastive Knowledge Distillation for Efficient Medical Image Segmentation","date":"2024-06-05","arxiv_id":"2406.03173","n_code_links":1,"syntology":null},{"paper":null,"slug":"mutual-information-guided-backdoor-mitigation","title":"Mutual Information Guided Backdoor Mitigation for Pre-trained Encoders","date":"2024-06-05","arxiv_id":"2406.03508","n_code_links":0,"syntology":null},{"paper":null,"slug":"plad-preference-based-large-language-model","title":"PLaD: Preference-based Large Language Model Distillation with Pseudo-Preference Pairs","date":"2024-06-05","arxiv_id":"2406.02886","n_code_links":0,"syntology":null},{"paper":null,"slug":"dl-kdd-dual-light-knowledge-distillation-for","title":"DL-KDD: Dual-Light Knowledge Distillation for Action Recognition in the Dark","date":"2024-06-04","arxiv_id":"2406.02468","n_code_links":0,"syntology":null},{"paper":"/paper/optimal-transport-guided-correlation","slug":"optimal-transport-guided-correlation","title":"Optimal Transport Guided Correlation Assignment for Multimodal Entity Linking","date":"2024-06-04","arxiv_id":"2406.01934","n_code_links":1,"syntology":null},{"paper":null,"slug":"decoupled-alignment-for-robust-plug-and-play","title":"Decoupled Alignment for Robust Plug-and-Play Adaptation","date":"2024-06-03","arxiv_id":"2406.01514","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-background-prompts-to-discover","title":"Learning Background Prompts to Discover Implicit Knowledge for Open Vocabulary Object Detection","date":"2024-06-01","arxiv_id":"2406.00510","n_code_links":0,"syntology":null},{"paper":"/paper/robust-knowledge-distillation-based-on","slug":"robust-knowledge-distillation-based-on","title":"Robust Knowledge Distillation Based on Feature Variance Against Backdoored Teacher Model","date":"2024-06-01","arxiv_id":"2406.03409","n_code_links":1,"syntology":null},{"paper":"/paper/distribution-aligned-semantics-adaption-for","slug":"distribution-aligned-semantics-adaption-for","title":"Distribution Aligned Semantics Adaption for Lifelong Person Re-Identification","date":"2024-05-30","arxiv_id":"2405.19695","n_code_links":1,"syntology":null},{"paper":null,"slug":"estimating-human-poses-across-datasets-a","title":"Estimating Human Poses Across Datasets: A Unified Skeleton and Multi-Teacher Distillation Approach","date":"2024-05-30","arxiv_id":"2405.20084","n_code_links":0,"syntology":null},{"paper":"/paper/improving-the-training-of-rectified-flows","slug":"improving-the-training-of-rectified-flows","title":"Improving the Training of Rectified Flows","date":"2024-05-30","arxiv_id":"2405.20320","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["sangyun884/rfpp"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"relation-modeling-and-distillation-for","title":"Relation Modeling and Distillation for Learning with Noisy Labels","date":"2024-05-30","arxiv_id":"2405.19606","n_code_links":0,"syntology":null},{"paper":null,"slug":"scalable-detection-of-salient-entities-in","title":"Scalable Detection of Salient Entities in News Articles","date":"2024-05-30","arxiv_id":"2405.20461","n_code_links":0,"syntology":null},{"paper":null,"slug":"blsp-kd-bootstrapping-language-speech-pre","title":"BLSP-KD: Bootstrapping Language-Speech Pre-training via Knowledge Distillation","date":"2024-05-29","arxiv_id":"2405.19041","n_code_links":0,"syntology":null},{"paper":null,"slug":"forward-backward-knowledge-distillation-for","title":"Forward-Backward Knowledge Distillation for Continual Clustering","date":"2024-05-29","arxiv_id":"2405.19234","n_code_links":0,"syntology":null},{"paper":null,"slug":"aligning-in-a-compact-space-contrastive","title":"Aligning in a Compact Space: Contrastive Knowledge Distillation between Heterogeneous Architectures","date":"2024-05-28","arxiv_id":"2405.18524","n_code_links":0,"syntology":null},{"paper":"/paper/slmrec-empowering-small-language-models-for","slug":"slmrec-empowering-small-language-models-for","title":"SLMRec: Distilling Large Language Models into Small for Sequential Recommendation","date":"2024-05-28","arxiv_id":"2405.17890","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":["wujiangxu/slmrec"],"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/loretrack-efficient-and-accurate-low","slug":"loretrack-efficient-and-accurate-low","title":"LoReTrack: Efficient and Accurate Low-Resolution Transformer Tracking","date":"2024-05-27","arxiv_id":"2405.17660","n_code_links":1,"syntology":null},{"paper":null,"slug":"p4-towards-private-personalized-and-peer-to","title":"P4: Towards private, personalized, and Peer-to-Peer learning","date":"2024-05-27","arxiv_id":"2405.17697","n_code_links":0,"syntology":null},{"paper":null,"slug":"tima-text-image-mutual-awareness-for","title":"TIMA: Text-Image Mutual Awareness for Balancing Zero-Shot Adversarial Robustness and Generalization Ability","date":"2024-05-27","arxiv_id":"2405.17678","n_code_links":0,"syntology":null},{"paper":null,"slug":"unicompress-enhancing-multi-data-medical","title":"UniCompress: Enhancing Multi-Data Medical Image Compression with Knowledge Distillation","date":"2024-05-27","arxiv_id":"2405.16850","n_code_links":0,"syntology":null},{"paper":null,"slug":"ldpkit-recovering-utility-in-ldp-schemes-by","title":"Noisy Data Meets Privacy: Training Local Models with Post-Processed Remote Queries","date":"2024-05-25","arxiv_id":"2405.16361","n_code_links":0,"syntology":null},{"paper":"/paper/rethinking-early-fusion-strategies-for","slug":"rethinking-early-fusion-strategies-for","title":"Rethinking Early-Fusion Strategies for Improved Multispectral Object Detection","date":"2024-05-25","arxiv_id":"2405.16038","n_code_links":1,"syntology":null},{"paper":null,"slug":"harnessing-increased-client-participation","title":"Harnessing Increased Client Participation with Cohort-Parallel Federated Learning","date":"2024-05-24","arxiv_id":"2405.15644","n_code_links":0,"syntology":null},{"paper":"/paper/leveraging-knowledge-distillation-for-partial","slug":"leveraging-knowledge-distillation-for-partial","title":"Leveraging knowledge distillation for partial multi-task learning from multiple remote sensing datasets","date":"2024-05-24","arxiv_id":"2405.15394","n_code_links":1,"syntology":null},{"paper":"/paper/adagmlp-adaboosting-gnn-to-mlp-knowledge","slug":"adagmlp-adaboosting-gnn-to-mlp-knowledge","title":"AdaGMLP: AdaBoosting GNN-to-MLP Knowledge Distillation","date":"2024-05-23","arxiv_id":"2405.14307","n_code_links":1,"syntology":null},{"paper":null,"slug":"efficient-multitask-dense-predictor-via","title":"Efficient Multitask Dense Predictor via Binarization","date":"2024-05-23","arxiv_id":"2405.14136","n_code_links":0,"syntology":null},{"paper":"/paper/jiuzhang3-0-efficiently-improving","slug":"jiuzhang3-0-efficiently-improving","title":"JiuZhang3.0: Efficiently Improving Mathematical Reasoning by Training Small Data Synthesis Models","date":"2024-05-23","arxiv_id":"2405.14365","n_code_links":1,"syntology":{"ran":9,"of":12,"n_ran_checked":9,"n_instrument":0,"unverified":3,"pointer_only":12,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["rucaibox/jiuzhang3.0"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/recurrent-early-exits-for-federated-learning","slug":"recurrent-early-exits-for-federated-learning","title":"Recurrent Early Exits for Federated Learning with Heterogeneous Clients","date":"2024-05-23","arxiv_id":"2405.14791","n_code_links":1,"syntology":{"ran":9,"of":20,"n_ran_checked":5,"n_instrument":4,"unverified":11,"pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 4 where Syntology's instrument failed) · 11 unverified","official":{"repos":["royson/reefl"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":11,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"data-free-federated-class-incremental","title":"Data-Free Federated Class Incremental Learning with Diffusion-Based Generative Memory","date":"2024-05-22","arxiv_id":"2405.17457","n_code_links":0,"syntology":null},{"paper":null,"slug":"hoverfast-an-accurate-high-throughput","title":"HoverFast: an accurate, high-throughput, clinically deployable nuclear segmentation tool for brightfield digital pathology images","date":"2024-05-22","arxiv_id":"2405.14028","n_code_links":0,"syntology":null},{"paper":null,"slug":"joint-optimization-of-streaming-and-non","title":"Joint Optimization of Streaming and Non-Streaming Automatic Speech Recognition with Multi-Decoder and Knowledge Distillation","date":"2024-05-22","arxiv_id":"2405.13514","n_code_links":0,"syntology":null},{"paper":"/paper/why-not-transform-chat-large-language-models","slug":"why-not-transform-chat-large-language-models","title":"Why Not Transform Chat Large Language Models to Non-English?","date":"2024-05-22","arxiv_id":"2405.13923","n_code_links":1,"syntology":null},{"paper":"/paper/active-object-detection-with-knowledge","slug":"active-object-detection-with-knowledge","title":"Active Object Detection with Knowledge Aggregation and Distillation from Large Models","date":"2024-05-21","arxiv_id":"2405.12509","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":["idejie/KAD"],"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/amfd-distillation-via-adaptive-multimodal","slug":"amfd-distillation-via-adaptive-multimodal","title":"AMFD: Distillation via Adaptive Multimodal Fusion for Multispectral Pedestrian Detection","date":"2024-05-21","arxiv_id":"2405.12944","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"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":["bigD233/AMFD"],"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":"distill-then-prune-an-efficient-compression","title":"Distill-then-prune: An Efficient Compression Framework for Real-time Stereo Matching Network on Edge Devices","date":"2024-05-20","arxiv_id":"2405.11809","n_code_links":0,"syntology":null},{"paper":null,"slug":"evolving-storytelling-benchmarks-and-methods","title":"Evolving Storytelling: Benchmarks and Methods for New Character Customization with Diffusion Models","date":"2024-05-20","arxiv_id":"2405.11852","n_code_links":0,"syntology":null},{"paper":"/paper/federated-learning-with-incomplete-sensing","slug":"federated-learning-with-incomplete-sensing","title":"Federated Learning for Time-Series Healthcare Sensing with Incomplete Modalities","date":"2024-05-20","arxiv_id":"2405.11828","n_code_links":1,"syntology":null},{"paper":null,"slug":"geomask3d-geometrically-informed-mask","title":"GeoMask3D: Geometrically Informed Mask Selection for Self-Supervised Point Cloud Learning in 3D","date":"2024-05-20","arxiv_id":"2405.12419","n_code_links":0,"syntology":null},{"paper":null,"slug":"stereo-knowledge-distillation-from-dpmv-to","title":"Stereo-Knowledge Distillation from dpMV to Dual Pixels for Light Field Video Reconstruction","date":"2024-05-20","arxiv_id":"2405.11823","n_code_links":0,"syntology":null},{"paper":null,"slug":"tinym-2-net-v3-memory-aware-compressed","title":"TinyM$^2$Net-V3: Memory-Aware Compressed Multimodal Deep Neural Networks for Sustainable Edge Deployment","date":"2024-05-20","arxiv_id":"2405.12353","n_code_links":0,"syntology":null},{"paper":null,"slug":"cross-domain-knowledge-distillation-for-low","title":"Cross-Domain Knowledge Distillation for Low-Resolution Human Pose Estimation","date":"2024-05-19","arxiv_id":"2405.11448","n_code_links":0,"syntology":null},{"paper":null,"slug":"hierarchical-selective-classification","title":"Hierarchical Selective Classification","date":"2024-05-19","arxiv_id":"2405.11533","n_code_links":0,"syntology":null},{"paper":"/paper/overcoming-data-and-model-heterogeneities-in","slug":"overcoming-data-and-model-heterogeneities-in","title":"Overcoming Data and Model Heterogeneities in Decentralized Federated Learning via Synthetic Anchors","date":"2024-05-19","arxiv_id":"2405.11525","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":0,"n_instrument":1,"unverified":1,"pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":null}},{"paper":null,"slug":"indus-effective-and-efficient-language-models","title":"INDUS: Effective and Efficient Language Models for Scientific Applications","date":"2024-05-17","arxiv_id":"2405.10725","n_code_links":0,"syntology":null},{"paper":null,"slug":"densely-distilling-cumulative-knowledge-for","title":"Densely Distilling Cumulative Knowledge for Continual Learning","date":"2024-05-16","arxiv_id":"2405.09820","n_code_links":0,"syntology":null},{"paper":"/paper/distilling-implicit-multimodal-knowledge-into","slug":"distilling-implicit-multimodal-knowledge-into","title":"Distilling Implicit Multimodal Knowledge into Large Language Models for Zero-Resource Dialogue Generation","date":"2024-05-16","arxiv_id":"2405.10121","n_code_links":1,"syntology":null},{"paper":"/paper/glira-black-box-membership-inference-attack","slug":"glira-black-box-membership-inference-attack","title":"GLiRA: Black-Box Membership Inference Attack via Knowledge Distillation","date":"2024-05-13","arxiv_id":"2405.07562","n_code_links":1,"syntology":null},{"paper":"/paper/enhancing-multi-modal-learning-meta-learned","slug":"enhancing-multi-modal-learning-meta-learned","title":"Meta-Learned Modality-Weighted Knowledge Distillation for Robust Multi-Modal Learning with Missing Data","date":"2024-05-12","arxiv_id":"2405.07155","n_code_links":1,"syntology":null},{"paper":null,"slug":"adakd-dynamic-knowledge-distillation-of-asr","title":"AdaKD: Dynamic Knowledge Distillation of ASR models using Adaptive Loss Weighting","date":"2024-05-11","arxiv_id":"2405.08019","n_code_links":0,"syntology":null},{"paper":null,"slug":"for-the-misgendered-chinese-in-gender-bias","title":"For the Misgendered Chinese in Gender Bias Research: Multi-Task Learning with Knowledge Distillation for Pinyin Name-Gender Prediction","date":"2024-05-10","arxiv_id":"2405.06221","n_code_links":0,"syntology":null},{"paper":null,"slug":"mh-pflid-model-heterogeneous-personalized","title":"MH-pFLID: Model Heterogeneous personalized Federated Learning via Injection and Distillation for Medical Data Analysis","date":"2024-05-10","arxiv_id":"2405.06822","n_code_links":0,"syntology":null},{"paper":"/paper/less-supervised-learning-with-knowledge","slug":"less-supervised-learning-with-knowledge","title":"Less-supervised learning with knowledge distillation for sperm morphology analysis","date":"2024-05-08","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"markowitz-meets-bellman-knowledge-distilled","title":"Markowitz Meets Bellman: Knowledge-distilled Reinforcement Learning for Portfolio Management","date":"2024-05-08","arxiv_id":"2405.05449","n_code_links":0,"syntology":null},{"paper":null,"slug":"elite-efficient-image-to-lidar-knowledge","title":"ELiTe: Efficient Image-to-LiDAR Knowledge Transfer for Semantic Segmentation","date":"2024-05-07","arxiv_id":"2405.04121","n_code_links":0,"syntology":null},{"paper":null,"slug":"govern-gradient-orientation-vote-ensemble-for","title":"GOVERN: Gradient Orientation Vote Ensemble for Multi-Teacher Reinforced Distillation","date":"2024-05-06","arxiv_id":"2405.03764","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-extreme-quantization-in-spiking","title":"Exploring Extreme Quantization in Spiking Language Models","date":"2024-05-04","arxiv_id":"2405.02543","n_code_links":0,"syntology":null},{"paper":"/paper/sub-goal-distillation-a-method-to-improve","slug":"sub-goal-distillation-a-method-to-improve","title":"Sub-goal Distillation: A Method to Improve Small Language Agents","date":"2024-05-04","arxiv_id":"2405.02749","n_code_links":1,"syntology":null},{"paper":"/paper/advancing-pre-trained-teacher-towards-robust","slug":"advancing-pre-trained-teacher-towards-robust","title":"Advancing Pre-trained Teacher: Towards Robust Feature Discrepancy for Anomaly Detection","date":"2024-05-03","arxiv_id":"2405.02068","n_code_links":1,"syntology":null}],"record_sha256":"9af847f0f1b72ea6d0b9cd170852b01f631dac6282206d4926e3ab338ba65b48","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}