{"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/19","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":19,"pages_in_order":43,"rows_per_page":100,"rows":[1801,1900],"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/18","next":"/task/knowledge-distillation/papers/20","papers":[{"url":null,"slug":"an-efficient-private-gpt-never","title":"An Efficient Private GPT Never Autoregressively Decodes","date":"2025-05-21","arxiv_id":"2505.15252","repositories_listed":0,"syntology":null},{"url":null,"slug":"mentalmac-enhancing-large-language-models-for","title":"MentalMAC: Enhancing Large Language Models for Detecting Mental Manipulation via Multi-Task Anti-Curriculum Distillation","date":"2025-05-21","arxiv_id":"2505.15255","repositories_listed":0,"syntology":null},{"url":null,"slug":"bridge-the-gap-between-past-and-future","title":"Bridge the Gap between Past and Future: Siamese Model Optimization for Context-Aware Document Ranking","date":"2025-05-20","arxiv_id":"2505.14180","repositories_listed":0,"syntology":null},{"url":null,"slug":"ground-v-teaching-vlms-to-ground-complex","title":"Ground-V: Teaching VLMs to Ground Complex Instructions in Pixels","date":"2025-05-20","arxiv_id":"2505.13788","repositories_listed":0,"syntology":null},{"url":null,"slug":"improved-methods-for-model-pruning-and","title":"Improved Methods for Model Pruning and Knowledge Distillation","date":"2025-05-20","arxiv_id":"2505.14052","repositories_listed":0,"syntology":null},{"url":null,"slug":"interpretable-traces-unexpected-outcomes","title":"Interpretable Traces, Unexpected Outcomes: Investigating the Disconnect in Trace-Based Knowledge Distillation","date":"2025-05-20","arxiv_id":"2505.13792","repositories_listed":0,"syntology":null},{"url":null,"slug":"bridging-the-modality-gap-enhancing-channel","title":"Bridging the Modality Gap: Enhancing Channel Prediction with Semantically Aligned LLMs and Knowledge Distillation","date":"2025-05-19","arxiv_id":"2505.12729","repositories_listed":0,"syntology":null},{"url":null,"slug":"orqa-a-benchmark-and-foundation-model-for","title":"ORQA: A Benchmark and Foundation Model for Holistic Operating Room Modeling","date":"2025-05-19","arxiv_id":"2505.12890","repositories_listed":0,"syntology":null},{"url":null,"slug":"why-knowledge-distillation-works-in","title":"Why Knowledge Distillation Works in Generative Models: A Minimal Working Explanation","date":"2025-05-19","arxiv_id":"2505.13111","repositories_listed":0,"syntology":null},{"url":null,"slug":"lameta-intent-aware-agentic-network","title":"LAMeTA: Intent-Aware Agentic Network Optimization via a Large AI Model-Empowered Two-Stage Approach","date":"2025-05-18","arxiv_id":"2505.12247","repositories_listed":0,"syntology":null},{"url":null,"slug":"ssr-enhancing-depth-perception-in-vision","title":"SSR: Enhancing Depth Perception in Vision-Language Models via Rationale-Guided Spatial Reasoning","date":"2025-05-18","arxiv_id":"2505.12448","repositories_listed":0,"syntology":null},{"url":null,"slug":"denoising-mutual-knowledge-distillation-in-bi","title":"Denoising Mutual Knowledge Distillation in Bi-Directional Multiple Instance Learning","date":"2025-05-17","arxiv_id":"2505.12074","repositories_listed":0,"syntology":null},{"url":null,"slug":"figkd-fine-grained-knowledge-distillation-via","title":"FiGKD: Fine-Grained Knowledge Distillation via High-Frequency Detail Transfer","date":"2025-05-17","arxiv_id":"2505.11897","repositories_listed":0,"syntology":null},{"url":null,"slug":"2505-11100","title":"Bidirectional Distillation: A Mixed-Play Framework for Multi-Agent Generalizable Behaviors","date":"2025-05-16","arxiv_id":"2505.11100","repositories_listed":0,"syntology":null},{"url":null,"slug":"semantically-aware-game-image-quality","title":"Semantically-Aware Game Image Quality Assessment","date":"2025-05-16","arxiv_id":"2505.11724","repositories_listed":0,"syntology":null},{"url":null,"slug":"2505-10649","title":"Advancing Multiple Instance Learning with Continual Learning for Whole Slide Imaging","date":"2025-05-15","arxiv_id":"2505.10649","repositories_listed":0,"syntology":null},{"url":null,"slug":"dcsnet-a-lightweight-knowledge-distillation","title":"DCSNet: A Lightweight Knowledge Distillation-Based Model with Explainable AI for Lung Cancer Diagnosis from Histopathological Images","date":"2025-05-14","arxiv_id":"2505.09334","repositories_listed":0,"syntology":null},{"url":null,"slug":"fusing-bidirectional-chains-of-thought-and","title":"Fusing Bidirectional Chains of Thought and Reward Mechanisms A Method for Enhancing Question-Answering Capabilities of Large Language Models for Chinese Intangible Cultural Heritage","date":"2025-05-13","arxiv_id":"2505.08167","repositories_listed":0,"syntology":null},{"url":null,"slug":"low-complexity-inference-in-continual","title":"Low-Complexity Inference in Continual Learning via Compressed Knowledge Transfer","date":"2025-05-13","arxiv_id":"2505.08327","repositories_listed":0,"syntology":null},{"url":null,"slug":"mokd-multi-task-optimization-for-knowledge","title":"MoKD: Multi-Task Optimization for Knowledge Distillation","date":"2025-05-13","arxiv_id":"2505.08170","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-extra-rmsnorm-is-all-you-need-for-fine","title":"An Extra RMSNorm is All You Need for Fine Tuning to 1.58 Bits","date":"2025-05-12","arxiv_id":"2505.08823","repositories_listed":0,"syntology":null},{"url":null,"slug":"channel-fingerprint-construction-for-massive","title":"Channel Fingerprint Construction for Massive MIMO: A Deep Conditional Generative Approach","date":"2025-05-12","arxiv_id":"2505.07893","repositories_listed":0,"syntology":null},{"url":null,"slug":"kdh-mltc-knowledge-distillation-for","title":"KDH-MLTC: Knowledge Distillation for Healthcare Multi-Label Text Classification","date":"2025-05-12","arxiv_id":"2505.07162","repositories_listed":0,"syntology":null},{"url":null,"slug":"ranking-aware-continual-learning-for-lidar","title":"Ranking-aware Continual Learning for LiDAR Place Recognition","date":"2025-05-12","arxiv_id":"2505.07198","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-distillation-for-enhancing-walmart","title":"Knowledge Distillation for Enhancing Walmart E-commerce Search Relevance Using Large Language Models","date":"2025-05-11","arxiv_id":"2505.07105","repositories_listed":0,"syntology":null},{"url":null,"slug":"human-in-the-latent-loop-hill-interactively","title":"Human in the Latent Loop (HILL): Interactively Guiding Model Training Through Human Intuition","date":"2025-05-09","arxiv_id":"2505.06325","repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-precise-knowledge-distillation-based","title":"Robust & Precise Knowledge Distillation-based Novel Context-Aware Predictor for Disease Detection in Brain and Gastrointestinal","date":"2025-05-09","arxiv_id":"2505.06381","repositories_listed":0,"syntology":null},{"url":null,"slug":"federated-deconfounding-and-debiasing","title":"Federated Deconfounding and Debiasing Learning for Out-of-Distribution Generalization","date":"2025-05-08","arxiv_id":"2505.04979","repositories_listed":0,"syntology":null},{"url":null,"slug":"theoretical-guarantees-for-lt-ttd-a-unified","title":"Theoretical Guarantees for LT-TTD: A Unified Transformer-based Architecture for Two-Level Ranking Systems","date":"2025-05-07","arxiv_id":"2505.04434","repositories_listed":0,"syntology":null},{"url":null,"slug":"action-spotting-and-precise-event-detection","title":"Action Spotting and Precise Event Detection in Sports: Datasets, Methods, and Challenges","date":"2025-05-06","arxiv_id":"2505.03991","repositories_listed":0,"syntology":null},{"url":null,"slug":"artificial-behavior-intelligence-technology","title":"Artificial Behavior Intelligence: Technology, Challenges, and Future Directions","date":"2025-05-06","arxiv_id":"2505.03315","repositories_listed":0,"syntology":null},{"url":null,"slug":"image-recognition-with-online-lightweight","title":"Image Recognition with Online Lightweight Vision Transformer: A Survey","date":"2025-05-06","arxiv_id":"2505.03113","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-distillation-for-speech-denoising","title":"Knowledge Distillation for Speech Denoising by Latent Representation Alignment with Cosine Distance","date":"2025-05-06","arxiv_id":"2505.03442","repositories_listed":0,"syntology":null},{"url":null,"slug":"sepalm-audio-language-models-are-error","title":"SepALM: Audio Language Models Are Error Correctors for Robust Speech Separation","date":"2025-05-06","arxiv_id":"2505.03273","repositories_listed":0,"syntology":null},{"url":null,"slug":"akd-adversarial-knowledge-distillation-for","title":"AKD : Adversarial Knowledge Distillation For Large Language Models Alignment on Coding tasks","date":"2025-05-05","arxiv_id":"2505.06267","repositories_listed":0,"syntology":null},{"url":null,"slug":"end-to-end-fully-binarized-network-design","title":"End-to-end fully-binarized network design: from Generic Learned Thermometer to Block Pruning","date":"2025-05-05","arxiv_id":"2505.13462","repositories_listed":0,"syntology":null},{"url":null,"slug":"optimizing-llms-for-resource-constrained","title":"Optimizing LLMs for Resource-Constrained Environments: A Survey of Model Compression Techniques","date":"2025-05-05","arxiv_id":"2505.02309","repositories_listed":0,"syntology":null},{"url":null,"slug":"segment-any-rgb-thermal-model-with-language","title":"Segment Any RGB-Thermal Model with Language-aided Distillation","date":"2025-05-04","arxiv_id":"2505.01950","repositories_listed":0,"syntology":null},{"url":null,"slug":"high-fidelity-pseudo-label-generation-by","title":"High-Fidelity Pseudo-label Generation by Large Language Models for Training Robust Radiology Report Classifiers","date":"2025-05-03","arxiv_id":"2505.01693","repositories_listed":0,"syntology":null},{"url":null,"slug":"llama-nemotron-efficient-reasoning-models","title":"Llama-Nemotron: Efficient Reasoning Models","date":"2025-05-02","arxiv_id":"2505.00949","repositories_listed":0,"syntology":null},{"url":null,"slug":"toward-data-centric-directed-graph-learning","title":"Toward Data-centric Directed Graph Learning: An Entropy-driven Approach","date":"2025-05-02","arxiv_id":"2505.00983","repositories_listed":0,"syntology":null},{"url":null,"slug":"uncertainty-aware-multi-expert-knowledge","title":"Uncertainty-Aware Multi-Expert Knowledge Distillation for Imbalanced Disease Grading","date":"2025-05-01","arxiv_id":"2505.00592","repositories_listed":0,"syntology":null},{"url":null,"slug":"cae-dfkd-bridging-the-transferability-gap-in","title":"CAE-DFKD: Bridging the Transferability Gap in Data-Free Knowledge Distillation","date":"2025-04-30","arxiv_id":"2504.21478","repositories_listed":0,"syntology":null},{"url":null,"slug":"how-to-backdoor-the-knowledge-distillation","title":"How to Backdoor the Knowledge Distillation","date":"2025-04-30","arxiv_id":"2504.21323","repositories_listed":0,"syntology":null},{"url":null,"slug":"federated-one-shot-learning-with-data-privacy","title":"Federated One-Shot Learning with Data Privacy and Objective-Hiding","date":"2025-04-29","arxiv_id":"2504.21182","repositories_listed":0,"syntology":null},{"url":null,"slug":"head-tail-aware-kl-divergence-in-knowledge","title":"Head-Tail-Aware KL Divergence in Knowledge Distillation for Spiking Neural Networks","date":"2025-04-29","arxiv_id":"2504.20445","repositories_listed":0,"syntology":null},{"url":null,"slug":"sam-guided-robust-representation-learning-for","title":"SAM-Guided Robust Representation Learning for One-Shot 3D Medical Image Segmentation","date":"2025-04-29","arxiv_id":"2504.20501","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-estimation-of-continual-causal-effect-for","title":"The Estimation of Continual Causal Effect for Dataset Shifting Streams","date":"2025-04-29","arxiv_id":"2504.20471","repositories_listed":0,"syntology":null},{"url":null,"slug":"trace-of-thought-prompting-investigating","title":"Trace-of-Thought Prompting: Investigating Prompt-Based Knowledge Distillation Through Question Decomposition","date":"2025-04-29","arxiv_id":"2504.20946","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-distillation-of-domain-adapted-llms","title":"Knowledge Distillation of Domain-adapted LLMs for Question-Answering in Telecom","date":"2025-04-28","arxiv_id":"2504.20000","repositories_listed":0,"syntology":null},{"url":null,"slug":"breaking-the-modality-barrier-universal","title":"Breaking the Modality Barrier: Universal Embedding Learning with Multimodal LLMs","date":"2025-04-24","arxiv_id":"2504.17432","repositories_listed":0,"syntology":null},{"url":null,"slug":"does-knowledge-distillation-matter-for-large","title":"Does Knowledge Distillation Matter for Large Language Model based Bundle Generation?","date":"2025-04-24","arxiv_id":"2504.17220","repositories_listed":0,"syntology":null},{"url":null,"slug":"unified-attacks-to-large-language-model","title":"Unified Attacks to Large Language Model Watermarks: Spoofing and Scrubbing in Unauthorized Knowledge Distillation","date":"2025-04-24","arxiv_id":"2504.17480","repositories_listed":0,"syntology":null},{"url":null,"slug":"emo-pillars-knowledge-distillation-to-support","title":"Emo Pillars: Knowledge Distillation to Support Fine-Grained Context-Aware and Context-Less Emotion Classification","date":"2025-04-23","arxiv_id":"2504.16856","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-distillation-and-dataset","title":"Knowledge Distillation and Dataset Distillation of Large Language Models: Emerging Trends, Challenges, and Future Directions","date":"2025-04-20","arxiv_id":"2504.14772","repositories_listed":0,"syntology":null},{"url":null,"slug":"turbo2k-towards-ultra-efficient-and-high","title":"Turbo2K: Towards Ultra-Efficient and High-Quality 2K Video Synthesis","date":"2025-04-20","arxiv_id":"2504.14470","repositories_listed":0,"syntology":null},{"url":null,"slug":"empirical-evaluation-of-knowledge","title":"Empirical Evaluation of Knowledge Distillation from Transformers to Subquadratic Language Models","date":"2025-04-19","arxiv_id":"2504.14366","repositories_listed":0,"syntology":null},{"url":null,"slug":"feature-alignment-and-representation-transfer","title":"Feature Alignment and Representation Transfer in Knowledge Distillation for Large Language Models","date":"2025-04-18","arxiv_id":"2504.13825","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-large-to-super-tiny-end-to-end","title":"From Large to Super-Tiny: End-to-End Optimization for Cost-Efficient LLMs","date":"2025-04-18","arxiv_id":"2504.13471","repositories_listed":0,"syntology":null},{"url":null,"slug":"scaling-laws-for-data-efficient-visual","title":"Scaling Laws for Data-Efficient Visual Transfer Learning","date":"2025-04-17","arxiv_id":"2504.13219","repositories_listed":0,"syntology":null},{"url":null,"slug":"transferable-deployment-of-semantic-edge","title":"Transferable Deployment of Semantic Edge Inference Systems via Unsupervised Domain Adaption","date":"2025-04-16","arxiv_id":"2504.11873","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-hybrid-language-model-compression","title":"Efficient Hybrid Language Model Compression through Group-Aware SSM Pruning","date":"2025-04-15","arxiv_id":"2504.11409","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-llms-revolutionize-the-design-of","title":"Can LLMs Revolutionize the Design of Explainable and Efficient TinyML Models?","date":"2025-04-13","arxiv_id":"2504.09685","repositories_listed":0,"syntology":null},{"url":null,"slug":"optimizing-multi-gateway-lorawan-via-cloud","title":"Optimizing Multi-Gateway LoRaWAN via Cloud-Edge Collaboration and Knowledge Distillation","date":"2025-04-13","arxiv_id":"2504.13194","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-distillation-for-multimodal","title":"Knowledge Distillation for Multimodal Egocentric Action Recognition Robust to Missing Modalities","date":"2025-04-11","arxiv_id":"2504.08578","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-distillation-for-underwater-feature","title":"Knowledge Distillation for Underwater Feature Extraction and Matching via GAN-synthesized Images","date":"2025-04-11","arxiv_id":"2504.08253","repositories_listed":0,"syntology":null},{"url":null,"slug":"distilling-knowledge-from-heterogeneous","title":"Distilling Knowledge from Heterogeneous Architectures for Semantic Segmentation","date":"2025-04-10","arxiv_id":"2504.07691","repositories_listed":0,"syntology":null},{"url":null,"slug":"thermostereort-thermal-stereo-matching-in","title":"ThermoStereoRT: Thermal Stereo Matching in Real Time via Knowledge Distillation and Attention-based Refinement","date":"2025-04-10","arxiv_id":"2504.07418","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-unconstrained-2d-pose-estimation-of","title":"Towards Unconstrained 2D Pose Estimation of the Human Spine","date":"2025-04-10","arxiv_id":"2504.08110","repositories_listed":0,"syntology":null},{"url":null,"slug":"wk-pnet-fm-based-positioning-via-wavelet","title":"WK-Pnet: FM-Based Positioning via Wavelet Packet Decomposition and Knowledge Distillation","date":"2025-04-10","arxiv_id":"2504.07399","repositories_listed":0,"syntology":null},{"url":null,"slug":"teaching-pathology-foundation-models-to","title":"Teaching pathology foundation models to accurately predict gene expression with parameter efficient knowledge transfer","date":"2025-04-09","arxiv_id":"2504.07061","repositories_listed":0,"syntology":null},{"url":null,"slug":"resource-efficient-beam-prediction-in-mmwave","title":"Resource-Efficient Beam Prediction in mmWave Communications with Multimodal Realistic Simulation Framework","date":"2025-04-07","arxiv_id":"2504.05187","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-novel-algorithm-for-personalized-federated","title":"A Novel Algorithm for Personalized Federated Learning: Knowledge Distillation with Weighted Combination Loss","date":"2025-04-06","arxiv_id":"2504.04642","repositories_listed":0,"syntology":null},{"url":null,"slug":"corrected-with-the-latest-version-make-robust","title":"Corrected with the Latest Version: Make Robust Asynchronous Federated Learning Possible","date":"2025-04-05","arxiv_id":"2504.04081","repositories_listed":0,"syntology":null},{"url":null,"slug":"agglomerating-large-vision-encoders-via","title":"Agglomerating Large Vision Encoders via Distillation for VFSS Segmentation","date":"2025-04-03","arxiv_id":"2504.02351","repositories_listed":0,"syntology":null},{"url":null,"slug":"causal-self-supervised-pretrained-frontend","title":"Causal Self-supervised Pretrained Frontend with Predictive Code for Speech Separation","date":"2025-04-03","arxiv_id":"2504.02302","repositories_listed":0,"syntology":null},{"url":null,"slug":"marine-saliency-segmenter-object-focused","title":"Marine Saliency Segmenter: Object-Focused Conditional Diffusion with Region-Level Semantic Knowledge Distillation","date":"2025-04-03","arxiv_id":"2504.02391","repositories_listed":0,"syntology":null},{"url":null,"slug":"undo-understanding-distillation-as","title":"UNDO: Understanding Distillation as Optimization","date":"2025-04-03","arxiv_id":"2504.02521","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-novel-approach-to-implementing-knowledge","title":"A Novel Approach To Implementing Knowledge Distillation In Tsetlin Machines","date":"2025-04-02","arxiv_id":"2504.01798","repositories_listed":0,"syntology":null},{"url":null,"slug":"kd-2-m-an-unifying-framework-for-feature","title":"KD$^{2}$M: An unifying framework for feature knowledge distillation","date":"2025-04-02","arxiv_id":"2504.01757","repositories_listed":0,"syntology":null},{"url":null,"slug":"random-conditioning-with-distillation-for","title":"Random Conditioning with Distillation for Data-Efficient Diffusion Model Compression","date":"2025-04-02","arxiv_id":"2504.02011","repositories_listed":0,"syntology":null},{"url":null,"slug":"style-over-substance-distilled-language","title":"Style over Substance: Distilled Language Models Reason Via Stylistic Replication","date":"2025-04-02","arxiv_id":"2504.01738","repositories_listed":0,"syntology":null},{"url":null,"slug":"adversarial-curriculum-graph-free-knowledge","title":"Adversarial Curriculum Graph-Free Knowledge Distillation for Graph Neural Networks","date":"2025-04-01","arxiv_id":"2504.00540","repositories_listed":0,"syntology":null},{"url":null,"slug":"global-intervention-and-distillation-for","title":"Global Intervention and Distillation for Federated Out-of-Distribution Generalization","date":"2025-04-01","arxiv_id":"2504.00850","repositories_listed":0,"syntology":null},{"url":null,"slug":"occludenerf-geometric-aware-3d-scene","title":"OccludeNeRF: Geometric-aware 3D Scene Inpainting with Collaborative Score Distillation in NeRF","date":"2025-04-01","arxiv_id":"2504.02007","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-plasticity-aware-method-for-continual-self","title":"A Plasticity-Aware Method for Continual Self-Supervised Learning in Remote Sensing","date":"2025-03-31","arxiv_id":"2503.24088","repositories_listed":0,"syntology":null},{"url":null,"slug":"crossmodal-knowledge-distillation-with","title":"Crossmodal Knowledge Distillation with WordNet-Relaxed Text Embeddings for Robust Image Classification","date":"2025-03-31","arxiv_id":"2503.24017","repositories_listed":0,"syntology":null},{"url":null,"slug":"is-llm-the-silver-bullet-to-low-resource","title":"Is LLM the Silver Bullet to Low-Resource Languages Machine Translation?","date":"2025-03-31","arxiv_id":"2503.24102","repositories_listed":0,"syntology":null},{"url":null,"slug":"unimodal-driven-distillation-in-multimodal","title":"Unimodal-driven Distillation in Multimodal Emotion Recognition with Dynamic Fusion","date":"2025-03-31","arxiv_id":"2503.23721","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-verified-machine-unlearning-for","title":"Efficient Verified Machine Unlearning For Distillation","date":"2025-03-28","arxiv_id":"2503.22539","repositories_listed":0,"syntology":null},{"url":null,"slug":"intrinsic-image-decomposition-for-robust-self","title":"Intrinsic Image Decomposition for Robust Self-supervised Monocular Depth Estimation on Reflective Surfaces","date":"2025-03-28","arxiv_id":"2503.22209","repositories_listed":0,"syntology":null},{"url":null,"slug":"alleviating-llm-based-generative-retrieval","title":"Alleviating LLM-based Generative Retrieval Hallucination in Alipay Search","date":"2025-03-27","arxiv_id":"2503.21098","repositories_listed":0,"syntology":null},{"url":null,"slug":"delving-deep-into-semantic-relation","title":"Delving Deep into Semantic Relation Distillation","date":"2025-03-27","arxiv_id":"2503.21269","repositories_listed":0,"syntology":null},{"url":null,"slug":"ducksegmentation-a-segmentation-model-based","title":"DuckSegmentation: A segmentation model based on the AnYue Hemp Duck Dataset","date":"2025-03-27","arxiv_id":"2503.21323","repositories_listed":0,"syntology":null},{"url":null,"slug":"mole-vla-dynamic-layer-skipping-vision","title":"MoLe-VLA: Dynamic Layer-skipping Vision Language Action Model via Mixture-of-Layers for Efficient Robot Manipulation","date":"2025-03-26","arxiv_id":"2503.20384","repositories_listed":0,"syntology":null},{"url":null,"slug":"small-object-detection-a-comprehensive-survey","title":"Small Object Detection: A Comprehensive Survey on Challenges, Techniques and Real-World Applications","date":"2025-03-26","arxiv_id":"2503.20516","repositories_listed":0,"syntology":null},{"url":null,"slug":"plug-and-play-interpretable-responsible-text","title":"Plug-and-Play Interpretable Responsible Text-to-Image Generation via Dual-Space Multi-facet Concept Control","date":"2025-03-24","arxiv_id":"2503.18324","repositories_listed":0,"syntology":null},{"url":null,"slug":"customkd-customizing-large-vision-foundation","title":"CustomKD: Customizing Large Vision Foundation for Edge Model Improvement via Knowledge Distillation","date":"2025-03-23","arxiv_id":"2503.18244","repositories_listed":0,"syntology":null},{"url":null,"slug":"fedskd-aggregation-free-model-heterogeneous","title":"FedSKD: Aggregation-free Model-heterogeneous Federated Learning using Multi-dimensional Similarity Knowledge Distillation","date":"2025-03-23","arxiv_id":"2503.18981","repositories_listed":0,"syntology":null},{"url":null,"slug":"omniscience-a-domain-specialized-llm-for","title":"OmniScience: A Domain-Specialized LLM for Scientific Reasoning and Discovery","date":"2025-03-22","arxiv_id":"2503.17604","repositories_listed":0,"syntology":null}],"record_sha256":"2876a1db94e6460626bdfc53b1f479f2b3f02a8b340527bfe86a63edea1f4dcc","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}