{"total":233,"rows":[{"id":"2105.13093","title":"Towards Understanding Knowledge Distillation","created":"2021-05-27","cited_by_count":158,"area":"distill"},{"id":"2106.05266","title":"Semi-Supervised 3D Hand-Object Poses Estimation with Interactions in Time","created":"2021-06-09","cited_by_count":141,"area":null},{"id":"2104.07905","title":"Ego-Exo: Transferring Visual Representations from Third-person to First-person Videos","created":"2021-04-16","cited_by_count":99,"area":null},{"id":"2311.06750","title":"Federated Learning for Generalization, Robustness, Fairness: A Survey and Benchmark","created":"2023-11-12","cited_by_count":99,"area":null},{"id":"2104.08271","title":"TEACHTEXT: CrossModal Generalized Distillation for Text-Video Retrieval","created":"2021-04-16","cited_by_count":81,"area":null},{"id":"2103.04062","title":"Adaptive Multi-Teacher Multi-level Knowledge Distillation","created":"2021-03-06","cited_by_count":72,"area":"distill"},{"id":"2106.09564","title":"Knowledge distillation from multi-modal to mono-modal segmentation networks","created":"2021-06-17","cited_by_count":68,"area":"distill"},{"id":"2502.08606","title":"Distillation Scaling Laws","created":"2025-02-12","cited_by_count":67,"area":"lr"},{"id":"2104.07163","title":"Annealing Knowledge Distillation","created":"2021-04-14","cited_by_count":61,"area":"distill"},{"id":"2110.06923","title":"Object DGCNN: 3D Object Detection using Dynamic Graphs","created":"2021-10-13","cited_by_count":58,"area":null},{"id":"2211.13916","title":"Towards Good Practices for Missing Modality Robust Action Recognition","created":"2022-11-25","cited_by_count":54,"area":null},{"id":"2402.02769","title":"Learning from Teaching Regularization: Generalizable Correlations Should be Easy to Imitate","created":"2024-02-05","cited_by_count":47,"area":null},{"id":"2206.06487","title":"The Modality Focusing Hypothesis: Towards Understanding Crossmodal Knowledge Distillation","created":"2022-06-13","cited_by_count":44,"area":"distill"},{"id":"2106.12378","title":"Co-advise: Cross Inductive Bias Distillation","created":"2021-06-23","cited_by_count":40,"area":null},{"id":"2103.03467","title":"Teachers Do More Than Teach: Compressing Image-to-Image Models","created":"2021-03-05","cited_by_count":37,"area":null},{"id":"2206.14532","title":"Revisiting Label Smoothing and Knowledge Distillation Compatibility: What was Missing?","created":"2022-06-29","cited_by_count":32,"area":"distill"},{"id":"2108.03267","title":"BiMaL: Bijective Maximum Likelihood Approach to Domain Adaptation in Semantic Scene Segmentation","created":"2021-08-06","cited_by_count":31,"area":null},{"id":"2106.13948","title":"Core Challenges in Embodied Vision-Language Planning","created":"2021-06-26","cited_by_count":30,"area":null},{"id":"2104.09732","title":"Knowledge Distillation as Semiparametric Inference","created":"2021-04-20","cited_by_count":29,"area":"distill"},{"id":"2107.02629","title":"Embracing the Dark Knowledge: Domain Generalization Using Regularized Knowledge Distillation","created":"2021-07-06","cited_by_count":29,"area":"distill"},{"id":"2303.15678","title":"DisWOT: Student Architecture Search for Distillation WithOut Training","created":"2023-03-28","cited_by_count":29,"area":"distill"},{"id":"2303.15410","title":"Human Pose Estimation in Extremely Low-Light Conditions","created":"2023-03-27","cited_by_count":27,"area":null},{"id":"2303.06869","title":"Adaptive Data-Free Quantization","created":"2023-03-13","cited_by_count":26,"area":null},{"id":"2403.06213","title":"$V_kD:$ Improving Knowledge Distillation using Orthogonal Projections","created":"2024-03-10","cited_by_count":26,"area":"distill"},{"id":"2305.12129","title":"Lifting the Curse of Capacity Gap in Distilling Language Models","created":"2023-05-20","cited_by_count":25,"area":"moe"},{"id":"2206.08491","title":"Revisiting Self-Distillation","created":"2022-06-17","cited_by_count":24,"area":"distill"},{"id":"2303.09830","title":"Prototype Knowledge Distillation for Medical Segmentation with Missing Modality","created":"2023-03-17","cited_by_count":24,"area":"distill"},{"id":"2210.04427","title":"Asymmetric Temperature Scaling Makes Larger Networks Teach Well Again","created":"2022-10-10","cited_by_count":23,"area":"distill"},{"id":"2210.13014","title":"Geometric Knowledge Distillation: Topology Compression for Graph Neural Networks","created":"2022-10-24","cited_by_count":22,"area":"distill"},{"id":"2106.10494","title":"Teacher's pet: understanding and mitigating biases in distillation","created":"2021-06-19","cited_by_count":21,"area":"distill"},{"id":"2301.13304","title":"Understanding Self-Distillation in the Presence of Label Noise","created":"2023-01-30","cited_by_count":21,"area":"distill"},{"id":"2106.08769","title":"Knowledge-Adaptation Priors","created":"2021-06-16","cited_by_count":20,"area":null},{"id":"2402.12022","title":"Distilling Large Language Models for Text-Attributed Graph Learning","created":"2024-02-19","cited_by_count":20,"area":"distill"},{"id":"2505.02138","title":"Efficient Multivariate Time Series Forecasting via Calibrated Language Models with Privileged Knowledge Distillation","created":"2025-05-04","cited_by_count":20,"area":"distill"},{"id":"2208.08741","title":"Quantifying the Knowledge in a DNN to Explain Knowledge Distillation for Classification","created":"2022-08-18","cited_by_count":19,"area":"distill"},{"id":"2105.01646","title":"Motion-Augmented Self-Training for Video Recognition at Smaller Scale","created":"2021-05-04","cited_by_count":17,"area":null},{"id":"2106.02654","title":"Churn Reduction via Distillation","created":"2021-06-04","cited_by_count":17,"area":null},{"id":"2110.08532","title":"Pro-KD: Progressive Distillation by Following the Footsteps of the Teacher","created":"2021-10-16","cited_by_count":17,"area":null},{"id":"2107.00197","title":"Few-Shot Learning with a Strong Teacher","created":"2021-07-01","cited_by_count":16,"area":null},{"id":"2209.08754","title":"Toward Understanding Privileged Features Distillation in Learning-to-Rank","created":"2022-09-19","cited_by_count":16,"area":null},{"id":"2301.12923","title":"On student-teacher deviations in distillation: does it pay to disobey?","created":"2023-01-30","cited_by_count":16,"area":"distill"},{"id":"2202.09244","title":"Transfer and Marginalize: Explaining Away Label Noise with Privileged Information","created":"2022-02-18","cited_by_count":15,"area":null},{"id":"2407.04600","title":"Understanding the Gains from Repeated Self-Distillation","created":"2024-07-05","cited_by_count":15,"area":"distill"},{"id":"2104.05965","title":"Dealing with Missing Modalities in the Visual Question Answer-Difference Prediction Task through Knowledge Distillation","created":"2021-04-13","cited_by_count":14,"area":"distill"},{"id":"2605.11609","title":"Anti-Self-Distillation for Reasoning RL via Pointwise Mutual Information","created":"2026-05-12","cited_by_count":14,"area":"lr"},{"id":"2306.16170","title":"Mitigating Accuracy-Robustness Trade-off via Balanced Multi-Teacher Adversarial Distillation","created":"2023-06-28","cited_by_count":13,"area":null},{"id":"2502.12465","title":"Computational-Statistical Tradeoffs at the Next-Token Prediction Barrier: Autoregressive and Imitation Learning under Misspecification","created":"2025-02-18","cited_by_count":13,"area":"offlinerl"},{"id":"2111.08774","title":"Finding the Right Moment: Human-Assisted Trailer Creation via Task Composition","created":"2021-11-16","cited_by_count":12,"area":null},{"id":"2203.14649","title":"Knowledge Distillation: Bad Models Can Be Good Role Models","created":"2022-03-28","cited_by_count":12,"area":"distill"},{"id":"2207.05049","title":"Fast-Vid2Vid: Spatial-Temporal Compression for Video-to-Video Synthesis","created":"2022-07-11","cited_by_count":12,"area":null},{"id":"2305.10919","title":"From the Lab to the Wild: Affect Modeling via Privileged Information","created":"2023-05-18","cited_by_count":12,"area":null},{"id":"2608.09228","title":"Privileged Solutions or Context-Induced Teacher Behavior? Dissecting On-Policy Self-Distillation","created":"2026-08-10","cited_by_count":12,"area":"distill"},{"id":"2305.17581","title":"Knowledge Distillation Performs Partial Variance Reduction","created":"2023-05-27","cited_by_count":11,"area":"distill"},{"id":"2406.02886","title":"PLaD: Preference-based Large Language Model Distillation with Pseudo-Preference Pairs","created":"2024-06-05","cited_by_count":11,"area":"distill"},{"id":"2105.13608","title":"Not Far Away, Not So Close: Sample Efficient Nearest Neighbour Data Augmentation via MiniMax","created":"2021-05-28","cited_by_count":10,"area":null},{"id":"2105.14975","title":"Privileged Graph Distillation for Cold Start Recommendation","created":"2021-05-31","cited_by_count":10,"area":null},{"id":"2110.14432","title":"Iterative Teaching by Label Synthesis","created":"2021-10-27","cited_by_count":10,"area":null},{"id":"2303.01806","title":"When does Privileged Information Explain Away Label Noise?","created":"2023-03-03","cited_by_count":10,"area":null},{"id":"2603.13134","title":"When Right Meets Wrong: Bilateral Context Conditioning with Reward-Confidence Correction for GRPO","created":"2026-03-13","cited_by_count":10,"area":"lr"},{"id":"2104.03618","title":"MRI-based Alzheimer's disease prediction via distilling the knowledge in multi-modal data","created":"2021-04-08","cited_by_count":9,"area":null},{"id":"2111.10561","title":"Teacher-Student Training and Triplet Loss to Reduce the Effect of Drastic Face Occlusion","created":"2021-11-20","cited_by_count":9,"area":"distill"},{"id":"2605.22511","title":"Search-E1: Self-Distillation Drives Self-Evolution in Search-Augmented Reasoning","created":"2026-05-21","cited_by_count":9,"area":"lr"},{"id":"2608.01589","title":"Is More Privileged Information Better? From Solution Traces to Problem-Solving Structure in Self-Distilled Reasoning","created":"2026-08-03","cited_by_count":9,"area":"distill"},{"id":"2105.00104","title":"Distilling EEG Representations via Capsules for Affective Computing","created":"2021-04-30","cited_by_count":8,"area":null},{"id":"2201.06945","title":"It's All in the Head: Representation Knowledge Distillation through Classifier Sharing","created":"2022-01-18","cited_by_count":8,"area":"distill"},{"id":"2102.06849","title":"Distilling Double Descent","created":"2021-02-13","cited_by_count":7,"area":"distill"},{"id":"2208.13648","title":"Dynamic Data-Free Knowledge Distillation by Easy-to-Hard Learning Strategy","created":"2022-08-29","cited_by_count":7,"area":"distill"},{"id":"2307.08436","title":"DOT: A Distillation-Oriented Trainer","created":"2023-07-17","cited_by_count":7,"area":"distill"},{"id":"2308.15846","title":"Exploring Multi-Modal Contextual Knowledge for Open-Vocabulary Object Detection","created":"2023-08-30","cited_by_count":7,"area":null},{"id":"2406.05405","title":"Robust Conformal Prediction Using Privileged Information","created":"2024-06-08","cited_by_count":7,"area":null},{"id":"2411.01547","title":"Decoupling Dark Knowledge via Block-wise Logit Distillation for Feature-level Alignment","created":"2024-11-03","cited_by_count":7,"area":"distill"},{"id":"2509.01649","title":"Distilled Pretraining: A modern lens of Data, In-Context Learning and Test-Time Scaling","created":"2025-09-01","cited_by_count":7,"area":"lr"},{"id":"2605.20643","title":"AVSD: Adaptive-View Self-Distillation by Balancing Consensus and Teacher-Specific Privileged Signals","created":"2026-05-20","cited_by_count":7,"area":"distill"},{"id":"2608.06243","title":"DASH: Divergence-Adaptive Supervision Horizons for On-Policy Self-Distillation of Reasoning Models","created":"2026-08-06","cited_by_count":7,"area":"lr"},{"id":"2103.11083","title":"Compacting Deep Neural Networks for Internet of Things: Methods and Applications","created":"2021-03-20","cited_by_count":6,"area":null},{"id":"2110.14993","title":"Using Time-Series Privileged Information for Provably Efficient Learning of Prediction Models","created":"2021-10-28","cited_by_count":6,"area":null},{"id":"2203.10163","title":"A Closer Look at Knowledge Distillation with Features, Logits, and Gradients","created":"2022-03-18","cited_by_count":6,"area":"distill"},{"id":"2207.09960","title":"Measuring and signing fairness as performance under multiple stakeholder distributions","created":"2022-07-20","cited_by_count":6,"area":null},{"id":"2404.09326","title":"Weight Copy and Low-Rank Adaptation for Few-Shot Distillation of Vision Transformers","created":"2024-04-14","cited_by_count":6,"area":"distill"},{"id":"2608.08726","title":"PAST: Privileged Adaptation from Complete Student Trajectories for On-Policy Self-Distillation","created":"2026-08-09","cited_by_count":6,"area":"lr"},{"id":"2106.08112","title":"Contextualizing Meta-Learning via Learning to Decompose","created":"2021-06-15","cited_by_count":5,"area":null},{"id":"2302.11984","title":"Unsupervised Domain Adaptation via Distilled Discriminative Clustering","created":"2023-02-23","cited_by_count":5,"area":null},{"id":"2407.13254","title":"Make a Strong Teacher with Label Assistance: A Novel Knowledge Distillation Approach for Semantic Segmentation","created":"2024-07-18","cited_by_count":5,"area":"distill"},{"id":"2409.11786","title":"Efficient Low-Resolution Face Recognition via Bridge Distillation","created":"2024-09-18","cited_by_count":5,"area":null},{"id":"2503.04824","title":"ProReflow: Progressive Reflow with Decomposed Velocity","created":"2025-03-05","cited_by_count":5,"area":"diffusion"},{"id":"2605.18299","title":"SD-Search: On-Policy Hindsight Self-Distillation for Search-Augmented Reasoning","created":"2026-05-18","cited_by_count":5,"area":"distill"},{"id":"2608.09826","title":"Distill Skills into Weights, Not Prompts: Abstract Skills as Privileged Signals for On-Policy Self-Distillation","created":"2026-08-10","cited_by_count":5,"area":"distill"},{"id":"2108.05598","title":"AffRankNet+: Ranking Affect Using Privileged Information","created":"2021-08-12","cited_by_count":4,"area":null},{"id":"2108.10131","title":"Improving the trustworthiness of image classification models by utilizing bounding-box annotations","created":"2021-08-15","cited_by_count":4,"area":null},{"id":"2110.09674","title":"Adaptive Distillation: Aggregating Knowledge from Multiple Paths for Efficient Distillation","created":"2021-10-19","cited_by_count":4,"area":"distill"},{"id":"2209.07067","title":"Efficient learning of nonlinear prediction models with time-series privileged information","created":"2022-09-15","cited_by_count":4,"area":null},{"id":"2303.09350","title":"Unsupervised domain adaptation by learning using privileged information","created":"2023-03-16","cited_by_count":4,"area":null},{"id":"2310.02421","title":"Can a student Large Language Model perform as well as it's teacher?","created":"2023-10-03","cited_by_count":4,"area":"distill"},{"id":"2310.07838","title":"Towards the Fundamental Limits of Knowledge Transfer over Finite Domains","created":"2023-10-11","cited_by_count":4,"area":null},{"id":"2404.00548","title":"Modeling State Shifting via Local-Global Distillation for Event-Frame Gaze Tracking","created":"2024-03-31","cited_by_count":4,"area":null},{"id":"2405.13078","title":"Exploring Dark Knowledge under Various Teacher Capacities and Addressing Capacity Mismatch","created":"2024-05-21","cited_by_count":4,"area":"distill"},{"id":"2409.19178","title":"FLINT: Learning-based Flow Estimation and Temporal Interpolation for Scientific Ensemble Visualization","created":"2024-09-27","cited_by_count":4,"area":null},{"id":"2410.03038","title":"CPFD: Confidence-aware Privileged Feature Distillation for Short Video Classification","created":"2024-10-03","cited_by_count":4,"area":"distill"},{"id":"2505.24361","title":"Revisiting Cross-Modal Knowledge Distillation: A Disentanglement Approach for RGBD Semantic Segmentation","created":"2025-05-30","cited_by_count":4,"area":"distill"},{"id":"2605.07505","title":"LiteGUI: Lightweight GUI Agents via Multi-Solution Guided Distillation and Dual-Level Reinforcement Learning","created":"2026-05-08","cited_by_count":4,"area":"lr"}],"next_cursor":"100"}