{"total":381,"rows":[{"id":"2306.14048","title":"H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models","created":"2023-06-24","cited_by_count":832,"area":"inference"},{"id":"2203.08679","title":"Decoupled Knowledge Distillation","created":"2022-03-16","cited_by_count":388,"area":"distill"},{"id":"2403.06977","title":"VideoMamba: State Space Model for Efficient Video Understanding","created":"2024-03-11","cited_by_count":328,"area":"ssm"},{"id":"2604.13016","title":"Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe","created":"2026-04-14","cited_by_count":299,"area":"lr"},{"id":"2106.05237","title":"Knowledge distillation: A good teacher is patient and consistent","created":"2021-06-09","cited_by_count":259,"area":"distill"},{"id":"2310.17157","title":"Deja Vu: Contextual Sparsity for Efficient LLMs at Inference Time","created":"2023-10-26","cited_by_count":252,"area":null},{"id":"2205.10536","title":"Knowledge Distillation from A Stronger Teacher","created":"2022-05-21","cited_by_count":208,"area":"distill"},{"id":"2106.05945","title":"Does Knowledge Distillation Really Work?","created":"2021-06-10","cited_by_count":190,"area":"distill"},{"id":"2212.08013","title":"FlexiViT: One Model for All Patch Sizes","created":"2022-12-15","cited_by_count":152,"area":null},{"id":"2310.13018","title":"Getting aligned on representational alignment","created":"2023-10-18","cited_by_count":143,"area":null},{"id":"2211.11004","title":"Minimizing the Accumulated Trajectory Error to Improve Dataset Distillation","created":"2022-11-20","cited_by_count":142,"area":null},{"id":"2101.04731","title":"SEED: Self-supervised Distillation For Visual Representation","created":"2021-01-12","cited_by_count":134,"area":null},{"id":"2105.08919","title":"Comparing Kullback-Leibler Divergence and Mean Squared Error Loss in Knowledge Distillation","created":"2021-05-19","cited_by_count":134,"area":"distill"},{"id":"2502.12143","title":"Small Models Struggle to Learn from Strong Reasoners","created":"2025-02-17","cited_by_count":113,"area":"lr"},{"id":"2205.01529","title":"Masked Generative Distillation","created":"2022-05-03","cited_by_count":107,"area":"distill"},{"id":"2403.01427","title":"Logit Standardization in Knowledge Distillation","created":"2024-03-03","cited_by_count":102,"area":"distill"},{"id":"2211.13976","title":"Expanding Small-Scale Datasets with Guided Imagination","created":"2022-11-25","cited_by_count":62,"area":null},{"id":"2303.15786","title":"HOICLIP: Efficient Knowledge Transfer for HOI Detection with Vision-Language Models","created":"2023-03-28","cited_by_count":61,"area":"mllm"},{"id":"2304.12777","title":"Class Attention Transfer Based Knowledge Distillation","created":"2023-04-25","cited_by_count":61,"area":"distill"},{"id":"2102.07650","title":"Learning Student-Friendly Teacher Networks for Knowledge Distillation","created":"2021-02-12","cited_by_count":60,"area":"distill"},{"id":"2212.08071","title":"MAViL: Masked Audio-Video Learners","created":"2022-12-15","cited_by_count":59,"area":null},{"id":"2305.13948","title":"Decoupled Kullback-Leibler Divergence Loss","created":"2023-05-23","cited_by_count":58,"area":"distill"},{"id":"2404.13813","title":"From LLM to NMT: Advancing Low-Resource Machine Translation with Claude","created":"2024-04-22","cited_by_count":58,"area":null},{"id":"2401.16335","title":"Iterative Data Smoothing: Mitigating Reward Overfitting and Overoptimization in RLHF","created":"2024-01-29","cited_by_count":57,"area":"alignment"},{"id":"2306.11369","title":"CrossKD: Cross-Head Knowledge Distillation for Object Detection","created":"2023-06-20","cited_by_count":52,"area":"distill"},{"id":"2103.01396","title":"DeepReDuce: ReLU Reduction for Fast Private Inference","created":"2021-03-02","cited_by_count":50,"area":null},{"id":"2205.15308","title":"Parameter-Efficient and Student-Friendly Knowledge Distillation","created":"2022-05-28","cited_by_count":47,"area":"distill"},{"id":"2402.04616","title":"Beyond Answers: Transferring Reasoning Capabilities to Smaller LLMs Using Multi-Teacher Knowledge Distillation","created":"2024-02-07","cited_by_count":47,"area":"lr"},{"id":"2112.12731","title":"ERNIE 3.0 Titan: Exploring Larger-scale Knowledge Enhanced Pre-training for Language Understanding and Generation","created":"2021-12-23","cited_by_count":46,"area":null},{"id":"2103.01353","title":"There is More than Meets the Eye: Self-Supervised Multi-Object Detection and Tracking with Sound by Distilling Multimodal Knowledge","created":"2021-03-01","cited_by_count":44,"area":"distill"},{"id":"2202.03680","title":"Exploring Inter-Channel Correlation for Diversity-preserved KnowledgeDistillation","created":"2022-02-08","cited_by_count":44,"area":"distill"},{"id":"2206.06487","title":"The Modality Focusing Hypothesis: Towards Understanding Crossmodal Knowledge Distillation","created":"2022-06-13","cited_by_count":44,"area":"distill"},{"id":"2304.05627","title":"Constructing Deep Spiking Neural Networks from Artificial Neural Networks with Knowledge Distillation","created":"2023-04-12","cited_by_count":44,"area":"distill"},{"id":"2103.05254","title":"MetaCorrection: Domain-aware Meta Loss Correction for Unsupervised Domain Adaptation in Semantic Segmentation","created":"2021-03-09","cited_by_count":43,"area":null},{"id":"2402.11890","title":"Revisiting Knowledge Distillation for Autoregressive Language Models","created":"2024-02-19","cited_by_count":42,"area":"distill"},{"id":"2206.06067","title":"Better Teacher Better Student: Dynamic Prior Knowledge for Knowledge Distillation","created":"2022-06-13","cited_by_count":41,"area":"distill"},{"id":"2106.12378","title":"Co-advise: Cross Inductive Bias Distillation","created":"2021-06-23","cited_by_count":40,"area":null},{"id":"2111.06061","title":"Edge-Cloud Polarization and Collaboration: A Comprehensive Survey for AI","created":"2021-11-11","cited_by_count":39,"area":null},{"id":"2210.06458","title":"Efficient Knowledge Distillation from Model Checkpoints","created":"2022-10-12","cited_by_count":37,"area":"distill"},{"id":"2208.12256","title":"Masked Autoencoders Enable Efficient Knowledge Distillers","created":"2022-08-25","cited_by_count":36,"area":"distill"},{"id":"2111.06638","title":"Meta-Teacher For Face Anti-Spoofing","created":"2021-11-12","cited_by_count":33,"area":null},{"id":"2404.16456","title":"Correlation-Decoupled Knowledge Distillation for Multimodal Sentiment Analysis with Incomplete Modalities","created":"2024-04-25","cited_by_count":32,"area":"distill"},{"id":"2102.07594","title":"Fast End-to-End Speech Recognition via Non-Autoregressive Models and Cross-Modal Knowledge Transferring from BERT","created":"2021-02-15","cited_by_count":31,"area":null},{"id":"2109.03775","title":"FedZKT: Zero-Shot Knowledge Transfer towards Resource-Constrained Federated Learning with Heterogeneous On-Device Models","created":"2021-09-08","cited_by_count":31,"area":null},{"id":"2205.14443","title":"A Closer Look at Self-Supervised Lightweight Vision Transformers","created":"2022-05-28","cited_by_count":31,"area":null},{"id":"2104.09732","title":"Knowledge Distillation as Semiparametric Inference","created":"2021-04-20","cited_by_count":29,"area":"distill"},{"id":"2209.04996","title":"Switchable Online Knowledge Distillation","created":"2022-09-12","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":"2307.07483","title":"Multimodal Distillation for Egocentric Action Recognition","created":"2023-07-14","cited_by_count":28,"area":"distill"},{"id":"2110.14149","title":"Diversity Matters When Learning From Ensembles","created":"2021-10-27","cited_by_count":27,"area":null},{"id":"2205.16004","title":"What Knowledge Gets Distilled in Knowledge Distillation?","created":"2022-05-31","cited_by_count":27,"area":"distill"},{"id":"2605.07804","title":"Prune-OPD: Efficient and Reliable On-Policy Distillation for Long-Horizon Reasoning","created":"2026-05-08","cited_by_count":27,"area":"lr"},{"id":"2204.00089","title":"Investigating Top-$k$ White-Box and Transferable Black-box Attack","created":"2022-03-30","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":"2410.03190","title":"Tuning Timestep-Distilled Diffusion Model Using Pairwise Sample Optimization","created":"2024-10-04","cited_by_count":26,"area":"diffusion"},{"id":"2302.09632","title":"HomoDistil: Homotopic Task-Agnostic Distillation of Pre-trained Transformers","created":"2023-02-19","cited_by_count":25,"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":"2401.08732","title":"Bayes Conditional Distribution Estimation for Knowledge Distillation Based on Conditional Mutual Information","created":"2024-01-16","cited_by_count":25,"area":"distill"},{"id":"2402.12842","title":"PromptKD: Distilling Student-Friendly Knowledge for Generative Language Models via Prompt Tuning","created":"2024-02-20","cited_by_count":25,"area":"distill"},{"id":"2605.10889","title":"Unmasking On-Policy Distillation: Where It Helps, Where It Hurts, and Why","created":"2026-05-11","cited_by_count":25,"area":"lr"},{"id":"2105.11683","title":"Towards Compact Single Image Super-Resolution via Contrastive Self-distillation","created":"2021-05-25","cited_by_count":24,"area":"distill"},{"id":"2109.06875","title":"Multi-Scale Aligned Distillation for Low-Resolution Detection","created":"2021-09-14","cited_by_count":24,"area":"distill"},{"id":"2110.08890","title":"Network Augmentation for Tiny Deep Learning","created":"2021-10-17","cited_by_count":24,"area":null},{"id":"2206.08491","title":"Revisiting Self-Distillation","created":"2022-06-17","cited_by_count":24,"area":"distill"},{"id":"2210.04208","title":"Let Images Give You More:Point Cloud Cross-Modal Training for Shape Analysis","created":"2022-10-09","cited_by_count":24,"area":null},{"id":"2301.01296","title":"TinyMIM: An Empirical Study of Distilling MIM Pre-trained Models","created":"2023-01-03","cited_by_count":24,"area":null},{"id":"2412.14964","title":"Efficient Knowledge Injection in LLMs via Self-Distillation","created":"2024-12-19","cited_by_count":24,"area":"distill"},{"id":"2105.12971","title":"Joint-DetNAS: Upgrade Your Detector with NAS, Pruning and Dynamic Distillation","created":"2021-05-27","cited_by_count":23,"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":"2505.04560","title":"ABKD: Pursuing a Proper Allocation of the Probability Mass in Knowledge Distillation via $\\alpha$-$\\beta$-Divergence","created":"2025-05-07","cited_by_count":23,"area":"distill"},{"id":"2103.14473","title":"Distilling a Powerful Student Model via Online Knowledge Distillation","created":"2021-03-26","cited_by_count":22,"area":"distill"},{"id":"2201.02356","title":"Cross-Modality Deep Feature Learning for Brain Tumor Segmentation","created":"2022-01-07","cited_by_count":22,"area":null},{"id":"2205.02399","title":"Spot-adaptive Knowledge Distillation","created":"2022-05-05","cited_by_count":22,"area":"distill"},{"id":"2304.01279","title":"Long-Tailed Visual Recognition via Self-Heterogeneous Integration with Knowledge Excavation","created":"2023-04-03","cited_by_count":22,"area":"moe"},{"id":"2501.16937","title":"TAID: Temporally Adaptive Interpolated Distillation for Efficient Knowledge Transfer in Language Models","created":"2025-01-28","cited_by_count":22,"area":"distill"},{"id":"2104.12528","title":"Spatio-Temporal Pruning and Quantization for Low-latency Spiking Neural Networks","created":"2021-04-26","cited_by_count":21,"area":null},{"id":"2106.10494","title":"Teacher's pet: understanding and mitigating biases in distillation","created":"2021-06-19","cited_by_count":21,"area":"distill"},{"id":"2203.02485","title":"Better Supervisory Signals by Observing Learning Paths","created":"2022-03-04","cited_by_count":21,"area":"distill"},{"id":"2406.19774","title":"Direct Preference Knowledge Distillation for Large Language Models","created":"2024-06-28","cited_by_count":21,"area":"alignment"},{"id":"2202.07940","title":"Meta Knowledge Distillation","created":"2022-02-16","cited_by_count":20,"area":"distill"},{"id":"2203.17008","title":"It's All In the Teacher: Zero-Shot Quantization Brought Closer to the Teacher","created":"2022-03-31","cited_by_count":20,"area":null},{"id":"2306.10687","title":"Categories of Response-Based, Feature-Based, and Relation-Based Knowledge Distillation","created":"2023-06-19","cited_by_count":20,"area":"distill"},{"id":"2402.04513","title":"Online Cascade Learning for Efficient Inference over Streams","created":"2024-02-07","cited_by_count":20,"area":null},{"id":"2209.09841","title":"Exploring Inconsistent Knowledge Distillation for Object Detection with Data Augmentation","created":"2022-09-20","cited_by_count":19,"area":"distill"},{"id":"2301.12245","title":"Supervision Complexity and its Role in Knowledge Distillation","created":"2023-01-28","cited_by_count":19,"area":"distill"},{"id":"2308.10306","title":"Omnidirectional Information Gathering for Knowledge Transfer-based Audio-Visual Navigation","created":"2023-08-20","cited_by_count":19,"area":null},{"id":"2411.18674","title":"Active Data Curation Effectively Distills Large-Scale Multimodal Models","created":"2024-11-27","cited_by_count":19,"area":"distill"},{"id":"2607.13399","title":"Demystifying On-Policy Distillation: Roles, Pathologies, and Regulations","created":"2026-07-15","cited_by_count":19,"area":"distill"},{"id":"2203.07159","title":"On the benefits of knowledge distillation for adversarial robustness","created":"2022-03-14","cited_by_count":18,"area":"distill"},{"id":"2208.05642","title":"Self-Knowledge Distillation via Dropout","created":"2022-08-11","cited_by_count":18,"area":"distill"},{"id":"2210.12787","title":"Respecting Transfer Gap in Knowledge Distillation","created":"2022-10-23","cited_by_count":18,"area":"distill"},{"id":"2304.11379","title":"LiDAR2Map: In Defense of LiDAR-Based Semantic Map Construction Using Online Camera Distillation","created":"2023-04-22","cited_by_count":18,"area":null},{"id":"2307.08500","title":"Cumulative Spatial Knowledge Distillation for Vision Transformers","created":"2023-07-17","cited_by_count":18,"area":"distill"},{"id":"2310.07265","title":"Distilling Efficient Vision Transformers from CNNs for Semantic Segmentation","created":"2023-10-11","cited_by_count":18,"area":"distill"},{"id":"2608.19098","title":"Open-MOPD: Diagnosing and Fixing Capability Imbalance in Multi-Teacher On-Policy Distillation","created":"2026-08-19","cited_by_count":18,"area":"lr"},{"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":"2211.09768","title":"D$^3$ETR: Decoder Distillation for Detection Transformer","created":"2022-11-17","cited_by_count":17,"area":"distill"},{"id":"2307.00331","title":"Quantization Variation: A New Perspective on Training Transformers with Low-Bit Precision","created":"2023-07-01","cited_by_count":17,"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":"2411.02793","title":"Toward Robust Incomplete Multimodal Sentiment Analysis via Hierarchical Representation Learning","created":"2024-11-05","cited_by_count":16,"area":null}],"next_cursor":"100"}