{"total":76,"rows":[{"id":"2305.02301","title":"Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizes","created":"2023-05-03","cited_by_count":737,"area":null},{"id":"2207.04397","title":"2DPASS: 2D Priors Assisted Semantic Segmentation on LiDAR Point Clouds","created":"2022-07-10","cited_by_count":158,"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":"2206.01254","title":"Which Explanation Should I Choose? A Function Approximation Perspective to Characterizing Post Hoc Explanations","created":"2022-06-02","cited_by_count":77,"area":null},{"id":"2203.00843","title":"X-Trans2Cap: Cross-Modal Knowledge Transfer using Transformer for 3D Dense Captioning","created":"2022-03-02","cited_by_count":70,"area":"distill"},{"id":"2204.12997","title":"DearKD: Data-Efficient Early Knowledge Distillation for Vision Transformers","created":"2022-04-27","cited_by_count":65,"area":"distill"},{"id":"2203.13104","title":"R-DFCIL: Relation-Guided Representation Learning for Data-Free Class Incremental Learning","created":"2022-03-24","cited_by_count":59,"area":null},{"id":"2111.05193","title":"A Survey on Green Deep Learning","created":"2021-11-08","cited_by_count":52,"area":null},{"id":"2305.13803","title":"NORM: Knowledge Distillation via N-to-One Representation Matching","created":"2023-05-23","cited_by_count":44,"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":"2303.15678","title":"DisWOT: Student Architecture Search for Distillation WithOut Training","created":"2023-03-28","cited_by_count":29,"area":"distill"},{"id":"2110.14149","title":"Diversity Matters When Learning From Ensembles","created":"2021-10-27","cited_by_count":27,"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":"2305.02279","title":"Learngene: Inheriting Condensed Knowledge from the Ancestry Model to Descendant Models","created":"2023-05-03","cited_by_count":24,"area":null},{"id":"2205.02399","title":"Spot-adaptive Knowledge Distillation","created":"2022-05-05","cited_by_count":22,"area":"distill"},{"id":"2205.14812","title":"TaSIL: Taylor Series Imitation Learning","created":"2022-05-30","cited_by_count":21,"area":"offlinerl"},{"id":"2305.19101","title":"Which Models have Perceptually-Aligned Gradients? An Explanation via Off-Manifold Robustness","created":"2023-05-30","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":"2108.12905","title":"Lipschitz Continuity Guided Knowledge Distillation","created":"2021-08-29","cited_by_count":19,"area":"distill"},{"id":"2112.05683","title":"Boosting Active Learning via Improving Test Performance","created":"2021-12-10","cited_by_count":19,"area":null},{"id":"2306.10014","title":"Coaching a Teachable Student","created":"2023-06-16","cited_by_count":19,"area":"distill"},{"id":"2108.13576","title":"Dead Pixel Test Using Effective Receptive Field","created":"2021-08-31","cited_by_count":18,"area":null},{"id":"2402.03119","title":"Good Teachers Explain: Explanation-Enhanced Knowledge Distillation","created":"2024-02-05","cited_by_count":14,"area":"distill"},{"id":"2109.14960","title":"Prune Your Model Before Distill It","created":"2021-09-30","cited_by_count":12,"area":"distill"},{"id":"2205.01915","title":"Generalized Knowledge Distillation via Relationship Matching","created":"2022-05-04","cited_by_count":12,"area":"distill"},{"id":"2102.13088","title":"Even your Teacher Needs Guidance: Ground-Truth Targets Dampen Regularization Imposed by Self-Distillation","created":"2021-02-25","cited_by_count":11,"area":"distill"},{"id":"2107.04386","title":"Joint Matrix Decomposition for Deep Convolutional Neural Networks Compression","created":"2021-07-09","cited_by_count":10,"area":null},{"id":"2111.12490","title":"Matching Learned Causal Effects of Neural Networks with Domain Priors","created":"2021-11-24","cited_by_count":10,"area":null},{"id":"2111.05073","title":"MixACM: Mixup-Based Robustness Transfer via Distillation of Activated Channel Maps","created":"2021-11-09","cited_by_count":9,"area":null},{"id":"2405.07562","title":"GLiRA: Black-Box Membership Inference Attack via Knowledge Distillation","created":"2024-05-13","cited_by_count":7,"area":"safety"},{"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":"2204.01971","title":"Non-Local Latent Relation Distillation for Self-Adaptive 3D Human Pose Estimation","created":"2022-04-05","cited_by_count":6,"area":null},{"id":"2206.15047","title":"Improving Ensemble Distillation With Weight Averaging and Diversifying Perturbation","created":"2022-06-30","cited_by_count":6,"area":"distill"},{"id":"2403.03846","title":"Can Distillation Mitigate Backdoor Attacks in Pre-trained Encoders?","created":"2024-03-06","cited_by_count":6,"area":"safety"},{"id":"2211.01071","title":"Gradient Knowledge Distillation for Pre-trained Language Models","created":"2022-11-02","cited_by_count":5,"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":"2608.01263","title":"Distill What the Student Can See: Fisher-Projected On-Policy Distillation for Vision-Language Models","created":"2026-08-02","cited_by_count":4,"area":"mllm"},{"id":"2102.04208","title":"Contrastive Embeddings for Neural Architectures","created":"2021-02-08","cited_by_count":3,"area":null},{"id":"2307.13885","title":"Characterizing Data Point Vulnerability via Average-Case Robustness","created":"2023-07-26","cited_by_count":3,"area":null},{"id":"2311.12813","title":"Targeted Activation Penalties Help CNNs Ignore Spurious Signals","created":"2023-09-22","cited_by_count":3,"area":null},{"id":"2504.09876","title":"HDC: Hierarchical Distillation for Multi-level Noisy Consistency in Semi-Supervised Fetal Ultrasound Segmentation","created":"2025-04-14","cited_by_count":3,"area":null},{"id":"2103.07600","title":"Student-Teacher Learning from Clean Inputs to Noisy Inputs","created":"2021-03-13","cited_by_count":2,"area":null},{"id":"2103.10047","title":"Similarity Transfer for Knowledge Distillation","created":"2021-03-18","cited_by_count":2,"area":"distill"},{"id":"2202.01011","title":"Auto-Transfer: Learning to Route Transferrable Representations","created":"2022-02-02","cited_by_count":2,"area":null},{"id":"2205.02604","title":"Holistic Approach to Measure Sample-level Adversarial Vulnerability and its Utility in Building Trustworthy Systems","created":"2022-05-05","cited_by_count":2,"area":null},{"id":"2206.13130","title":"Revisiting Architecture-aware Knowledge Distillation: Smaller Models and Faster Search","created":"2022-06-27","cited_by_count":2,"area":"distill"},{"id":"2601.05913","title":"Distilling Lightweight Domain Experts from Large ML Models by Identifying Relevant Subspaces","created":"2026-01-09","cited_by_count":2,"area":"distill"},{"id":"2112.09532","title":"Pixel Distillation: A New Knowledge Distillation Scheme for Low-Resolution Image Recognition","created":"2021-12-17","cited_by_count":1,"area":"distill"},{"id":"2204.11526","title":"Selective Cross-Task Distillation","created":"2022-04-25","cited_by_count":1,"area":"distill"},{"id":"2208.11628","title":"Debias the Black-box: A Fair Ranking Framework via Knowledge Distillation","created":"2022-08-24","cited_by_count":1,"area":"distill"},{"id":"2304.02641","title":"Self-Distillation for Gaussian Process Regression and Classification","created":"2023-04-05","cited_by_count":1,"area":"distill"},{"id":"2409.18785","title":"Student-Oriented Teacher Knowledge Refinement for Knowledge Distillation","created":"2024-09-27","cited_by_count":1,"area":"distill"},{"id":"2412.00696","title":"Intermediate Outputs Are More Sensitive Than You Think","created":"2024-12-01","cited_by_count":1,"area":null},{"id":"2604.19011","title":"Accelerating trajectory optimization with Sobolev-trained diffusion policies","created":"2026-04-21","cited_by_count":1,"area":"diffusion"},{"id":"2106.00368","title":"Natural Statistics of Network Activations and Implications for Knowledge Distillation","created":"2021-06-01","cited_by_count":0,"area":"distill"},{"id":"2111.03664","title":"Oracle Teacher: Leveraging Target Information for Better Knowledge Distillation of CTC Models","created":"2021-11-05","cited_by_count":0,"area":"distill"},{"id":"2201.06507","title":"Distillation from heterogeneous unlabeled collections","created":"2022-01-17","cited_by_count":0,"area":null},{"id":"2211.03000","title":"Distilling Representations from GAN Generator via Squeeze and Span","created":"2022-11-06","cited_by_count":0,"area":null},{"id":"2301.12006","title":"Improved knowledge distillation by utilizing backward pass knowledge in neural networks","created":"2023-01-27","cited_by_count":0,"area":"distill"},{"id":"2310.00946","title":"Distilling Influences to Mitigate Prediction Churn in Graph Neural Networks","created":"2023-10-02","cited_by_count":0,"area":"distill"},{"id":"2312.03510","title":"Towards Sobolev Pruning","created":"2023-12-06","cited_by_count":0,"area":null},{"id":"2404.03263","title":"On the Surprising Efficacy of Distillation as an Alternative to Pre-Training Small Models","created":"2024-04-04","cited_by_count":0,"area":"distill"},{"id":"2404.15024","title":"A Learning Paradigm for Interpretable Gradients","created":"2024-04-23","cited_by_count":0,"area":null},{"id":"2406.08528","title":"Adaptive Teaching with Shared Classifier for Knowledge Distillation","created":"2024-06-12","cited_by_count":0,"area":"distill"},{"id":"2410.06567","title":"Convex Distillation: Efficient Compression of Deep Networks via Convex Optimization","created":"2024-10-09","cited_by_count":0,"area":null},{"id":"2411.18898","title":"Textured As-Is BIM via GIS-informed Point Cloud Segmentation","created":"2024-11-28","cited_by_count":0,"area":null},{"id":"2505.01391","title":"Learning and Transferring Physical Models through Derivatives","created":"2025-05-02","cited_by_count":0,"area":null},{"id":"2505.10822","title":"Distilled Circuits: A Mechanistic Study of Internal Restructuring in Knowledge Distillation","created":"2025-05-16","cited_by_count":0,"area":"distill"},{"id":"2506.05398","title":"2ndMatch: Finetuning Pruned Diffusion Models via Second-Order Jacobian Matching","created":"2025-06-03","cited_by_count":0,"area":"diffusion"},{"id":"2510.22208","title":"Simplifying Knowledge Transfer in Pretrained Models","created":"2025-10-25","cited_by_count":0,"area":null},{"id":"2601.11638","title":"Verifying Physics-Informed Neural Network Fidelity using Classical Fisher Information from Differentiable Dynamical System","created":"2026-01-14","cited_by_count":0,"area":null},{"id":"2606.01596","title":"Second-order consistency for learning chaotic dynamics via randomized Jacobian matching","created":"2026-06-01","cited_by_count":0,"area":null},{"id":"2608.11937","title":"Distillation of Foundation Models for Time-dependent PDEs","created":"2026-08-12","cited_by_count":0,"area":null},{"id":"2610.02906","title":"Tangent Schr\\\"odinger Bridge Matching: Learning Stochastic Transport with Mechanistic Sensitivities","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.13045","title":"Redirecting Teacher Supervision: Temporal-Response-Guided Latent Distillation for Video-Language Models","created":"2026-10-09","cited_by_count":0,"area":"distill"},{"id":"2610.19007","title":"Action Jets: Learning the Local Shape of the Action-conditioned Data Manifold","created":"2026-10-13","cited_by_count":0,"area":"wm"}],"next_cursor":null}