{"total":67,"rows":[{"id":"2503.09567","title":"Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models","created":"2025-03-12","cited_by_count":384,"area":"lr"},{"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":"2604.00626","title":"A Survey of On-Policy Distillation for Large Language Models","created":"2026-04-01","cited_by_count":163,"area":"distill"},{"id":"2601.08584","title":"Ministral 3","created":"2026-01-13","cited_by_count":114,"area":null},{"id":"2507.09404","title":"Scaling Laws for Optimal Data Mixtures","created":"2025-07-12","cited_by_count":52,"area":null},{"id":"2503.19551","title":"Scaling Laws of Synthetic Data for Language Models","created":"2025-03-25","cited_by_count":46,"area":"synth"},{"id":"2503.20083","title":"Universal Cross-Tokenizer Distillation via Approximate Likelihood Matching","created":"2025-03-25","cited_by_count":41,"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":"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":"2512.05620","title":"Hyperparameter Transfer Enables Consistent Gains of Matrix-Preconditioned Optimizers Across Scales","created":"2025-12-05","cited_by_count":21,"area":null},{"id":"2507.12466","title":"Language Models Improve When Pretraining Data Matches Target Tasks","created":"2025-07-16","cited_by_count":19,"area":null},{"id":"2606.30626","title":"DOPD: Dual On-policy Distillation","created":"2026-06-29","cited_by_count":12,"area":"distill"},{"id":"2506.08415","title":"Improved Scaling Laws in Linear Regression via Data Reuse","created":"2025-06-10","cited_by_count":11,"area":null},{"id":"2605.12652","title":"Multi-Rollout On-Policy Distillation via Peer Successes and Failures","created":"2026-05-12","cited_by_count":10,"area":"distill"},{"id":"2509.25087","title":"Scaling with Collapse: Efficient and Predictable Training of LLM Families","created":"2025-09-29","cited_by_count":9,"area":null},{"id":"2509.23574","title":"Towards Efficient CoT Distillation: Self-Guided Rationale Selector for Better Performance with Fewer Rationales","created":"2025-09-28","cited_by_count":8,"area":"lr"},{"id":"2504.09802","title":"Enhancing Reasoning Abilities of Small LLMs with Cognitive Alignment","created":"2025-04-14","cited_by_count":7,"area":"lr"},{"id":"2505.24181","title":"SCOUT: Teaching Pre-trained Language Models to Enhance Reasoning via Flow Chain-of-Thought","created":"2025-05-30","cited_by_count":7,"area":"lr"},{"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":"2509.15248","title":"Synthetic bootstrapped pretraining","created":"2025-09-17","cited_by_count":6,"area":"synth"},{"id":"2602.21472","title":"The Design Space of Tri-Modal Masked Diffusion Models","created":"2026-02-25","cited_by_count":6,"area":"diffusion"},{"id":"2507.00004","title":"A Theory of Inference Compute Scaling: Reasoning through Directed Stochastic Skill Search","created":"2025-06-10","cited_by_count":5,"area":"lr"},{"id":"2510.12077","title":"Compressibility Measures Complexity: Minimum Description Length Meets Singular Learning Theory","created":"2025-10-14","cited_by_count":5,"area":null},{"id":"2511.02833","title":"In Good GRACEs: Principled Teacher Selection for Knowledge Distillation","created":"2025-11-04","cited_by_count":5,"area":"distill"},{"id":"2502.11284","title":"Balancing the Budget: Understanding Trade-offs Between Supervised and Preference-Based Finetuning","created":"2025-02-16","cited_by_count":4,"area":"alignment"},{"id":"2505.12512","title":"Scalable Strategies for Continual Learning with Replay","created":"2025-05-18","cited_by_count":4,"area":null},{"id":"2508.02929","title":"Realizing Scaling Laws in Recommender Systems: A Foundation-Expert Paradigm for Hyperscale Model Deployment","created":"2025-08-04","cited_by_count":4,"area":"distill"},{"id":"2603.23911","title":"Self-Distillation for Multi-Token Prediction","created":"2026-03-25","cited_by_count":4,"area":"distill"},{"id":"2504.13219","title":"Scaling Laws for Data-Efficient Visual Transfer Learning","created":"2025-04-17","cited_by_count":3,"area":null},{"id":"2505.22027","title":"Improving Respiratory Sound Classification with Architecture-Agnostic Knowledge Distillation from Ensembles","created":"2025-05-28","cited_by_count":3,"area":"distill"},{"id":"2510.02228","title":"xLSTM Scaling Laws: Competitive Performance with Linear Time-Complexity","created":"2025-10-02","cited_by_count":3,"area":null},{"id":"2510.20860","title":"Data-Centric Lessons To Improve Speech-Language Pretraining","created":"2025-10-22","cited_by_count":3,"area":null},{"id":"2605.23857","title":"Strong Teacher Not Needed? On Distillation in LLM Pretraining","created":"2026-05-22","cited_by_count":3,"area":"distill"},{"id":"2608.07222","title":"Skaling: Chinchilla's Exponents Meet Kaplan's Coupling","created":"2026-08-07","cited_by_count":3,"area":null},{"id":"2608.27395","title":"LeVJEPA: Efficient & Scalable Video Pretraining without the Heuristics","created":"2026-08-27","cited_by_count":3,"area":null},{"id":"2504.04342","title":"Pruning Laws for Large Language Models","created":"2025-04-06","cited_by_count":2,"area":"moe"},{"id":"2505.20836","title":"HAD: Hybrid Architecture Distillation Outperforms Teacher in Genomic Sequence Modeling","created":"2025-05-27","cited_by_count":2,"area":"distill"},{"id":"2509.23963","title":"Evaluating the Robustness of Chinchilla Compute-Optimal Scaling","created":"2025-09-28","cited_by_count":2,"area":null},{"id":"2510.08095","title":"Beyond Real Data: Synthetic Data through the Lens of Regularization","created":"2025-10-09","cited_by_count":2,"area":null},{"id":"2601.22563","title":"EUGens: Efficient, Unified, and General Dense Layers","created":"2026-01-30","cited_by_count":2,"area":null},{"id":"2602.00217","title":"Dispersion Loss Counteracts Embedding Condensation and Improves Generalization in Small Language Models","created":"2026-01-30","cited_by_count":2,"area":null},{"id":"2604.24416","title":"Scaling Properties of Continuous Diffusion Spoken Language Models","created":"2026-04-27","cited_by_count":1,"area":null},{"id":"2606.02113","title":"A Primer in Post-Training Reasoning Data: What We Know About How It Works","created":"2026-06-01","cited_by_count":1,"area":"lr"},{"id":"2607.11505","title":"Proxy OPD: On-Policy Distillation with Transferable Relative Proxy Update","created":"2026-07-13","cited_by_count":1,"area":"distill"},{"id":"2508.06617","title":"Generalizing Scaling Laws for Dense and Sparse Large Language Models","created":"2025-08-08","cited_by_count":0,"area":"moe"},{"id":"2511.17886","title":"When Better Teachers Don't Make Better Students: Revisiting Knowledge Distillation for CLIP Models in VQA","created":"2025-11-22","cited_by_count":0,"area":"mllm"},{"id":"2511.18829","title":"Towards Characterizing Knowledge Distillation of PPG Heart Rate Estimation Models","created":"2025-11-24","cited_by_count":0,"area":"distill"},{"id":"2602.22508","title":"Metacognitive Behavioral Tuning of Large Language Models for Multi-Hop Question Answering","created":"2026-02-26","cited_by_count":0,"area":"lr"},{"id":"2605.10641","title":"LLaVA-CKD: Bottom-Up Cascaded Knowledge Distillation for Vision-Language Models","created":"2026-05-11","cited_by_count":0,"area":"mllm"},{"id":"2605.10777","title":"Locking Pretrained Weights via Deep Low-Rank Residual Distillation","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2605.11513","title":"A Study on Hidden Layer Distillation for Large Language Model Pre-Training","created":"2026-05-12","cited_by_count":0,"area":"distill"},{"id":"2605.26246","title":"The Bridge-Garden Dilemma in LLM Distillation: Why Mixing Hard and Soft Labels Works","created":"2026-05-25","cited_by_count":0,"area":"distill"},{"id":"2606.24747","title":"Scaling Laws for Task-Specific LLM Distillation","created":"2026-06-23","cited_by_count":0,"area":null},{"id":"2607.01727","title":"When Does Generating More Help? Disentangling Fixed-Source Synthesis from Source Expansion in Synthetic Data Scaling","created":"2026-07-02","cited_by_count":0,"area":null},{"id":"2607.05461","title":"AdaStop: Cost-Aware Early Stopping for DNN Test Selection","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2607.08268","title":"Different Teachers, Different Capabilities: Sub-1B On-Device Distillation for Structured Text Enrichment","created":"2026-07-09","cited_by_count":0,"area":null},{"id":"2609.32722","title":"Scaling Properties of Same-Family On-Policy Distillation","created":"2026-09-26","cited_by_count":0,"area":"lr"},{"id":"2609.33835","title":"An Active-Bottleneck Mechanism for Weak-to-Strong Generalization","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.34386","title":"Look Before You Select: Rethinking Vocabulary Sparsification in On-Policy Distillation","created":"2026-09-28","cited_by_count":0,"area":"distill"},{"id":"2609.35699","title":"Distillation Defenses Easily Break After Reinforcement Learning","created":"2026-09-28","cited_by_count":0,"area":"lr"},{"id":"2609.38149","title":"Pretraining Latent Information Feedback Transformers with Teacher Supervision","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.02462","title":"Capability Scaling-Down Laws for LLM Compression","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.02597","title":"GRAFT: Growing Agglomerative Foundation Models via Continual Teacher Distillation","created":"2026-10-01","cited_by_count":0,"area":"distill"},{"id":"2610.13568","title":"Rationally Linearized MLPs","created":"2026-10-09","cited_by_count":0,"area":null},{"id":"2610.15589","title":"The Gradient That Top-k Distillation Never Computes","created":"2026-10-11","cited_by_count":0,"area":"distill"},{"id":"2610.17637","title":"Mixed Precision Scaling Laws for Quantized Pretraining","created":"2026-10-13","cited_by_count":0,"area":null},{"id":"2610.17644","title":"DisaggKD: Efficient Knowledge Distillation through Teacher-Student Disaggregation and a Fused Loss","created":"2026-10-13","cited_by_count":0,"area":"distill"}],"next_cursor":null}