{"total":60,"rows":[{"id":"2606.02800","title":"Cosmos 3: Omnimodal World Models for Physical AI","created":"2026-06-01","cited_by_count":165,"area":"wm"},{"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":"2605.03677","title":"Uni-OPD: Unifying On-Policy Distillation with a Dual-Perspective Recipe","created":"2026-05-05","cited_by_count":49,"area":"distill"},{"id":"2606.15007","title":"Nemotron 3 Ultra: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning","created":"2026-06-12","cited_by_count":42,"area":"lr"},{"id":"2605.07865","title":"KL for a KL: On-Policy Distillation with Control Variate Baseline","created":"2026-05-08","cited_by_count":26,"area":"lr"},{"id":"2605.16826","title":"Decoupling KL and Trajectories: A Unified Perspective for SFT, DAgger, Offline RL, and OPD in LLM Distillation","created":"2026-05-16","cited_by_count":20,"area":"offlinerl"},{"id":"2605.27115","title":"Counteraction-Aware Multi-Teacher On-Policy Distillation for General Capability Recovery with Domain Preservation","created":"2026-05-26","cited_by_count":15,"area":"distill"},{"id":"2606.13657","title":"Dense Supervision, Sparse Updates: On the Sparsity and Geometry of On-Policy Distillation","created":"2026-06-11","cited_by_count":10,"area":"distill"},{"id":"2606.17199","title":"PowerOPD: Stabilizing On-Policy Distillation with Bounded Power Transformation","created":"2026-06-15","cited_by_count":9,"area":"distill"},{"id":"2608.18271","title":"Rethinking Privileged Information in On-Policy Self-Distillation","created":"2026-08-18","cited_by_count":9,"area":"distill"},{"id":"2606.06260","title":"OneReason Technical Report","created":"2026-06-04","cited_by_count":8,"area":"lr"},{"id":"2607.04425","title":"UI-MOPD: Multi-Platform On-Policy Distillation for Unified GUI Agents","created":"2026-07-05","cited_by_count":8,"area":"agents"},{"id":"2604.07941","title":"Large Language Model Post-Training: A Unified View of Off-Policy and On-Policy Learning","created":"2026-04-09","cited_by_count":6,"area":null},{"id":"2606.01774","title":"FLARE: Diffusion for Hybrid Language Model","created":"2026-06-01","cited_by_count":6,"area":null},{"id":"2606.14502","title":"From Chatbot to Digital Colleague: The Paradigm Shift Toward Persistent Autonomous AI","created":"2026-06-12","cited_by_count":6,"area":null},{"id":"2605.07579","title":"Your Language Model is Its Own Critic: Reinforcement Learning with Value Estimation from Actor's Internal States","created":"2026-05-08","cited_by_count":5,"area":"lr"},{"id":"2607.28449","title":"Lightning OPD 2.0: Mitigating Style Bias in Cross-Teacher On-Policy Distillation for Large Reasoning Models","created":"2026-07-30","cited_by_count":5,"area":"lr"},{"id":"2608.11829","title":"Towards Understanding On-Policy Distillation through the Lens of Test-Time Scaling","created":"2026-08-12","cited_by_count":5,"area":"lr"},{"id":"2609.02998","title":"Verify Before You Distill: Prompt-Level Teacher Gating for On-Policy Distillation","created":"2026-09-02","cited_by_count":5,"area":"distill"},{"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":"2608.16647","title":"Every Coin Has Two Sides: On the Dual Nature of Generalization in On-Policy Distillation of Large Language Models","created":"2026-08-17","cited_by_count":4,"area":"distill"},{"id":"2608.26218","title":"Same Model, Different Harness: Different Coding-Agent Results","created":"2026-08-26","cited_by_count":4,"area":"agents"},{"id":"2609.02548","title":"Learn from Whoever Is Right: Answer-Verified Multi-Teacher Distillation for Multi-Domain LLMs","created":"2026-09-02","cited_by_count":4,"area":"distill"},{"id":"2604.25578","title":"Marco-MoE: Open Multilingual Mixture-of-Expert Language Models with Efficient Upcycling","created":"2026-04-28","cited_by_count":3,"area":"moe"},{"id":"2607.04751","title":"Trust Region Policy Distillation","created":"2026-07-06","cited_by_count":3,"area":"distill"},{"id":"2607.24720","title":"The Physics of Multi-Turn Long-Horizon Planning: From Pre-training to Post-training via Single- and Multi-Teacher On-Policy Agentic Distillation","created":"2026-07-27","cited_by_count":3,"area":"wm"},{"id":"2609.16937","title":"Beyond Token-Local Imitation: Reward-Compatible Temporal Credit Assignment for On-Policy Distillation","created":"2026-09-15","cited_by_count":3,"area":"distill"},{"id":"2606.00437","title":"EST-PRM: Stress-Testing Process Reward Models Before They Become Load-Bearing","created":"2026-05-30","cited_by_count":2,"area":"lr"},{"id":"2608.24987","title":"D$^3$-MOPD: Dynamic Domain ScheDuling for Efficient Multi-Teacher Distillation","created":"2026-08-25","cited_by_count":2,"area":"distill"},{"id":"2609.08798","title":"Eliciting Weak-to-Strong Generalization with On-Policy Reverse Distillation","created":"2026-09-08","cited_by_count":2,"area":"distill"},{"id":"2605.10344","title":"TMAS: Scaling Test-Time Compute via Multi-Agent Synergy","created":"2026-05-11","cited_by_count":1,"area":"lr"},{"id":"2608.03610","title":"Language-Specialized Multi-Teacher On-Policy Distillation for Multilingual LLM-Based ASR","created":"2026-08-04","cited_by_count":1,"area":"distill"},{"id":"2608.11152","title":"Scheduling Mixed RL Rollouts Beyond Prefix Locality","created":"2026-08-11","cited_by_count":1,"area":null},{"id":"2609.00092","title":"Safin-1: Safety from Within through Memory-Native State Evolution","created":"2026-08-31","cited_by_count":1,"area":null},{"id":"2609.14193","title":"Data-Free On-Policy Distillation: How Far Can We Go Without External Data?","created":"2026-09-12","cited_by_count":1,"area":"distill"},{"id":"2609.19553","title":"From Parameters to Behaviors: A Survey of Model Fusion for Large Language Models","created":"2026-09-17","cited_by_count":1,"area":null},{"id":"2610.01352","title":"MMVistaReason: Toward Open-Data and Post-Training Recipes for Multimodal Reasoning","created":"2026-10-01","cited_by_count":1,"area":"lr"},{"id":"2605.07276","title":"Signal Reshaping for GRPO in Weak-Feedback Agentic Code Repair","created":"2026-05-08","cited_by_count":0,"area":"lr"},{"id":"2606.00609","title":"CARE-RL: Capability-Aware Reinforcement Learning for Mitigating Cross-Domain Conflicts","created":"2026-05-30","cited_by_count":0,"area":"lr"},{"id":"2606.10479","title":"ComBench: A Benchmark for Rigorous Proof Reasoning and Constructive Realization in Olympiad-Level Combinatorics","created":"2026-06-09","cited_by_count":0,"area":"lr"},{"id":"2606.31693","title":"ShopX: A Foundation Model for Intent-to-Item Fulfillment in Agentic Shopping","created":"2026-06-30","cited_by_count":0,"area":"agents"},{"id":"2607.05198","title":"Noisy-Channel Minimum Bayes Risk Decoding","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2608.20953","title":"Quantization-Aware Healing: A Practical Recipe for Recovering Compressed, 4-Bit LLMs","created":"2026-08-21","cited_by_count":0,"area":null},{"id":"2608.26735","title":"Recovering General Capabilities via Uncertainty-Calibrated Multi-Teacher On-Policy Distillation","created":"2026-08-27","cited_by_count":0,"area":"distill"},{"id":"2609.00791","title":"Instella-MoE Technical Report","created":"2026-09-01","cited_by_count":0,"area":"moe"},{"id":"2609.10293","title":"GANDR: Claim Auditing for Verifiable Legal Answer Generation","created":"2026-09-09","cited_by_count":0,"area":null},{"id":"2609.14708","title":"Lightning Weave: Improving the Accuracy-Efficiency Frontier of Reasoning Models through Capability Composition","created":"2026-09-13","cited_by_count":0,"area":"lr"},{"id":"2609.23989","title":"ACLArena: Agent Continue Learning in Multi-stage Post-training","created":"2026-09-21","cited_by_count":0,"area":null},{"id":"2609.30837","title":"MOPD-Router: Rethinking Teacher Routing in Multi-Teacher On-Policy Distillation","created":"2026-09-25","cited_by_count":0,"area":"distill"},{"id":"2609.31900","title":"Understanding the Synergy between SFT, RLVR, and OPD in LLM Post-Training","created":"2026-09-25","cited_by_count":0,"area":"distill"},{"id":"2609.33780","title":"Selecting Diverse SFT Traces Improves Post-RL Generalization","created":"2026-09-27","cited_by_count":0,"area":"lr"},{"id":"2609.34745","title":"No Pain, More Gain: Iterative Merging for Effective Multi-Teacher On-Policy Distillation","created":"2026-09-28","cited_by_count":0,"area":"distill"},{"id":"2609.35937","title":"PrivacySkills: How Privacy Guidance Shapes Source Selection in LLM Agents","created":"2026-09-28","cited_by_count":0,"area":"agents"},{"id":"2609.35954","title":"ROSS: Relearning from Self-Generated Rollouts through Selective Supervision","created":"2026-09-28","cited_by_count":0,"area":"synth"},{"id":"2610.00979","title":"RISED: RubrIcs for agentic multi-environment Selection and sElf-Distillation","created":"2026-10-01","cited_by_count":0,"area":"agents"},{"id":"2610.02359","title":"Lexicographic Multi-Objective On-Policy Distillation","created":"2026-10-01","cited_by_count":0,"area":"distill"},{"id":"2610.03529","title":"Divergence controls entropy in distillation","created":"2026-10-02","cited_by_count":0,"area":"distill"},{"id":"2610.11291","title":"When Do We Need On-Policy Distillation? Distilling on Offline Student Rollouts Is Often Better","created":"2026-10-08","cited_by_count":0,"area":"distill"},{"id":"2610.13521","title":"Beyond Domain-Routed Supervision: Cross-Teacher Guarding for Multi-Teacher On-Policy Distillation","created":"2026-10-09","cited_by_count":0,"area":"distill"},{"id":"2610.15894","title":"Make Every Expansion Count: Learning to Search Efficiently in LLM Code Repair","created":"2026-10-11","cited_by_count":0,"area":null}],"next_cursor":null}