Expert-Space Exploration in MoE Reinforcement Learning
Paper • 2609.13058 • Published • 7
Jiho Kang
jihokang02
AI & ML interests
Reinforcement learning, reward modeling, RLHF, policy optimization, offline RL
Recent Activity
liked a dataset about 8 hours ago
haruki-abe/cross_embodiment_offline_rl liked a dataset about 8 hours ago
andersonbcdefg/red_teaming_reward_modeling_pairwise_no_as_an_ai liked a dataset about 8 hours ago
introvoyz041/reinforcement-learningOrganizations
None yet
upvoted 4
papers about 8 hours ago
MInTRL: Off-policy Intervention can boost On-policy RL
Paper • 2609.12419 • Published • 10
Not All Prompts Are Equal: Exploration-Guided Prompt Scaffolding for Multimodal Reinforcement Post-Training
Paper • 2609.15051 • Published • 11
Grouped Value Attention: Efficient KV Caching via On-Demand Key Reconstruction
Paper • 2609.13285 • Published • 68
upvoted 3
papers 1 day ago
upvoted 6
papers 2 days ago
DRG-MAPPO: Hierarchical Dynamic Role-Graph Multi-Agent Reinforcement Learning for Cooperative Air Combat
Paper • 2609.11155 • Published • 25
CARDEA: Auditable Reasoning Grounded in Spatial Evidence for End-to-End Coronary Angiography Interpretation
Paper • 2609.06931 • Published • 26
Negative Self-Distillation: Learning to Reason by Avoiding Flaws
Paper • 2609.11699 • Published • 37
An Open Recipe for IMO Gold: Training Nemotron for Olympiad Mathematics
Paper • 2609.10712 • Published • 43
SenseNova-U1.5: Towards Native Unified Visual Intelligence
Paper • 2609.11929 • Published • 262
Studying Image Tokenizers as Visual Languages in Unified Multimodal Models
Paper • 2609.09143 • Published • 31
upvoted 3
papers 3 days ago
Revisiting Complete Reasoning Traces for Post-Training
Paper • 2609.07103 • Published • 23
Difficulty-Adaptive Tree-Structured Policy Optimization for Expanding Reasoning Coverage in RLVR
Paper • 2609.08650 • Published • 12
WearableQA: A Benchmark for Health Reasoning over Real-World Wearable Data
Paper • 2609.05405 • Published • 42
upvoted 4
papers 4 days ago
It Takes Two to Match: Co-Evolving Generative Retriever with Reinforcement Learning
Paper • 2609.00638 • Published • 75
Cliff: Learning Process Rewards from the First Mistake
Paper • 2609.02817 • Published • 21
Environments as Scaffold: Enriching Feedback to Bootstrap Self-Evolving Agents in Long-Horizon Tasks
Paper • 2609.08404 • Published • 25
One Symptom, Three Levers: A Critical Review of On-Policy Self-Distillation
Paper • 2608.25936 • Published • 17