ImpossibleRubrics: Stress-Testing Generated Rubrics as Reward Signals
Paper • 2609.16816 • Published • 11
Jiho Kang
jihokang02
AI & ML interests
Reinforcement learning, reward modeling, RLHF, policy optimization, offline RL
Recent Activity
liked a model 2 days ago
jarguello76/reinforcement_learning_lunar_landing upvoted a paper 2 days ago
ImpossibleRubrics: Stress-Testing Generated Rubrics as Reward Signals upvoted a paper 2 days ago
PARSER: Read in Parallel, Reason in Depth for Long-Context LLM AgentsOrganizations
None yet
upvoted 9
papers 2 days ago
PARSER: Read in Parallel, Reason in Depth for Long-Context LLM Agents
Paper • 2609.06702 • Published • 26
T1: Terminal Agent Reinforcement Learning for Long-Horizon Tasks
Paper • 2609.11042 • Published • 63
Scaling Automatic Research Agents via World Models
Paper • 2608.12564 • Published • 471
AI for Games in the Foundation Model Era
Paper • 2609.16679 • Published • 146
Drift-Constrained Optimization: Only Direction Matters in Fine-Tuning Instruct Models
Paper • 2609.13680 • Published • 12
ScienceBuddy: Recursive-in-Recursive Self-Improvement for Interactive Scientific Agents
Paper • 2609.17523 • Published • 30
StepAudio 3 Music Technical Report
Paper • 2609.16034 • Published • 108
Continual Learning Mechanisms Compose for Long-Horizon Memorization
Paper • 2609.06986 • Published • 367
upvoted 4
papers 4 days ago
Expert-Space Exploration in MoE Reinforcement Learning
Paper • 2609.13058 • Published • 7
MInTRL: Off-policy Intervention can boost On-policy RL
Paper • 2609.12419 • Published • 14
Not All Prompts Are Equal: Exploration-Guided Prompt Scaffolding for Multimodal Reinforcement Post-Training
Paper • 2609.15051 • Published • 14
Grouped Value Attention: Efficient KV Caching via On-Demand Key Reconstruction
Paper • 2609.13285 • Published • 77
upvoted 7
papers 5 days ago
MobileVLA-R1 2.0: RL-Enhanced Reasoning for Mobile Robot Control
Paper • 2609.06251 • Published • 8
DataFlex-RL: An Evaluation Platform for RLVR Data Policies
Paper • 2609.06107 • Published • 163
Occamy-1.0: Open Pareto-frontier 35B Intelligence for Co-work
Paper • 2609.11977 • Published • 114
DRG-MAPPO: Hierarchical Dynamic Role-Graph Multi-Agent Reinforcement Learning for Cooperative Air Combat
Paper • 2609.11155 • Published • 28
CARDEA: Auditable Reasoning Grounded in Spatial Evidence for End-to-End Coronary Angiography Interpretation
Paper • 2609.06931 • Published • 27
Negative Self-Distillation: Learning to Reason by Avoiding Flaws
Paper • 2609.11699 • Published • 36
An Open Recipe for IMO Gold: Training Nemotron for Olympiad Mathematics
Paper • 2609.10712 • Published • 44