Towards Full Pipeline FP8 Reinforcement Learning for LLMs
Paper • 2609.22870 • Published • 15
Karthik Iyer
kiyer97
AI & ML interests
Reinforcement learning, reward modeling, RLHF, policy optimization, offline RL
Recent Activity
liked a dataset about 15 hours ago
youinwww/reinforcement_learning upvoted a paper about 15 hours ago
Towards Full Pipeline FP8 Reinforcement Learning for LLMs upvoted a paper about 15 hours ago
ShieldVLA: Feasibility-Aware Safety Alignment for Vision-Language-Action ModelsOrganizations
None yet
upvoted 4
papers about 15 hours ago
ShieldVLA: Feasibility-Aware Safety Alignment for Vision-Language-Action Models
Paper • 2609.13231 • Published • 13
VideoGen-Agent: Reinforcing Video Generation Agents
Paper • 2609.24997 • Published • 66
One to More, More to One: Category-Aware Iterative Expert Training for Software Engineering Agents
Paper • 2609.23377 • Published • 48
upvoted 6
papers 1 day ago
CodeMidas: Scaling Agentic Coding RL Environments from Code Itself
Paper • 2609.22068 • Published • 131
Grounded Skill Synthesis from Code at Scale for Agentic Intelligence
Paper • 2609.05571 • Published • 114
StudentSim: Training LLM-based Student Simulators
Paper • 2609.01591 • Published • 372
MintAct: A Unified Visual Agent for Digital Environments
Paper • 2609.22083 • Published • 32
BI-Agent and BI-Bench: Towards Automating End-to-End Business Intelligence
Paper • 2609.20886 • Published • 28
From Pretraining to Proficiency: Real-World Subtask RL for Long-Horizon Manipulation with Minimal Human Intervention
Paper • 2609.21788 • Published • 13
upvoted 4
papers 3 days ago
Region-Level Policy Optimization for Fine-grained MLLM Perception
Paper • 2609.19745 • Published • 41
Don't Mask the Environment: Observation Supervision Changes How Agents Explore Under RL
Paper • 2609.20715 • Published • 42
RetireOPD: Self-Retiring On-Policy Distillation for Agentic Reinforcement Learning
Paper • 2609.20784 • Published • 56
Verifiable Social Reasoning for LLM Assistants
Paper • 2609.17496 • Published • 65
upvoted 3
papers 4 days ago
Rethinking Critic Learning in PPO: Understanding and Mitigating Value Flattening
Paper • 2609.18708 • Published • 79
ScienceIDE: Turning World's Scientific Codebase into Agent Learnable Environments
Paper • 2609.19134 • Published • 100
ActionPiece: Rethinking Action Tokenization for Autoregressive Vision-Language-Action Models
Paper • 2609.18487 • Published • 47
upvoted 3
papers 6 days ago
SenseNova-U1.5: Towards Native Unified Visual Intelligence
Paper • 2609.11929 • Published • 274
ModularRSI: Modular and Generalizable Recursive Harness Self-Improvement
Paper • 2609.14857 • Published • 214
Drift-Constrained Optimization: Only Direction Matters in Fine-Tuning Instruct Models
Paper • 2609.13680 • Published • 13