Karthik Iyer

kiyer97

·

AI & ML interests

Reinforcement learning, reward modeling, RLHF, policy optimization, offline RL

Recent Activity

liked a dataset about 20 hours ago

kunishou/hh-rlhf-49k-ja

liked a dataset about 20 hours ago

ProlificAI/social-reasoning-rlhf

liked a model about 20 hours ago

Chaew00n/test-policy-optimization-query-rewrite-8B

View all activity

Organizations

None yet

upvoted a paper about 20 hours ago

EmbodiedMemory-Bench: Benchmarking Embodied Memory for Long-Horizon Embodied Tasks

Paper • 2609.28236 • Published 9 days ago • 37

upvoted a paper 1 day ago

FuseReg: Regularizing Layer Fusion Mitigates the Reconstruction-Generation Gap in Representation Autoencoders

Paper • 2609.31620 • Published 7 days ago • 158

upvoted a paper 7 days ago

Flash-dLLM: IO-Aware KV Caching and Parallel Decoding for Fast, Memory-Efficient Diffusion LLMs

Paper • 2609.26796 • Published 10 days ago • 36

upvoted 10 papers 8 days ago

Towards Full Pipeline FP8 Reinforcement Learning for LLMs

Paper • 2609.22870 • Published 13 days ago • 17

ShieldVLA: Feasibility-Aware Safety Alignment for Vision-Language-Action Models

Paper • 2609.13231 • Published about 1 month ago • 18

VideoGen-Agent: Reinforcing Video Generation Agents

Paper • 2609.24997 • Published 11 days ago • 73

One to More, More to One: Category-Aware Iterative Expert Training for Software Engineering Agents

Paper • 2609.23377 • Published 12 days ago • 50

CodeMidas: Scaling Agentic Coding RL Environments from Code Itself

Paper • 2609.22068 • Published 14 days ago • 138

Grounded Skill Synthesis from Code at Scale for Agentic Intelligence

Paper • 2609.05571 • Published 28 days ago • 119

StudentSim: Training LLM-based Student Simulators

Paper • 2609.01591 • Published Sep 1 • 494

MintAct: A Unified Visual Agent for Digital Environments

Paper • 2609.22083 • Published 14 days ago • 35

BI-Agent and BI-Bench: Towards Automating End-to-End Business Intelligence

Paper • 2609.20886 • Published 16 days ago • 30

From Pretraining to Proficiency: Real-World Subtask RL for Long-Horizon Manipulation with Minimal Human Intervention

Paper • 2609.21788 • Published 14 days ago • 13

upvoted 4 papers 10 days ago

Region-Level Policy Optimization for Fine-grained MLLM Perception

Paper • 2609.19745 • Published 15 days ago • 41

Don't Mask the Environment: Observation Supervision Changes How Agents Explore Under RL

Paper • 2609.20715 • Published 15 days ago • 44

RetireOPD: Self-Retiring On-Policy Distillation for Agentic Reinforcement Learning

Paper • 2609.20784 • Published 15 days ago • 57

Verifiable Social Reasoning for LLM Assistants

Paper • 2609.17496 • Published 17 days ago • 67

upvoted 3 papers 11 days ago

Rethinking Critic Learning in PPO: Understanding and Mitigating Value Flattening

Paper • 2609.18708 • Published 16 days ago • 84

ScienceIDE: Turning World's Scientific Codebase into Agent Learnable Environments

Paper • 2609.19134 • Published 16 days ago • 101

ActionPiece: Rethinking Action Tokenization for Autoregressive Vision-Language-Action Models

Paper • 2609.18487 • Published 16 days ago • 48