Terminal-Universe: Turning Agent Trajectories into Scalable Terminal Environments
Paper • 2609.04148 • Published • 286
Ian Cole
codingiancole
AI & ML interests
Reinforcement learning, reward modeling, RLHF, policy optimization, offline RL
Recent Activity
liked a dataset 20 minutes ago
winglian/no_robots_rlhf liked a dataset 20 minutes ago
jojo0217/korean_rlhf_dataset liked a dataset 20 minutes ago
RLHFlow/UltraFeedback-preference-standardOrganizations
None yet
upvoted a paper about 9 hours ago
upvoted 3
papers 2 days ago
Does On-Policy Distillation Really Distill? From Noisy Teacher to Self-Improvement
Paper • 2608.31046 • Published • 143
LightNav-0: Eliciting VLM Spatial Intelligence for Generalist Embodied Navigation
Paper • 2608.30935 • Published • 32
SMELT: Scaling Laws for Compute-Matched MoE Looped Transformers
Paper • 2609.01343 • Published • 99
upvoted 3
papers 4 days ago
InternReviewer & InternAdvocate: Objective Reward and Evaluation for Agentic Reinforcement Learning in Peer Review and Rebuttal
Paper • 2608.28612 • Published • 8
Learning Where Outcomes Change:Credit-Addressable Reasoning for Multimodal Geometry
Paper • 2608.30457 • Published • 9
Qwen-Drive-1.0: An Initial Step towards a Vision-Language Foundation Model for Autonomous Driving
Paper • 2609.00111 • Published • 376
upvoted a paper 6 days ago
upvoted 3
papers 7 days ago
Prefix Sliding for efficient test-time scaling
Paper • 2608.26070 • Published • 5
Open-MOPD: Diagnosing and Fixing Capability Imbalance in Multi-Teacher On-Policy Distillation
Paper • 2608.19098 • Published • 23
FrontierChallenge: Evaluating Scientific Workflow Completion
Paper • 2608.24979 • Published • 148
upvoted 4
papers 8 days ago
Agent-G^2: Gaussian Guidance for Agentic Reinforcement Learning
Paper • 2608.23318 • Published • 32
FIRM-Video: Check Before You Score for Reliable Text-to-Video Reward Modeling
Paper • 2608.21839 • Published • 4
WarpSAC: Towards the Pinnacle of Scalable Off-policy RL by Rethinking Exploration and Exploitation
Paper • 2608.24479 • Published • 142
VBVR-Pro: A Scalable and Verifiable Suite for Native Visual Reasoning
Paper • 2608.26105 • Published • 269