Post-Training Leaves Behavioral Shadows on Unrelated Decisions
Paper • 2609.29233 • Published • 272
Xuan He PRO
hexuan21
AI & ML interests
None yet
Recent Activity
upvoted a paper about 2 hours ago
Post-Training Leaves Behavioral Shadows on Unrelated Decisions upvoted a paper 2 days ago
PixelUMM: Encoder-Free Unified Image and Video Understanding and Generation liked a model 2 days ago
nvidia/PixelUMMOrganizations
upvoted a paper about 2 hours ago
upvoted a paper 2 days ago
upvoted 4
papers 7 days ago
Diffusion Reward Models
Paper • 2609.33803 • Published • 35
How Far Are We from Removing the Visual Encoder? Scaling Laws for Encoder-Free Multimodal Pretraining
Paper • 2609.35457 • Published • 66
TraceDance: An Automated System for Building Agent Behavior Benchmarks from Real-World Agent Deployment Traces
Paper • 2609.33295 • Published • 72
Self-Evolving Coding Agents: From Digital Programs to Physical-World Intelligence
Paper • 2609.35432 • Published • 107
upvoted 5
papers 19 days ago
Self-Distilled RLVR
Paper • 2604.03128 • Published • 146
FIPO: Eliciting Deep Reasoning with Future-KL Influenced Policy Optimization
Paper • 2603.19835 • Published • 121
SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-unify Architecture
Paper • 2605.12500 • Published • 199
MolmoAct2: Action Reasoning Models for Real-world Deployment
Paper • 2605.02881 • Published • 358
AI for Games in the Foundation Model Era
Paper • 2609.16679 • Published • 146
upvoted 4
papers 20 days ago
RSIAgent: Autonomous Exploration for Recursive Self-improvement in New Environments
Paper • 2609.15364 • Published • 84
Dream-RSI: Recursive Self-Improvement through Evolving Worlds
Paper • 2609.14858 • Published • 251
Vidu S2: Real-Time Interactive, Editable, and Spatial Video Generation
Paper • 2609.11638 • Published • 707
Atria Dawn: The Dawn of Agentic Superintelligence
Paper • 2609.15818 • Published • 434
upvoted 2
papers 25 days ago
upvoted 3
papers about 1 month ago