Weichen Lou

WChenL's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted 2 papers about 4 hours ago

Rollback: Experience Backtracking in World Models for Policy Improvement

Paper • 2610.36068 • Published 5 days ago • 89

Sensorimotor Alignment: A Platonic Proxy for Embodied Policy Success

Paper • 2610.31670 • Published 8 days ago • 38

upvoted 2 papers 3 days ago

Steering Black-Box Large Language Model Agents with Pitfall Anticipation World Model

Paper • 2610.29139 • Published 10 days ago • 16

Extreme Compression of Per-Layer Embeddings via Cross-Layer Latent Vector Quantization

Paper • 2610.31309 • Published 9 days ago • 22

upvoted 3 papers 4 days ago

Dual Exam: Controlled Evaluation of Multimodal Agents and World Models

Paper • 2610.31066 • Published 9 days ago • 37

UserArena: Benchmarking Interactive User Simulation for Long-Horizon Shopping Agents

Paper • 2610.30932 • Published 9 days ago • 64

Easy-3Dfy: Object-Level Geometric Composition for Single-Image 3D Scene Construction

Paper • 2610.32250 • Published 8 days ago • 11

upvoted 2 papers 9 days ago

State World Models: Execute the Rules, Generate the Pixels

Paper • 2610.26811 • Published 12 days ago • 17

Interlock: From Local Correctness to Task Completion in Long-Horizon Agents

Paper • 2610.19686 • Published 17 days ago • 50

upvoted 3 papers 12 days ago

SafeDriveVLA: Navigation-Conditioned World Model Dreaming for Conflict-Aware End-to-End Autonomous Driving

Paper • 2610.20609 • Published 17 days ago • 15

Towards Agentic Robots: Model, Data, Environment, and Harness

Paper • 2610.20442 • Published 17 days ago • 43

Hybrid Reasoning Agents

Paper • 2610.18861 • Published 18 days ago • 44

upvoted 2 papers 13 days ago

ExeWorldBench: Benchmarking Code-Based Executable 3D World Modeling

Paper • 2610.15166 • Published 21 days ago • 86

DoSA: Dots Sparse Attention

Paper • 2610.13990 • Published Sep 26 • 76

upvoted 2 papers 16 days ago

WOVEN: Weaving Visual World Modeling into Multimodal LLMs

Paper • 2610.12417 • Published 23 days ago • 21

GroundingPI: A Grounding Foundation Model towards Physical Intelligence with Visual Primitives

Paper • 2609.39601 • Published Sep 30 • 151

upvoted 2 papers 17 days ago

RSI-Anything: Unlocking Recursive Self-Improvement with World Models

Paper • 2610.13912 • Published 22 days ago • 53

The Life Cycle of a Massive Activation: Stochastic Birth, Weight-Decay-Driven Growth, and Competitive Consolidation

Paper • 2610.00423 • Published 26 days ago • 9

upvoted 2 papers 19 days ago

WorldSonus: Bringing Sound to Worlds

Paper • 2610.08760 • Published 25 days ago • 40

GRACE: Generation-aware latent compression for efficient video generation

Paper • 2610.10524 • Published 24 days ago • 85