xuwang

wx91726's activity

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

upvoted 2 papers about 23 hours ago

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

Paper • 2609.20784 • Published 3 days ago • 26

Reflect, Revise, Reuse: Training-Free Skill Evolution for GUI Agents

Paper • 2609.17653 • Published 5 days ago • 25

upvoted a paper 18 days ago

PaperGym: Rubric-Centered Evolution for Research-Plan Generation

Paper • 2608.31119 • Published 20 days ago • 33

upvoted a paper 22 days ago

TTPO: Test-Time Policy Optimization

Paper • 2608.27448 • Published 24 days ago • 83

upvoted a paper 23 days ago

Agent-G^2: Gaussian Guidance for Agentic Reinforcement Learning

Paper • 2608.23318 • Published 27 days ago • 32

upvoted a paper about 1 month ago

Embodied-Navigator: Point, Think, Memorize, and Align for Efficient Navigation

Paper • 2608.17512 • Published Aug 18 • 52

liked a dataset about 1 month ago

wx91726/SpatialGen-Bench

Viewer • Updated Jul 24 • 470 • 325 • 4

upvoted 2 papers about 2 months ago

Pass the Baton: Trajectory-Relayed On-Policy Distillation

Paper • 2607.26057 • Published Jul 28 • 33

Show, Don't Tell: Evaluating Spatial Cognition in Generative Pixels Rather Than LLM Text

Paper • 2607.21072 • Published Jul 23 • 35

authored a paper about 2 months ago

Show, Don't Tell: Evaluating Spatial Cognition in Generative Pixels Rather Than LLM Text

Paper • 2607.21072 • Published Jul 23 • 35

updated a dataset about 2 months ago

wx91726/SpatialGen-Bench

Viewer • Updated Jul 24 • 470 • 325 • 4

published a dataset 2 months ago

wx91726/SpatialGen-Bench

Viewer • Updated Jul 24 • 470 • 325 • 4

upvoted a paper 3 months ago

VLA-Corrector: Lightweight Detect-and-Correct Inference for Adaptive Action Horizon

Paper • 2607.01804 • Published Jul 2 • 27

upvoted a paper 5 months ago

GFT: From Imitation to Reward Fine-Tuning with Unbiased Group Advantages and Dynamic Coefficient Rectification

Paper • 2604.14258 • Published Apr 15 • 23

upvoted a paper 8 months ago

Visual Generation Unlocks Human-Like Reasoning through Multimodal World Models

Paper • 2601.19834 • Published Jan 27 • 25

upvoted a paper 9 months ago

N3D-VLM: Native 3D Grounding Enables Accurate Spatial Reasoning in Vision-Language Models

Paper • 2512.16561 • Published Dec 18, 2025 • 20