Xingyi Yang

adamdad's activity

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

upvoted a paper 2 days ago

BadWAM: When World-Action Models Dream Right but Act Wrong

Paper • 2607.15207 • Published 3 days ago • 44

upvoted a paper 6 days ago

From RGB Generation to Dense Field Readout: Pixel-Space Dense Prediction with Text-to-Image Models

Paper • 2607.06553 • Published 10 days ago • 20

upvoted a paper 12 days ago

PixWorld: Unifying 3D Scene Generation and Reconstruction in Pixel Space

Paper • 2607.05373 • Published 13 days ago • 65

upvoted a paper 26 days ago

World Action Models: A Survey

Paper • 2606.20781 • Published about 1 month ago • 56

upvoted 2 papers about 1 month ago

SAE Interventions are Unreliable: Post-Intervention Recovery of Suppressed Behavior

Paper • 2606.18322 • Published Jun 16 • 17

BadWorld: Adversarial Attacks on World Models

Paper • 2606.16519 • Published Jun 15 • 18

upvoted 3 papers about 2 months ago

dMoE: dLLMs with Learnable Block Experts

Paper • 2605.30876 • Published May 29 • 38

Q-ARVD: Quantizing Autoregressive Video Diffusion Models

Paper • 2605.21072 • Published May 20 • 21

Mix-Quant: Quantized Prefilling, Precise Decoding for Agentic LLMs

Paper • 2605.20315 • Published May 19 • 28

upvoted 2 papers 2 months ago

ReactiveGWM: Steering NPC in Reactive Game World Models

Paper • 2605.15256 • Published May 14 • 28

On-Policy Self-Evolution via Failure Trajectories for Agentic Safety Alignment

Paper • 2605.11882 • Published May 12 • 16

upvoted 2 papers 3 months ago

Free Geometry: Refining 3D Reconstruction from Longer Versions of Itself

Paper • 2604.14048 • Published Apr 15 • 16

DMax: Aggressive Parallel Decoding for dLLMs

Paper • 2604.08302 • Published Apr 9 • 54

upvoted 4 papers 4 months ago

Gated Condition Injection without Multimodal Attention: Towards Controllable Linear-Attention Transformers

Paper • 2603.27666 • Published Mar 29 • 18

Make Geometry Matter for Spatial Reasoning

Paper • 2603.26639 • Published Mar 27 • 33

Anatomy of a Lie: A Multi-Stage Diagnostic Framework for Tracing Hallucinations in Vision-Language Models

Paper • 2603.15557 • Published Mar 16 • 30

ViFeEdit: A Video-Free Tuner of Your Video Diffusion Transformer

Paper • 2603.15478 • Published Mar 16 • 24

upvoted a paper 5 months ago

dVoting: Fast Voting for dLLMs

Paper • 2602.12153 • Published Feb 12 • 23

upvoted a paper 6 months ago

MHLA: Restoring Expressivity of Linear Attention via Token-Level Multi-Head

Paper • 2601.07832 • Published Jan 12 • 53

upvoted a paper 7 months ago

SpotEdit: Selective Region Editing in Diffusion Transformers

Paper • 2512.22323 • Published Dec 26, 2025 • 39