Yuwen Xia

yuwenxia's activity

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

upvoted a paper about 6 hours ago

RynnVLA-Latent: Scaling Robotic Manipulation Foundation Models with 3D-Grounded Latent Actions

Paper • 2610.34356 • Published 4 days ago • 30

upvoted 2 papers 1 day ago

Speculative Diffusion is a Tale of Two Tradeoffs

Paper • 2610.31819 • Published 7 days ago • 25

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

Paper • 2610.32250 • Published 6 days ago • 11

upvoted 2 papers 4 days ago

ForcingBooster: Adaptive Patch-wise Denoising for Fast Autoregressive Video Diffusion

Paper • 2610.12625 • Published 21 days ago • 43

Spectral-Spatial Interpretation

Paper • 2610.21114 • Published 14 days ago • 759

upvoted 2 papers 7 days ago

RoAR-VAE: Improving Latent Diffusability through Robust Prediction

Paper • 2610.26216 • Published 10 days ago • 42

MemT-1.0: Towards Memory-Native Evolution

Paper • 2610.26825 • Published 10 days ago • 184

upvoted 2 papers 8 days ago

MOSS-Image Technical Report

Paper • 2610.23374 • Published 13 days ago • 107

Pack Light, CarryOn: Building Object-Oriented Context for Long-Horizon Agents

Paper • 2610.18784 • Published 16 days ago • 126

upvoted 2 papers 10 days ago

BigCell: Generating Gigapixel Whole-Slide Images

Paper • 2610.14261 • Published 20 days ago • 14

APT: Feedback-Driven Agentic Post-Training for Text-to-Image Generation

Paper • 2610.18097 • Published 16 days ago • 31

upvoted 3 papers 13 days ago

Narrow Multimodal Fine-Tuning Can Induce Emergent Misalignment

Paper • 2609.35291 • Published Sep 28 • 30

GroundAnything: Reconciling Parallel Decoding with Precise Visual Grounding at Flash Speed

Paper • 2609.39600 • Published 29 days ago • 58

WOVEN: Weaving Visual World Modeling into Multimodal LLMs

Paper • 2610.12417 • Published 21 days ago • 21

upvoted 3 papers 16 days ago

From Prompting to Composing: A Spatial Canvas Interface for Poster Generation

Paper • 2610.12230 • Published 21 days ago • 21

Post-Training Frontier Text-to-Image Models by Composing Preference and Rubric Rewards

Paper • 2610.02967 • Published 27 days ago • 44

RobotWorld: Benchmarking Multimodal Agents for Robot Use Across Diverse Tasks and Embodiments

Paper • 2610.10409 • Published 22 days ago • 40

upvoted 2 papers 20 days ago

ALoDLM: Adaptively Looped Diffusion Language Models

Paper • 2610.04198 • Published 26 days ago • 81

Memadapter: Counterfactual Adaptation Against Memory-induced Sycophancy

Paper • 2610.05162 • Published 25 days ago • 63

upvoted a paper 22 days ago

HelixWorld: A Real-time Interactive Audio-Visual World Model

Paper • 2609.38123 • Published about 1 month ago • 39