Yuhao Dong PRO

THUdyh's activity

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

upvoted a paper 1 day ago

Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe

Paper • 2604.13016 • Published 3 days ago • 71

upvoted 2 papers 3 days ago

Prompt Relay: Inference-Time Temporal Control for Multi-Event Video Generation

Paper • 2604.10030 • Published 6 days ago • 14

WildDet3D: Scaling Promptable 3D Detection in the Wild

Paper • 2604.08626 • Published 8 days ago • 232

upvoted a paper 4 days ago

VisionFoundry: Teaching VLMs Visual Perception with Synthetic Images

Paper • 2604.09531 • Published 7 days ago • 8

upvoted a paper 7 days ago

HY-Embodied-0.5: Embodied Foundation Models for Real-World Agents

Paper • 2604.07430 • Published 9 days ago • 181

upvoted 2 papers 9 days ago

Video-MME-v2: Towards the Next Stage in Benchmarks for Comprehensive Video Understanding

Paper • 2604.05015 • Published 11 days ago • 232

Vero: An Open RL Recipe for General Visual Reasoning

Paper • 2604.04917 • Published 11 days ago • 30

upvoted 2 papers 10 days ago

FileGram: Grounding Agent Personalization in File-System Behavioral Traces

Paper • 2604.04901 • Published 11 days ago • 40

A Simple Baseline for Streaming Video Understanding

Paper • 2604.02317 • Published 15 days ago • 72

upvoted a paper 11 days ago

Xpertbench: Expert Level Tasks with Rubrics-Based Evaluation

Paper • 2604.02368 • Published 21 days ago • 11

upvoted a paper 14 days ago

HippoCamp: Benchmarking Contextual Agents on Personal Computers

Paper • 2604.01221 • Published 15 days ago • 29

upvoted a paper 15 days ago

PerceptionComp: A Video Benchmark for Complex Perception-Centric Reasoning

Paper • 2603.26653 • Published 20 days ago • 18

upvoted a paper 24 days ago

Insight-V++: Towards Advanced Long-Chain Visual Reasoning with Multimodal Large Language Models

Paper • 2603.18118 • Published 29 days ago • 12

upvoted a paper 27 days ago

VTC-Bench: Evaluating Agentic Multimodal Models via Compositional Visual Tool Chaining

Paper • 2603.15030 • Published Mar 16 • 21

upvoted 6 papers about 1 month ago

Mixture-of-Depths Attention

Paper • 2603.15619 • Published about 1 month ago • 80

Attention Residuals

Paper • 2603.15031 • Published Mar 16 • 180

Spatial-TTT: Streaming Visual-based Spatial Intelligence with Test-Time Training

Paper • 2603.12255 • Published Mar 12 • 91

Memex(RL): Scaling Long-Horizon LLM Agents via Indexed Experience Memory

Paper • 2603.04257 • Published Mar 4 • 19

ArtHOI: Articulated Human-Object Interaction Synthesis by 4D Reconstruction from Video Priors

Paper • 2603.04338 • Published Mar 4 • 24

UniG2U-Bench: Do Unified Models Advance Multimodal Understanding?

Paper • 2603.03241 • Published Mar 3 • 87