Jinhong Xia

zhi-dian's activity

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

upvoted a paper 18 days ago

LEGO-Anything: Coding Agents for 3D Scene Reconstruction

Paper • 2609.36380 • Published 26 days ago • 104

upvoted a paper 3 months ago

Reinforcement Learning with Evolving Rubrics as Rewards for Audio Reasoning

Paper • 2608.02831 • Published Aug 3 • 16

upvoted a paper 8 months ago

What does RL improve for Visual Reasoning? A Frankenstein-Style Analysis

Paper • 2602.12395 • Published Feb 12 • 17

upvoted 2 papers 9 months ago

Quantifying the Gap between Understanding and Generation within Unified Multimodal Models

Paper • 2602.02140 • Published Feb 2 • 13

TSRBench: A Comprehensive Multi-task Multi-modal Time Series Reasoning Benchmark for Generalist Models

Paper • 2601.18744 • Published Jan 26 • 12