Jinhong Xia's picture

3 1

Jinhong Xia

zhi-dian

·

zhi-dian

AI & ML interests

efficient LLM, 3D Computer Vision

Recent Activity

upvoted a paper about 23 hours ago

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

upvoted a paper 13 days ago

Quantifying the Gap between Understanding and Generation within Unified Multimodal Models

upvoted a paper 21 days ago

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

View all activity

Organizations

upvoted a paper about 23 hours ago

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

Paper • 2602.12395 • Published 6 days ago • 14

upvoted a paper 13 days ago

Quantifying the Gap between Understanding and Generation within Unified Multimodal Models

Paper • 2602.02140 • Published 16 days ago • 12

upvoted a paper 21 days ago

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

Paper • 2601.18744 • Published 23 days ago • 10

liked a model 2 months ago

Qwen/Qwen3-0.6B

Text Generation • 0.8B • Updated Jul 26, 2025 • 10.2M • 1.09k