zjn's picture

zjn

garlicisnotmyfavor

·

AI & ML interests

multimodal LLMs && video generation

Recent Activity

authored a paper about 2 months ago

PairUni: Pairwise Training for Unified Multimodal Language Models

upvoted a paper 4 months ago

MMaDA-Parallel: Multimodal Large Diffusion Language Models for Thinking-Aware Editing and Generation

commented on a paper 4 months ago

PairUni: Pairwise Training for Unified Multimodal Language Models

View all activity

Organizations

None yet

upvoted a paper 4 months ago

MMaDA-Parallel: Multimodal Large Diffusion Language Models for Thinking-Aware Editing and Generation

Paper • 2511.09611 • Published Nov 12, 2025 • 70

upvoted 2 papers 5 months ago

Grasp Any Region: Towards Precise, Contextual Pixel Understanding for Multimodal LLMs

Paper • 2510.18876 • Published Oct 21, 2025 • 37

Low-probability Tokens Sustain Exploration in Reinforcement Learning with Verifiable Reward

Paper • 2510.03222 • Published Oct 3, 2025 • 75

upvoted a paper 6 months ago

Revolutionizing Reinforcement Learning Framework for Diffusion Large Language Models

Paper • 2509.06949 • Published Sep 8, 2025 • 56

upvoted 2 papers 8 months ago

A Survey of Context Engineering for Large Language Models

Paper • 2507.13334 • Published Jul 17, 2025 • 261

Traceable Evidence Enhanced Visual Grounded Reasoning: Evaluation and Methodology

Paper • 2507.07999 • Published Jul 10, 2025 • 50

upvoted a paper about 1 year ago

VEM: Environment-Free Exploration for Training GUI Agent with Value Environment Model

Paper • 2502.18906 • Published Feb 26, 2025 • 12

upvoted a paper over 2 years ago

Make Pixels Dance: High-Dynamic Video Generation

Paper • 2311.10982 • Published Nov 18, 2023 • 68