Zesen Cheng

ClownRat's activity

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

upvoted an article 1 day ago

view article

Article

Mixture of Experts Explained

Dec 11, 2023

• 393

upvoted an article 2 days ago

view article

Article

SigLIP 2: A better multilingual vision language encoder

3 days ago

• 75

upvoted 3 papers 4 days ago

Qwen2.5-VL Technical Report

Paper • 2502.13923 • Published 5 days ago • 137

Small Models Struggle to Learn from Strong Reasoners

Paper • 2502.12143 • Published 7 days ago • 25

LongPO: Long Context Self-Evolution of Large Language Models through Short-to-Long Preference Optimization

Paper • 2502.13922 • Published 5 days ago • 25

upvoted 2 papers 16 days ago

Kimi k1.5: Scaling Reinforcement Learning with LLMs

Paper • 2501.12599 • Published Jan 22 • 97

DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Paper • 2501.12948 • Published Jan 22 • 330

upvoted 5 papers 26 days ago

OmniThink: Expanding Knowledge Boundaries in Machine Writing through Thinking

Paper • 2501.09751 • Published Jan 16 • 47

Towards Best Practices for Open Datasets for LLM Training

Paper • 2501.08365 • Published Jan 14 • 55

MMDocIR: Benchmarking Multi-Modal Retrieval for Long Documents

Paper • 2501.08828 • Published Jan 15 • 30

Tarsier2: Advancing Large Vision-Language Models from Detailed Video Description to Comprehensive Video Understanding

Paper • 2501.07888 • Published Jan 14 • 15

MiniMax-01: Scaling Foundation Models with Lightning Attention

Paper • 2501.08313 • Published Jan 14 • 273

upvoted 3 papers 29 days ago

Valley2: Exploring Multimodal Models with Scalable Vision-Language Design

Paper • 2501.05901 • Published Jan 10 • 1

Eagle: Exploring The Design Space for Multimodal LLMs with Mixture of Encoders

Paper • 2408.15998 • Published Aug 28, 2024 • 86

Language Model Can Listen While Speaking

Paper • 2408.02622 • Published Aug 5, 2024 • 39

upvoted a paper 30 days ago

Video-MMMU: Evaluating Knowledge Acquisition from Multi-Discipline Professional Videos

Paper • 2501.13826 • Published Jan 23 • 24

upvoted 3 collections about 1 month ago

VideoRefer

Collection

6 items • Updated 5 days ago • 2

VideoLLaMA

Collection

The first edition of VideoLLaMA • 6 items • Updated Jan 4 • 3

VideoLLaMA3

Collection

Frontier Multimodal Foundation Models for Video Understanding • 14 items • Updated 17 days ago • 13

upvoted a paper about 1 month ago

VideoAutoArena: An Automated Arena for Evaluating Large Multimodal Models in Video Analysis through User Simulation

Paper • 2411.13281 • Published Nov 20, 2024 • 20