Xin Li

lixin67's activity

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

upvoted an article 3 days ago

view article

Article

🤔👀🎬🖥️📖 Kimi-VL-A3B-Thinking-2506: A Quick Navigation

By and 1 other •

5 days ago

• 50

upvoted 2 articles 15 days ago

view article

Article

GRPO for GUI Grounding Done Right

By •

15 days ago

• 27

view article

Article

No GPU left behind: Unlocking Efficiency with Co-located vLLM in TRL

By and 5 others •

23 days ago

• 58

upvoted 3 papers 17 days ago

Advancing Multimodal Reasoning: From Optimized Cold Start to Staged Reinforcement Learning

Paper • 2506.04207 • Published 22 days ago • 45

SynthRL: Scaling Visual Reasoning with Verifiable Data Synthesis

Paper • 2506.02096 • Published 24 days ago • 51

OpenThoughts: Data Recipes for Reasoning Models

Paper • 2506.04178 • Published 22 days ago • 40

upvoted a paper 29 days ago

Beyond Distillation: Pushing the Limits of Medical LLM Reasoning with Minimalist Rule-Based RL

Paper • 2505.17952 • Published May 23 • 21

upvoted 7 papers about 1 month ago

InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models

Paper • 2504.10479 • Published Apr 14 • 274

Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling

Paper • 2412.05271 • Published Dec 6, 2024 • 159

AttentionInfluence: Adopting Attention Head Influence for Weak-to-Strong Pretraining Data Selection

Paper • 2505.07293 • Published May 12 • 26

MMLongBench: Benchmarking Long-Context Vision-Language Models Effectively and Thoroughly

Paper • 2505.10610 • Published May 15 • 53

Seed1.5-VL Technical Report

Paper • 2505.07062 • Published May 11 • 145

Visual Planning: Let's Think Only with Images

Paper • 2505.11409 • Published May 16 • 56

Qwen3 Technical Report

Paper • 2505.09388 • Published May 14 • 203

upvoted a collection about 1 month ago

PixMo

Collection

A set of vision-language datasets built by Ai2 and used to train the Molmo family of models. Read more at https://molmo.allenai.org/blog • 10 items • Updated Apr 30 • 72

upvoted 3 papers 3 months ago

UI-R1: Enhancing Action Prediction of GUI Agents by Reinforcement Learning

Paper • 2503.21620 • Published Mar 27 • 62

Creation-MMBench: Assessing Context-Aware Creative Intelligence in MLLM

Paper • 2503.14478 • Published Mar 18 • 48

VisualPRM: An Effective Process Reward Model for Multimodal Reasoning

Paper • 2503.10291 • Published Mar 13 • 37

upvoted an article 4 months ago

view article

Article

Welcome Gemma 3: Google's all new multimodal, multilingual, long context open LLM

By and 3 others •

Mar 12

• 437

upvoted a paper 4 months ago

YuE: Scaling Open Foundation Models for Long-Form Music Generation

Paper • 2503.08638 • Published Mar 11 • 66