Xinyu Fang

nebulae09's activity

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

upvoted a paper 9 days ago

AgentCompass: A Unified Evaluation Infrastructure for Agent Capabilities

Paper • 2607.13705 • Published 11 days ago • 44

upvoted 3 papers 13 days ago

WildCity: A Real-World City-Scale Testbed for Rendering, Simulation, and Spatial Intelligence

Paper • 2607.06838 • Published 19 days ago • 14

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence

Paper • 2607.07675 • Published 18 days ago • 64

Scalable Visual Pretraining for Language Intelligence

Paper • 2607.09657 • Published 16 days ago • 56

upvoted a collection 19 days ago

RNGBench

Collection

Beyond the Current Observation: Evaluating Multimodal Large Language Models in Controllable Non-Markov Games • 2 items • Updated Jun 23 • 3

liked a dataset 19 days ago

internlm/RNGBench-Game-Trajectories

Viewer • Updated Jun 23 • 45.3k • 201 • 4

upvoted a paper 19 days ago

Beyond the Current Observation: Evaluating Multimodal Large Language Models in Controllable Non-Markov Games

Paper • 2606.19338 • Published Jun 17 • 50

upvoted a paper about 2 months ago

N-GRPO: Embedding-Level Neighbor Mixing for Enhanced Policy Optimization

Paper • 2606.10768 • Published Jun 9 • 25

upvoted a paper 2 months ago

Training Long-Context Vision-Language Models Effectively with Generalization Beyond 128K Context

Paper • 2605.13831 • Published May 13 • 90

upvoted 3 papers 3 months ago

OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation

Paper • 2604.18486 • Published Apr 20 • 96

OpenGame: Open Agentic Coding for Games

Paper • 2604.18394 • Published Apr 20 • 85

Agent-World: Scaling Real-World Environment Synthesis for Evolving General Agent Intelligence

Paper • 2604.18292 • Published Apr 20 • 89

upvoted 4 papers 4 months ago

Kernel-Smith: A Unified Recipe for Evolutionary Kernel Optimization

Paper • 2603.28342 • Published Mar 30 • 26

Intern-S1-Pro: Scientific Multimodal Foundation Model at Trillion Scale

Paper • 2603.25040 • Published Mar 26 • 134

OpenClaw-RL: Train Any Agent Simply by Talking

Paper • 2603.10165 • Published Mar 10 • 158

Visual-ERM: Reward Modeling for Visual Equivalence

Paper • 2603.13224 • Published Mar 13 • 21

liked a model 4 months ago

internlm/Visual-ERM

770k • Updated Mar 24 • 30 • 11

liked 2 models 5 months ago

microsoft/Phi-4-reasoning-vision-15B

Image-Text-to-Text • 15B • Updated Mar 18 • 5.85k • 175

Qwen/Qwen3.5-397B-A17B

Image-Text-to-Text • 403B • Updated Apr 24 • 426k • • 1.54k

upvoted a paper 5 months ago

DataChef: Cooking Up Optimal Data Recipes for LLM Adaptation via Reinforcement Learning

Paper • 2602.11089 • Published Feb 11 • 18