Xirui Li PRO

AIcell's activity

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

upvoted 4 papers 2 days ago

Towards a Science of AI Agent Reliability

Paper • 2602.16666 • Published 3 days ago • 12

Multi-agent cooperation through in-context co-player inference

Paper • 2602.16301 • Published 3 days ago • 13

Learning Situated Awareness in the Real World

Paper • 2602.16682 • Published 3 days ago • 5

Learning Humanoid End-Effector Control for Open-Vocabulary Visual Loco-Manipulation

Paper • 2602.16705 • Published 3 days ago • 26

upvoted 5 papers 3 days ago

Understanding vs. Generation: Navigating Optimization Dilemma in Multimodal Models

Paper • 2602.15772 • Published 4 days ago • 6

SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks

Paper • 2602.12670 • Published 8 days ago • 48

Revisiting the Platonic Representation Hypothesis: An Aristotelian View

Paper • 2602.14486 • Published 5 days ago • 9

Visual Persuasion: What Influences Decisions of Vision-Language Models?

Paper • 2602.15278 • Published 5 days ago • 3

Does Socialization Emerge in AI Agent Society? A Case Study of Moltbook

Paper • 2602.14299 • Published 6 days ago • 24

upvoted 2 papers 4 days ago

Embed-RL: Reinforcement Learning for Reasoning-Driven Multimodal Embeddings

Paper • 2602.13823 • Published 7 days ago • 9

BitDance: Scaling Autoregressive Generative Models with Binary Tokens

Paper • 2602.14041 • Published 6 days ago • 42

upvoted 2 papers 5 days ago

Less is Enough: Synthesizing Diverse Data in Feature Space of LLMs

Paper • 2602.10388 • Published 11 days ago • 219

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

Paper • 2602.12395 • Published 9 days ago • 14

upvoted a paper 13 days ago

PaperBanana: Automating Academic Illustration for AI Scientists

Paper • 2601.23265 • Published 22 days ago • 192

upvoted a paper 14 days ago

Quantifying the Gap between Understanding and Generation within Unified Multimodal Models

Paper • 2602.02140 • Published 19 days ago • 12

upvoted 5 papers about 2 months ago

mHC: Manifold-Constrained Hyper-Connections

Paper • 2512.24880 • Published Dec 31, 2025 • 307

TurboDiffusion: Accelerating Video Diffusion Models by 100-200 Times

Paper • 2512.16093 • Published Dec 18, 2025 • 95

StereoWorld: Geometry-Aware Monocular-to-Stereo Video Generation

Paper • 2512.09363 • Published Dec 10, 2025 • 72

Schoenfeld's Anatomy of Mathematical Reasoning by Language Models

Paper • 2512.19995 • Published Dec 23, 2025 • 16

EgoX: Egocentric Video Generation from a Single Exocentric Video

Paper • 2512.08269 • Published Dec 9, 2025 • 119