Xirui Li PRO

AIcell's activity

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

upvoted a paper about 1 hour ago

EgoX: Egocentric Video Generation from a Single Exocentric Video

Paper • 2512.08269 • Published 17 days ago • 110

upvoted a paper about 24 hours ago

WorldPlay: Towards Long-Term Geometric Consistency for Real-Time Interactive World Modeling

Paper • 2512.14614 • Published 9 days ago • 64

upvoted 2 papers 1 day ago

The Prism Hypothesis: Harmonizing Semantic and Pixel Representations via Unified Autoencoding

Paper • 2512.19693 • Published 3 days ago • 60

SpatialTree: How Spatial Abilities Branch Out in MLLMs

Paper • 2512.20617 • Published 2 days ago • 40

upvoted a paper 3 days ago

Can LLMs Estimate Student Struggles? Human-AI Difficulty Alignment with Proficiency Simulation for Item Difficulty Prediction

Paper • 2512.18880 • Published 4 days ago • 23

upvoted a paper 10 days ago

V-REX: Benchmarking Exploratory Visual Reasoning via Chain-of-Questions

Paper • 2512.11995 • Published 13 days ago • 9

upvoted 2 papers about 1 month ago

The Path Not Taken: RLVR Provably Learns Off the Principals

Paper • 2511.08567 • Published Nov 11 • 33

Routing Manifold Alignment Improves Generalization of Mixture-of-Experts LLMs

Paper • 2511.07419 • Published Nov 10 • 26

upvoted a paper about 2 months ago

ThinkMorph: Emergent Properties in Multimodal Interleaved Chain-of-Thought Reasoning

Paper • 2510.27492 • Published Oct 30 • 82

upvoted 2 papers 3 months ago

VLA-RFT: Vision-Language-Action Reinforcement Fine-tuning with Verified Rewards in World Simulators

Paper • 2510.00406 • Published Oct 1 • 65

Vision-Zero: Scalable VLM Self-Improvement via Strategic Gamified Self-Play

Paper • 2509.25541 • Published Sep 29 • 140

upvoted a paper 4 months ago

AgentFly: Fine-tuning LLM Agents without Fine-tuning LLMs

Paper • 2508.16153 • Published Aug 22 • 160

upvoted 2 papers 8 months ago

FUSION: Fully Integration of Vision-Language Representations for Deep Cross-Modal Understanding

Paper • 2504.09925 • Published Apr 14 • 38

VL-Rethinker: Incentivizing Self-Reflection of Vision-Language Models with Reinforcement Learning

Paper • 2504.08837 • Published Apr 10 • 43

upvoted a collection 10 months ago

InternVL2.5

Collection

Better than InternVL 2.0 • 19 items • Updated Sep 28 • 92

upvoted 2 papers 10 months ago

R1-Zero's "Aha Moment" in Visual Reasoning on a 2B Non-SFT Model

Paper • 2503.05132 • Published Mar 7 • 57

Thus Spake Long-Context Large Language Model

Paper • 2502.17129 • Published Feb 24 • 73

upvoted 3 papers 12 months ago

NVILA: Efficient Frontier Visual Language Models

Paper • 2412.04468 • Published Dec 5, 2024 • 59

Perception Tokens Enhance Visual Reasoning in Multimodal Language Models

Paper • 2412.03548 • Published Dec 4, 2024 • 17

STIV: Scalable Text and Image Conditioned Video Generation

Paper • 2412.07730 • Published Dec 10, 2024 • 74