Xiangtai Li

LXT's activity

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

upvoted a paper 4 days ago

PixelEyes: Decoupling Perception and Reasoning for Pinpoint Visual Evidence Seeking

Paper • 2607.00115 • Published 7 days ago • 10

upvoted 2 papers 12 days ago

Improved Large Language Diffusion Models

Paper • 2606.25331 • Published 13 days ago • 43

The Hitchhiker's Guide to Agentic AI: From Foundations to Systems

Paper • 2606.24937 • Published 15 days ago • 18

upvoted a paper 15 days ago

PerceptionDLM: Parallel Region Perception with Multimodal Diffusion Language Models

Paper • 2606.19534 • Published 20 days ago • 64

upvoted a paper 26 days ago

Skill-3D: Evolving Scene-Aware Skills for Agentic 3D Spatial Reasoning

Paper • 2606.07436 • Published Jun 5 • 25

upvoted a paper 29 days ago

Watch, Remember, Reason: Human-View Video Understanding with MLLMs

Paper • 2606.07433 • Published Jun 5 • 21

upvoted a paper 30 days ago

Towards One-to-Many Temporal Grounding

Paper • 2606.06294 • Published Jun 4 • 7

upvoted a paper about 1 month ago

LoomVideo: Unifying Multimodal Inputs into Video Generation and Editing

Paper • 2606.06042 • Published Jun 4 • 24

upvoted 3 papers 2 months ago

Turning the TIDE: Cross-Architecture Distillation for Diffusion Large Language Models

Paper • 2604.26951 • Published Apr 29 • 50

Context Unrolling in Omni Models

Paper • 2604.21921 • Published Apr 23 • 14

LLaDA2.0-Uni: Unifying Multimodal Understanding and Generation with Diffusion Large Language Model

Paper • 2604.20796 • Published Apr 22 • 245

upvoted a paper 3 months ago

VideoZeroBench: Probing the Limits of Video MLLMs with Spatio-Temporal Evidence Verification

Paper • 2604.01569 • Published Apr 2 • 14

upvoted a paper 4 months ago

A Very Big Video Reasoning Suite

Paper • 2602.20159 • Published Feb 23 • 526

upvoted a paper 5 months ago

SAMTok: Representing Any Mask with Two Words

Paper • 2601.16093 • Published Jan 22 • 44

upvoted 4 papers 6 months ago

Molmo2: Open Weights and Data for Vision-Language Models with Video Understanding and Grounding

Paper • 2601.10611 • Published Jan 15 • 35

STEP3-VL-10B Technical Report

Paper • 2601.09668 • Published Jan 14 • 196

BabyVision: Visual Reasoning Beyond Language

Paper • 2601.06521 • Published Jan 10 • 201

Watching, Reasoning, and Searching: A Video Deep Research Benchmark on Open Web for Agentic Video Reasoning

Paper • 2601.06943 • Published Jan 11 • 215

upvoted 2 papers 7 months ago

Vision-Language-Action Models for Autonomous Driving: Past, Present, and Future

Paper • 2512.16760 • Published Dec 18, 2025 • 15

LLaDA2.0: Scaling Up Diffusion Language Models to 100B

Paper • 2512.15745 • Published Dec 10, 2025 • 90