SHI Labs

university

https://www.humphreyshi.com/

Activity Feed Request to join this org

AI & ML interests

Computer Vision, AI, Machine Learning

Recent Activity

JiayiGuo821 authored a paper 12 days ago

InsightTok: Improving Text and Face Fidelity in Discrete Tokenization for Autoregressive Image Generation

JiayiGuo821 authored a paper 12 days ago

Refinement via Regeneration: Enlarging Modification Space Boosts Image Refinement in Unified Multimodal Models

JiayiGuo821 authored a paper 12 days ago

Elastic Diffusion Transformer

View all activity

Papers

PAI-Bench: A Comprehensive Benchmark For Physical AI

IMG: Calibrating Diffusion Models via Implicit Multimodal Guidance

View all Papers

authored 4 papers 12 days ago

InsightTok: Improving Text and Face Fidelity in Discrete Tokenization for Autoregressive Image Generation

Paper • 2605.14333 • Published May 14 • 35

Refinement via Regeneration: Enlarging Modification Space Boosts Image Refinement in Unified Multimodal Models

Paper • 2604.25636 • Published Apr 28 • 25

Elastic Diffusion Transformer

Paper • 2602.13993 • Published Feb 15

FastVMT: Eliminating Redundancy in Video Motion Transfer

Paper • 2602.05551 • Published Feb 5 • 3

updated a Space 18 days ago

Physical AI Bench Leaderboard

Benchmark for Physical AI generation and understanding

submitted a paper to Daily Papers 4 months ago

Refinement via Regeneration: Enlarging Modification Space Boosts Image Refinement in Unified Multimodal Models

Paper • 2604.25636 • Published Apr 28 • 25

updated a collection 6 months ago

PAI-Bench

A comprehensive benchmark for Physical AI • 5 items • Updated Feb 24 • 1

updated a collection 7 months ago

MapReduce LoRA

8 items • Updated Feb 12

authored a paper 8 months ago

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

Paper • 2601.10611 • Published Jan 15 • 36