UniX Lab

non-profit

AI & ML interests

Unifying vision, reasoning the world, empowering agents. UniX Lab stands at the frontier intersection of multimodal intelligence. With unified modeling as our cornerstone, we expand from visual generation to deep reasoning and autonomous agents. We believe in the power of collaboration and invite you to join this journey of exploring the boundaries of intelligence.

Recent Activity

littlepure2333 authored a paper about 9 hours ago

Geometry-Aware Rotary Position Embedding for Consistent Video World Model

wukeming11 authored a paper about 1 month ago

DeepResearchEval: An Automated Framework for Deep Research Task Construction and Agentic Evaluation

wukeming11 submitted a paper about 1 month ago

DeepResearchEval: An Automated Framework for Deep Research Task Construction and Agentic Evaluation

View all activity

littlepure2333

authored a paper about 9 hours ago

Geometry-Aware Rotary Position Embedding for Consistent Video World Model

Paper • 2602.07854 • Published 11 days ago • 2

wukeming11

authored a paper about 1 month ago

DeepResearchEval: An Automated Framework for Deep Research Task Construction and Agentic Evaluation

Paper • 2601.09688 • Published Jan 14 • 126

wukeming11

submitted a paper to Daily Papers about 1 month ago

DeepResearchEval: An Automated Framework for Deep Research Task Construction and Agentic Evaluation

Paper • 2601.09688 • Published Jan 14 • 126

mwxely

authored a paper 2 months ago

A Comprehensive Study on Visual Token Redundancy for Discrete Diffusion-based Multimodal Large Language Models

Paper • 2511.15098 • Published Nov 19, 2025

kcz358

authored a paper 3 months ago

LongVT: Incentivizing "Thinking with Long Videos" via Native Tool Calling

Paper • 2511.20785 • Published Nov 25, 2025 • 185

mwxely

authored 2 papers 3 months ago

FACE: Evaluating Natural Language Generation with Fourier Analysis of Cross-Entropy

Paper • 2305.10307 • Published May 17, 2023

LongVT: Incentivizing "Thinking with Long Videos" via Native Tool Calling

Paper • 2511.20785 • Published Nov 25, 2025 • 185

wukeming11

authored 2 papers 3 months ago

LongVT: Incentivizing "Thinking with Long Videos" via Native Tool Calling

Paper • 2511.20785 • Published Nov 25, 2025 • 185

EditReward: A Human-Aligned Reward Model for Instruction-Guided Image Editing

Paper • 2509.26346 • Published Sep 30, 2025 • 19

mwxely

authored 5 papers 3 months ago

TimeExpert: An Expert-Guided Video LLM for Video Temporal Grounding

Paper • 2508.01699 • Published Aug 3, 2025

AI-Generated Images as Data Source: The Dawn of Synthetic Era

Paper • 2310.01830 • Published Oct 3, 2023

ToDRE: Visual Token Pruning via Diversity and Task Awareness for Efficient Large Vision-Language Models

Paper • 2505.18757 • Published May 24, 2025

Versatile Transition Generation with Image-to-Video Diffusion

Paper • 2508.01698 • Published Aug 3, 2025

OpenMMReasoner: Pushing the Frontiers for Multimodal Reasoning with an Open and General Recipe

Paper • 2511.16334 • Published Nov 20, 2025 • 93

wukeming11

authored a paper 3 months ago

OpenMMReasoner: Pushing the Frontiers for Multimodal Reasoning with an Open and General Recipe

Paper • 2511.16334 • Published Nov 20, 2025 • 93

kcz358

authored 2 papers 3 months ago

UniME-V2: MLLM-as-a-Judge for Universal Multimodal Embedding Learning

Paper • 2510.13515 • Published Oct 15, 2025 • 12

OpenMMReasoner: Pushing the Frontiers for Multimodal Reasoning with an Open and General Recipe

Paper • 2511.16334 • Published Nov 20, 2025 • 93

wukeming11

authored a paper 4 months ago

A Rigorous Benchmark with Multidimensional Evaluation for Deep Research Agents: From Answers to Reports

Paper • 2510.02190 • Published Oct 2, 2025 • 19

wukeming11

authored 2 papers 5 months ago

Modeling All-Atom Glycan Structures via Hierarchical Message Passing and Multi-Scale Pre-training

Paper • 2506.01376 • Published Jun 2, 2025

VideoScore2: Think before You Score in Generative Video Evaluation

Paper • 2509.22799 • Published Sep 26, 2025 • 26