LMMs-Lab

community

https://www.lmms-lab.com/

EvolvingLMMs-Lab

AI & ML interests

Feeling and building the multimodal intelligence.

Recent Activity

luodian new activity 3 days ago

lmms-lab/HLE-Verified:Clarification Regarding HLE-Verified Dataset Attribution

luodian updated a dataset 3 days ago

lmms-lab/HLE-Verified

yl-1993 authored a paper 6 days ago

The Quest for Generalizable Motion Generation: Data, Model, and Evaluation

View all activity

Papers

OneVision-Encoder: Codec-Aligned Sparsity as a Foundational Principle for Multimodal Intelligence

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

View all Papers

in lmms-lab/HLE-Verified 3 days ago

Clarification Regarding HLE-Verified Dataset Attribution

#1 opened 3 days ago by

updated a dataset 3 days ago

lmms-lab/HLE-Verified

Preview • Updated 3 days ago • 5.2k • 2

authored 2 papers 6 days ago

The Quest for Generalizable Motion Generation: Data, Model, and Evaluation

Paper • 2510.26794 • Published Oct 30, 2025 • 27

ConsistCompose: Unified Multimodal Layout Control for Image Composition

Paper • 2511.18333 • Published Nov 23, 2025 • 4

authored 2 papers 7 days ago

The Quest for Generalizable Motion Generation: Data, Model, and Evaluation

Paper • 2510.26794 • Published Oct 30, 2025 • 27

ConsistCompose: Unified Multimodal Layout Control for Image Composition

Paper • 2511.18333 • Published Nov 23, 2025 • 4

authored a paper 7 days ago

A Very Big Video Reasoning Suite

Paper • 2602.20159 • Published 8 days ago • 504

authored a paper 7 days ago

A Very Big Video Reasoning Suite

Paper • 2602.20159 • Published 8 days ago • 504

published a dataset 10 days ago

lmms-lab/minerva

Updated 10 days ago • 11

published a dataset 11 days ago

lmms-lab/HLE-Verified

Preview • Updated 3 days ago • 5.2k • 2

authored a paper 13 days ago

UniT: Unified Multimodal Chain-of-Thought Test-time Scaling

Paper • 2602.12279 • Published 19 days ago • 19

authored a paper 14 days ago

OneVision-Encoder: Codec-Aligned Sparsity as a Foundational Principle for Multimodal Intelligence

Paper • 2602.08683 • Published 22 days ago • 49

submitted a paper to Daily Papers 15 days ago

OneVision-Encoder: Codec-Aligned Sparsity as a Foundational Principle for Multimodal Intelligence

Paper • 2602.08683 • Published 22 days ago • 49

authored 2 papers 20 days ago

ProCLIP: Progressive Vision-Language Alignment via LLM-based Embedder

Paper • 2510.18795 • Published Oct 21, 2025 • 11

DanQing: An Up-to-Date Large-Scale Chinese Vision-Language Pre-training Dataset

Paper • 2601.10305 • Published Jan 15 • 36

updated a Space 20 days ago

README

updated a collection 21 days ago

OneVision-Encoder

HEVC-Style Vision Transformer • 2 items • Updated 21 days ago • 3

updated a model 25 days ago

lmms-lab/LLaVA-OneVision-1.5-4B-Instruct

Image-Text-to-Text • 5B • Updated 25 days ago • 3.38k • 18

authored a paper about 1 month ago

iFSQ: Improving FSQ for Image Generation with 1 Line of Code

Paper • 2601.17124 • Published Jan 23 • 33

in lmms-lab/sae-sample-cache-dataset about 2 months ago

Why there are so many duplicated images?

#1 opened about 2 months ago by