LMMS Lab Logo
Home
Posts
Notes
About

Building
the way to multimodal intelligence.

Open research on multimodal models, evaluation, benchmarks, and lmms-eval tooling - shared as we discover.

Explore Research
About the Lab
LMMS-LAB // BREACH ACTIVENEURAL WEIGHT EXTRACTION
1/7LIVE
_
thinking:
_
Featured Research
LLaVA-OneVision-2: Towards Next-Generation Perceptual Intelligence
APR 20, 2026

LLaVA-OneVision-2:
Towards Next-Generation Perceptual Intelligence

models
Read Paper
Latest Publications
View Archive
[01]
OneVision Encoder: Codec-Aligned Sparsity as a Foundational Principle for Multimodal Intelligence
OneVision Encoder: Codec-Aligned Spar...
JAN 2026

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

models
[02]
LLaVA-OneVision-1.5: Fully Open Framework for Democratized Multimodal Training
LLaVA-OneVision-1.5: Fully Open Frame...
SEP 2025

LLaVA-OneVision-1.5: Fully Open Framework for Democratized Multimodal Training

models
[03]
LongVT: Incentivizing "Thinking with Long Videos" via Native Tool Calling
LongVT: Incentivizing "Thinking with ...
NOV 2025

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

models
[04]
OpenMMReasoner: Pushing the Frontiers for Multimodal Reasoning with an Open and General Recipe
OpenMMReasoner: Pushing the Frontiers...
NOV 2025

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

models
2026 LMMs-Lab
GitHubTwitter