LMMs-Lab-SI

community

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

EvolvingLMMs-Lab

AI & ML interests

Feeling and building the multimodal intelligence.

Recent Activity

yl-1993 authored a paper 3 days ago

From Pixels to Actions - Towards Native Vision-Language-Action Policies

caizhongang authored a paper 7 days ago

From Pixels to Actions - Towards Native Vision-Language-Action Policies

caizhongang authored a paper 9 days ago

Probing Spatial State Representations in Visual Foundation Models

View all activity

authored a paper 3 days ago

From Pixels to Actions - Towards Native Vision-Language-Action Policies

Paper • 2611.06918 • Published 8 days ago • 61

authored a paper 7 days ago

From Pixels to Actions - Towards Native Vision-Language-Action Policies

Paper • 2611.06918 • Published 8 days ago • 61

authored 2 papers 9 days ago

Probing Spatial State Representations in Visual Foundation Models

Paper • 2610.40636 • Published 14 days ago • 21

Read, Allocate, Route: Role-Coupled Tokenization for Pixel-Space Generative Transformers

Paper • 2610.40647 • Published 15 days ago • 27

authored a paper 10 days ago

Probing Spatial State Representations in Visual Foundation Models

Paper • 2610.40636 • Published 14 days ago • 21

authored 3 papers 21 days ago

Has GPT-6-Astra Achieved Embodied Intelligence?

Paper • 2610.22471 • Published 29 days ago • 136

MTEdit: Packed Trajectories Beat Rollouts for Multi-Turn Image Editing

Paper • 2610.23751 • Published 28 days ago • 23

MT Forcing: Towards Stable and Consistent Multi-Turn Image Editing with Autoregressive Diffusion

Paper • 2610.25404 • Published 26 days ago • 40

authored 3 papers 23 days ago

Has GPT-6-Astra Achieved Embodied Intelligence?

Paper • 2610.22471 • Published 29 days ago • 136

Looped Diffusion Transformer

Paper • 2609.40305 • Published Sep 30 • 6

Learning Native Reflection in Unified Models with Interleaved Reinforcement Learning

Paper • 2609.35767 • Published Sep 28 • 42

authored a paper 24 days ago

Has GPT-6-Astra Achieved Embodied Intelligence?

Paper • 2610.22471 • Published 29 days ago • 136

authored a paper 24 days ago

SenseNova-U1.5: Towards Native Unified Visual Intelligence

Paper • 2609.11929 • Published Sep 10 • 139

authored a paper 24 days ago

VBVR-Pro: A Scalable and Verifiable Suite for Native Visual Reasoning

Paper • 2608.26105 • Published Aug 26 • 76

authored 3 papers 24 days ago

SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-unify Architecture

Paper • 2605.12500 • Published May 12 • 153

Scaling Spatial Intelligence with Multimodal Foundation Models

Paper • 2511.13719 • Published Nov 17, 2025 • 50

Has GPT-5 Achieved Spatial Intelligence? An Empirical Study

Paper • 2508.13142 • Published Aug 18, 2025 • 37

submitted a paper to Daily Papers 25 days ago

Has GPT-6-Astra Achieved Embodied Intelligence?

Paper • 2610.22471 • Published 29 days ago • 136

authored a paper 28 days ago

LightVAE: Towards Compact and Efficient Video Autoencoders

Paper • 2610.14726 • Published Oct 10 • 19

authored a paper about 2 months ago

Senses Wide Shut: A Representation-Action Gap in Omnimodal LLMs

Paper • 2605.13737 • Published May 13 • 2