Situated Language and Embodied Dialogue Lab

university

https://sled.eecs.umich.edu/

SLED_AI

sled-group

Activity Feed Request to join this org

AI & ML interests

We develop computational models for language processing that take into account the rich situational and communicative context and build embodied AI agents that can communicate with humans in language.

Recent Activity

Xuweiyi authored a paper 10 days ago

Frame In-N-Out: Unbounded Controllable Image-to-Video Generation

marstin authored a paper about 1 month ago

VEGGIE: Instructional Editing and Reasoning of Video Concepts with Grounded Generation

marstin authored a paper about 1 month ago

Vision-Language Models Are Not Pragmatically Competent in Referring Expression Generation

View all activity

sled-umich's activity

Xuweiyi

authored a paper 10 days ago

Frame In-N-Out: Unbounded Controllable Image-to-Video Generation

Paper • 2505.21491 • Published 10 days ago • 17

marstin

authored 2 papers about 1 month ago

VEGGIE: Instructional Editing and Reasoning of Video Concepts with Grounded Generation

Paper • 2503.14350 • Published Mar 18

Vision-Language Models Are Not Pragmatically Competent in Referring Expression Generation

Paper • 2504.16060 • Published Apr 22

Jiayi-Pan

authored a paper about 1 month ago

Learning Adaptive Parallel Reasoning with Language Models

Paper • 2504.15466 • Published Apr 21 • 42

miyen

updated a Space 3 months ago

3D-POPE Leaderboard

Submit and evaluate 3D models on a leaderboard

marstin

authored 4 papers 3 months ago

DriVLMe: Enhancing LLM-based Autonomous Driving Agents with Embodied and Social Experiences

Paper • 2406.03008 • Published Jun 5, 2024

Vision-and-Language Navigation Today and Tomorrow: A Survey in the Era of Foundation Models

Paper • 2407.07035 • Published Jul 9, 2024

Humanity's Last Exam

Paper • 2501.14249 • Published Jan 24 • 75

Training Turn-by-Turn Verifiers for Dialogue Tutoring Agents: The Curious Case of LLMs as Your Coding Tutors

Paper • 2502.13311 • Published Feb 18 • 1

jedyang97

authored a paper 4 months ago

Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Pass

Paper • 2501.13928 • Published Jan 23 • 17

594zyc

authored a paper 5 months ago

Next Token Prediction Towards Multimodal Intelligence: A Comprehensive Survey

Paper • 2412.18619 • Published Dec 16, 2024 • 59

jedyang97

in sled-umich/3D-GRAND 5 months ago

How to find the instance id for 3D-FRONT?

#12 opened 5 months ago by

jedyang97

updated a dataset 5 months ago

sled-umich/3D-GRAND

Updated Jan 6 • 106 • 8

Jiayi-Pan

authored 5 papers 5 months ago

World-to-Words: Grounded Open Vocabulary Acquisition through Fast Mapping in Vision-Language Models

Paper • 2306.08685 • Published Jun 14, 2023 • 1

Inversion-Free Image Editing with Natural Language

Paper • 2312.04965 • Published Dec 7, 2023 • 2

ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL

Paper • 2402.19446 • Published Feb 29, 2024

DANLI: Deliberative Agent for Following Natural Language Instructions

Paper • 2210.12485 • Published Oct 22, 2022

Fine-Tuning Large Vision-Language Models as Decision-Making Agents via Reinforcement Learning

Paper • 2405.10292 • Published May 16, 2024 • 2

6kplus

updated a model 7 months ago

sled-umich/DriVLMe

Updated Nov 16, 2024 • 7

jedyang97

authored a paper 7 months ago

Teaching Embodied Reinforcement Learning Agents: Informativeness and Diversity of Language Use

Paper • 2410.24218 • Published Oct 31, 2024 • 6