Tiancai Wang

Partner@Dexmal·中国·OpenReview

研究方向

Robotics · Multi-Modal Large Language Model · 3D Object Detection · Multi-Object Tracking · Instance Segmentation · Human-Object Interaction · Object Detection

4.5

MemoryVLA: Perceptual-Cognitive Memory in Vision-Language-Action Models for Robotic Manipulation

ICLR 2026Poster

3.0

ROSA: Harnessing Robot States for Vision-Language and Action Alignment

ICLR 2026Withdrawn

6.0

Vision Foundation Models as Effective Visual Tokenizers for Autoregressive Generation

NeurIPS 2025Poster

5.8

Reconstructive Visual Instruction Tuning

ICLR 2025Poster

5.6

Glad: A Streaming Scene Generator for Autonomous Driving

ICLR 2025Poster

三作

5.3

Embodied Scene Cloning: Solving Generalization in Embodied AI via Visual-Prompt Image Editing

合作者 (20)

Tiancai Wang

MemoryVLA: Perceptual-Cognitive Memory in Vision-Language-Action Models for Robotic Manipulation

ROSA: Harnessing Robot States for Vision-Language and Action Alignment

Vision Foundation Models as Effective Visual Tokenizers for Autoregressive Generation

Reconstructive Visual Instruction Tuning

Glad: A Streaming Scene Generator for Autonomous Driving

Embodied Scene Cloning: Solving Generalization in Embodied AI via Visual-Prompt Image Editing

Is a 3D-Tokenized LLM the Key to Reliable Autonomous Driving?

Continual LLaVA: Continual Instruction Tuning in Large Vision-Language Models

MOTRv3: Release-Fetch Supervision for End-to-End Multi-Object Tracking

PADriver: Towards Personalized Autonomous Driving