影响力指数

49.96/100

前 8.6%

全站排名 #5,526

发表论文12 篇

平均评分5.3

年均产出4.0 篇/年

Wenyu Liu

Full Professor@Huazhong University of Science and Technology·中国·OpenReview

研究方向

Artificial intelligence · Computer Vision

5.5

AlphaDrive: Unleashing the Power of VLMs in Autonomous Driving via RL and Reasoning

ICLR 2026Withdrawn

4.5

TriC-Motion: Tri-Domain Causal Modeling Grounded Text-to-Motion Generation

ICLR 2026Poster

3.0

UniLat3D: Geometry-Appearance Unified Latents for Single-Stage 3D Generation

ICLR 2026Withdrawn

7.0

Genesis: Multimodal Driving Scene Generation with Spatio-Temporal and Cross-Modal Consistency

NeurIPS 2025Poster

6.8

RAD: Training an End-to-End Driving Policy via Large-Scale 3DGS-based Reinforcement Learning

NeurIPS 2025Poster

6.3

ControlAR: Controllable Image Generation with Autoregressive Models

ICLR 2025Poster

4.2

EVF-SAM: Early Vision-Language Fusion For Text-Prompted Segment Anything Model

合作者 (20)

Wenyu Liu

VADv2: End-to-End Vectorized Autonomous Driving via Probabilistic Planning

ReCogDrive: A Reinforced Cognitive Framework for End-to-End Autonomous Driving

4DLangVGGT: 4D Language Visual Geometry Grounded Transformer

TransLight: Image-Guided Customized Lighting Control with Generative Decoupling

AlphaDrive: Unleashing the Power of VLMs in Autonomous Driving via RL and Reasoning

TriC-Motion: Tri-Domain Causal Modeling Grounded Text-to-Motion Generation

UniLat3D: Geometry-Appearance Unified Latents for Single-Stage 3D Generation

Genesis: Multimodal Driving Scene Generation with Spatio-Temporal and Cross-Modal Consistency

RAD: Training an End-to-End Driving Policy via Large-Scale 3DGS-based Reinforcement Learning

ControlAR: Controllable Image Generation with Autoregressive Models

EVF-SAM: Early Vision-Language Fusion For Text-Prompted Segment Anything Model