影响力指数
68.98/100
前 2.8%
全站排名 #1,825
发表论文26
平均评分5.0
年均产出8.7 篇/年

Zhengzhong Tu

Assistant Professor@Texas A&M University - College Station·美国·OpenReview
研究方向

Autonomous Driving · Generative Models · Vision Language Models · Image Restoration · Computer Vision · Agentic AI

6.0
14

Noisy-Pair Robust Representation Alignment for Positive-Unlabeled Learning

ICLR 2026Poster
二作
6.0
24

FASA: FREQUENCY-AWARE SPARSE ATTENTION

ICLR 2026Poster
6.0
4

AirV2X: Unified Air-Ground Vehicle-to-Everything Collaboration

ICLR 2026Withdrawn
通讯
5.5
18

Improving LLM Symbolic Problem-Solving via Automated Heuristic Discovery

ICLR 2026Rejected
5.3
25

DecAlign: Hierarchical Cross-Modal Alignment for Decoupled Multimodal Representation Learning

ICLR 2026Poster
通讯
5.3
24

Charts Are Not Images: On the Challenges of Scientific Chart Editing

ICLR 2026Poster
5.0
20

Tramba: Mamba with Adaptive Attention for Traffic Speed Forecasting

ICLR 2026Withdrawn
三作
5.0
19

CAST: Contrastive Adaptation and Distillation for Semi-Supervised Instance Segmentation

ICLR 2026Rejected
通讯
5.0
5

NexusFlow: Unifying Disparate Tasks under Partial Supervision via Invertible Flow Networks

ICLR 2026Withdrawn
4.8
26

NavTrust: Benchmarking Trustworthiness for Embodied Navigation

ICLR 2026Rejected
4.7
25

TrustGen: A Platform of Dynamic Benchmarking on the Trustworthiness of Generative Foundation Models

ICLR 2026Poster
4.5
18

LLMs Can Get "Brain Rot"!

ICLR 2026Rejected
4.5
15

MMHU: A Massive-Scale Multimodal Benchmark for Human Behavior Understanding in Autonomous Driving

ICLR 2026Rejected
通讯
4.5
21

Q-Router: Agentic Video Quality Assessment with Expert Model Routing

ICLR 2026Rejected
通讯
4.0
5

HeadsUp! High-Fidelity Portrait Image Super-Resolution

ICLR 2026Withdrawn
通讯
4.0
8

V2X-UniPool: Unifying Multimodal Perception and Knowledge Reasoning for Autonomous Driving

ICLR 2026Rejected
3.5
5

SafeCoop: Unravelling Full Stack Safety in Agentic Cooperative Driving

ICLR 2026Withdrawn
通讯
2.0
4

Ariadne: Advancing Real-world Path-finding Capabilities of VLMs via Difficulty-aware Reinforcement Learning

ICLR 2026Withdrawn
-1

Unlocking the Boundaries of Cross-Task Visual In-Context Learning via Implicit Text-Driven LVMs

ICLR 2026Withdrawn
三作