影响力指数

69.18/100

前 2.8%

全站排名 #1,799

发表论文12 篇

平均评分5.5

年均产出6.0 篇/年

Kui Jia

Full Professor@The Chinese University of Hong Kong, Shenzhen·中国·OpenReview

研究方向

learning and generalization · explainable AI; Interpretable AI · deep learning surface reconstruction · 3D detection; object pose estimation · manipulation and grasping · deep transfer learning

6.0

Sim2Real VLA: Zero-Shot Generalization of Synthesized Skills to Realistic Manipulation

ICLR 2026Poster

5.5

VLBiMan: Vision-Language Anchored One-Shot Demonstration Enables Generalizable Bimanual Robotic Manipulation

ICLR 2026Poster

二作

5.5

HWC-Loco: A Hierarchical Whole-Body Control Approach to Robust Humanoid Locomotion

ICLR 2026Poster

5.3

BiNoMaP: Learning Category-Level Bimanual Non-Prehensile Manipulation Primitives

ICLR 2026Rejected

二作

4.5

Efficient and Context-Aware Label Propagation for Zero-/Few-Shot Training-Free Adaptation of Vision-Language Model

ICLR 2025Poster

6.3

On the Adversarial Risk of Test Time Adaptation: An Investigation into Realistic Test-Time Data Poisoning

ICLR 2025Poster

4.8

DexScale: Automating Data Scaling for Sim2Real Generalizable Robot Control

ICML 2025Poster

通讯

4.6

Boosting Semi-Supervised 2D Human Pose Estimation by Revisiting Data Augmentation and Consistency Training

合作者 (20)

Kui Jia

Sim2Real VLA: Zero-Shot Generalization of Synthesized Skills to Realistic Manipulation

VLBiMan: Vision-Language Anchored One-Shot Demonstration Enables Generalizable Bimanual Robotic Manipulation

HWC-Loco: A Hierarchical Whole-Body Control Approach to Robust Humanoid Locomotion

BiNoMaP: Learning Category-Level Bimanual Non-Prehensile Manipulation Primitives

One-Shot Real-World Demonstration Synthesis for Scalable Bimanual Manipulation

SceneLCM: Multi-Room Indoor Scene Generation with Latent Consistency Modeling

ARMesh: Autoregressive Mesh Generation via Next-Level-of-Detail Prediction

Nabla-R2D3: Effective and Efficient 3D Diffusion Alignment with 2D Rewards

Efficient and Context-Aware Label Propagation for Zero-/Few-Shot Training-Free Adaptation of Vision-Language Model

On the Adversarial Risk of Test Time Adaptation: An Investigation into Realistic Test-Time Data Poisoning

DexScale: Automating Data Scaling for Sim2Real Generalizable Robot Control

Boosting Semi-Supervised 2D Human Pose Estimation by Revisiting Data Augmentation and Consistency Training