Xiang Deng

papers

981

total citations

papers (12)

Mind2Web: Towards a Generalist Agent for the Web

NEURIPS 2023arXiv

829

citations

LION: Empowering Multimodal Large Language Model with Dual-Level Visual Knowledge

CVPR 2024arXiv

citations

Dual-View Visual Contextualization for Web Navigation

CVPR 2024arXiv

citations

3D-AffordanceLLM: Harnessing Large Language Models for Open-Vocabulary Affordance Detection in 3D Worlds

ICLR 2025arXiv

citations

Spatial-Temporal Graph Diffusion Policy with Kinematic Modeling for Bimanual Robotic Manipulation

CVPR 2025arXiv

citations

STAR: Learning Diverse Robot Skill Abstractions through Rotation-Augmented Vector Quantization

ICML 2025arXiv

citations

RoboMP$^2$: A Robotic Multimodal Perception-Planning Framework with Multimodal Large Language Models

ICML 2024arXiv

citations

Understanding the Forgetting of (Replay-based) Continual Learning via Feature Learning: Angle Matters

ICML 2025

citations

Addressing Multi-Label Learning with Partial Labels: From Sample Selection to Label Selection

AAAI 2025

citations

Xiang Deng

papers (12)

Mind2Web: Towards a Generalist Agent for the Web

LION: Empowering Multimodal Large Language Model with Dual-Level Visual Knowledge

Dual-View Visual Contextualization for Web Navigation

3D-AffordanceLLM: Harnessing Large Language Models for Open-Vocabulary Affordance Detection in 3D Worlds

Spatial-Temporal Graph Diffusion Policy with Kinematic Modeling for Bimanual Robotic Manipulation

STAR: Learning Diverse Robot Skill Abstractions through Rotation-Augmented Vector Quantization

RoboMP$^2$: A Robotic Multimodal Perception-Planning Framework with Multimodal Large Language Models

Understanding the Forgetting of (Replay-based) Continual Learning via Feature Learning: Angle Matters

Addressing Multi-Label Learning with Partial Labels: From Sample Selection to Label Selection

Comprehensive Knowledge Distillation with Causal Intervention

Personalized Education: Blind Knowledge Distillation

Embodied Crowd Counting

papers (12)

Mind2Web: Towards a Generalist Agent for the Web

LION: Empowering Multimodal Large Language Model with Dual-Level Visual Knowledge

Dual-View Visual Contextualization for Web Navigation

3D-AffordanceLLM: Harnessing Large Language Models for Open-Vocabulary Affordance Detection in 3D Worlds

Spatial-Temporal Graph Diffusion Policy with Kinematic Modeling for Bimanual Robotic Manipulation

STAR: Learning Diverse Robot Skill Abstractions through Rotation-Augmented Vector Quantization

RoboMP$^2$: A Robotic Multimodal Perception-Planning Framework with Multimodal Large Language Models

Understanding the Forgetting of (Replay-based) Continual Learning via Feature Learning: Angle Matters

Addressing Multi-Label Learning with Partial Labels: From Sample Selection to Label Selection

Comprehensive Knowledge Distillation with Causal Intervention

Personalized Education: Blind Knowledge Distillation

Embodied Crowd Counting