Hao Sun

Affiliations

University of Cambridge

papers

523

total citations

papers (23)

A Neural Corpus Indexer for Document Retrieval

NEURIPS 2022arXiv

185

citations

TR-DETR: Task-Reciprocal Transformer for Joint Moment Retrieval and Highlight Detection

AAAI 2024arXiv

citations

Bayesian Spline Learning for Equation Discovery of Nonlinear Dynamics with Quantified Uncertainty

NEURIPS 2022arXiv

citations

MTL-LoRA: Low-Rank Adaptation for Multi-Task Learning

AAAI 2025arXiv

citations

Accountability in Offline Reinforcement Learning: Explaining Decisions with a Corpus of Examples

NEURIPS 2023arXiv

citations

Model-enhanced Vector Index

NEURIPS 2023arXiv

citations

SpotActor: Training-Free Layout-Controlled Consistent Image Generation

AAAI 2025arXiv

citations

What is Flagged in Uncertainty Quantification? Latent Density Models for Uncertainty Categorization

NEURIPS 2023arXiv

citations

A Token-level Text Image Foundation Model for Document Understanding

ICCV 2025arXiv

citations

SAUI: Scale-Aware Unseen Imagineer for Zero-Shot Object Detection

AAAI 2024

citations

The Synergy of LLMs & RL Unlocks Offline Learning of Generalizable Language-Conditioned Policies with Low-fidelity Data

ICML 2025arXiv

citations

EyEar: Learning Audio Synchronized Human Gaze Trajectory Based on Physics-Informed Dynamics

AAAI 2025arXiv

citations

A Set of Generalized Components to Achieve Effective Poison-only Clean-label Backdoor Attacks with Collaborative Sample Selection and Triggers

NEURIPS 2025arXiv

citations

HHAN: Comprehensive Infectious Disease Source Tracing via Heterogeneous Hypergraph Neural Network

AAAI 2025

citations

VL-Match: Enhancing Vision-Language Pretraining with Token-Level and Instance-Level Matching

ICCV 2023

citations

Exploit Reward Shifting in Value-Based Deep-RL: Optimistic Curiosity-Based Exploration and Conservative Exploitation via Linear Reward Shaping

NEURIPS 2022

citations

A Comprehensive Study on Text-attributed Graphs: Benchmarking and Rethinking

NEURIPS 2023

citations

Chain of Semantics Programming in 3D Gaussian Splatting Representation for 3D Vision Grounding

CVPR 2025

citations

LiDAR-Net: A Real-scanned 3D Point Cloud Dataset for Indoor Scenes

CVPR 2024

citations

Hao Sun

Affiliations

papers (23)

A Neural Corpus Indexer for Document Retrieval

TR-DETR: Task-Reciprocal Transformer for Joint Moment Retrieval and Highlight Detection

Reciprocal Learning Networks for Human Trajectory Prediction

Dense Reward for Free in Reinforcement Learning from Human Feedback

Stare at What You See: Masked Image Modeling Without Reconstruction

Trusted Unified Feature-Neighborhood Dynamics for Multi-View Classification

Bayesian Spline Learning for Equation Discovery of Nonlinear Dynamics with Quantified Uncertainty

MTL-LoRA: Low-Rank Adaptation for Multi-Task Learning

Accountability in Offline Reinforcement Learning: Explaining Decisions with a Corpus of Examples

Model-enhanced Vector Index

SpotActor: Training-Free Layout-Controlled Consistent Image Generation

What is Flagged in Uncertainty Quantification? Latent Density Models for Uncertainty Categorization

A Token-level Text Image Foundation Model for Document Understanding

SAUI: Scale-Aware Unseen Imagineer for Zero-Shot Object Detection

The Synergy of LLMs & RL Unlocks Offline Learning of Generalizable Language-Conditioned Policies with Low-fidelity Data

EyEar: Learning Audio Synchronized Human Gaze Trajectory Based on Physics-Informed Dynamics

A Set of Generalized Components to Achieve Effective Poison-only Clean-label Backdoor Attacks with Collaborative Sample Selection and Triggers

HHAN: Comprehensive Infectious Disease Source Tracing via Heterogeneous Hypergraph Neural Network

VL-Match: Enhancing Vision-Language Pretraining with Token-Level and Instance-Level Matching

Exploit Reward Shifting in Value-Based Deep-RL: Optimistic Curiosity-Based Exploration and Conservative Exploitation via Linear Reward Shaping

A Comprehensive Study on Text-attributed Graphs: Benchmarking and Rethinking

Chain of Semantics Programming in 3D Gaussian Splatting Representation for 3D Vision Grounding

LiDAR-Net: A Real-scanned 3D Point Cloud Dataset for Indoor Scenes

papers (23)

A Neural Corpus Indexer for Document Retrieval

TR-DETR: Task-Reciprocal Transformer for Joint Moment Retrieval and Highlight Detection

Reciprocal Learning Networks for Human Trajectory Prediction

Dense Reward for Free in Reinforcement Learning from Human Feedback

Stare at What You See: Masked Image Modeling Without Reconstruction

Trusted Unified Feature-Neighborhood Dynamics for Multi-View Classification

Bayesian Spline Learning for Equation Discovery of Nonlinear Dynamics with Quantified Uncertainty

MTL-LoRA: Low-Rank Adaptation for Multi-Task Learning

Accountability in Offline Reinforcement Learning: Explaining Decisions with a Corpus of Examples

Model-enhanced Vector Index

SpotActor: Training-Free Layout-Controlled Consistent Image Generation

What is Flagged in Uncertainty Quantification? Latent Density Models for Uncertainty Categorization

A Token-level Text Image Foundation Model for Document Understanding

SAUI: Scale-Aware Unseen Imagineer for Zero-Shot Object Detection

The Synergy of LLMs & RL Unlocks Offline Learning of Generalizable Language-Conditioned Policies with Low-fidelity Data

EyEar: Learning Audio Synchronized Human Gaze Trajectory Based on Physics-Informed Dynamics

A Set of Generalized Components to Achieve Effective Poison-only Clean-label Backdoor Attacks with Collaborative Sample Selection and Triggers

HHAN: Comprehensive Infectious Disease Source Tracing via Heterogeneous Hypergraph Neural Network

VL-Match: Enhancing Vision-Language Pretraining with Token-Level and Instance-Level Matching

Exploit Reward Shifting in Value-Based Deep-RL: Optimistic Curiosity-Based Exploration and Conservative Exploitation via Linear Reward Shaping

A Comprehensive Study on Text-attributed Graphs: Benchmarking and Rethinking

Chain of Semantics Programming in 3D Gaussian Splatting Representation for 3D Vision Grounding

LiDAR-Net: A Real-scanned 3D Point Cloud Dataset for Indoor Scenes