Hao Zhou

42

Papers

431

Total Citations

Papers (42)

Large Language Models Are Not Robust Multiple Choice Selectors

Unified Generative Modeling of 3D Molecules with Bayesian Flow Networks

Hypothesis Testing in Unsupervised Domain Adaptation with Applications in Alzheimer's Disease

Open-Vocabulary 3D Semantic Segmentation with Text-to-Image Diffusion Models

Steering Protein Family Design through Profile Bayesian Flow

Smooth Interpolation for Improved Discrete Graph Generative Models

MoE-LPR: Multilingual Extension of Large Language Models Through Mixture-of-Experts with Language Priors Routing

Empower Structure-Based Molecule Optimization with Gradient Guided Bayesian Flow Networks

MolCRAFT: Structure-Based Drug Design in Continuous Parameter Space

Reducing Balancing Error for Causal Inference via Optimal Transport

On Prompt-Driven Safeguarding for Large Language Models

Variance-reduced Zeroth-Order Methods for Fine-Tuning Language Models

Collage: Light-Weight Low-Precision Strategy for LLM Training

Mol-AE: Auto-Encoder Based Molecular Representation Learning With 3D Cloze Test Objective

ESM All-Atom: Multi-Scale Protein Language Model for Unified Molecular Modeling

VideoPrism: A Foundational Visual Encoder for Video Understanding

Label Denoising Adversarial Network (LDAN) for Inverse Lighting of Faces

Where, What, Whether: Multi-Modal Learning Meets Pedestrian Detection

SharinGAN: Combining Synthetic and Real Data for Unsupervised Geometry Estimation

Improving Sign Language Translation With Monolingual Data by Sign Back-Translation

Embracing Uncertainty: Decoupling and De-Bias for Robust Temporal Grounding

Change3D: Revisiting Change Detection and Captioning from A Video Modeling Perspective

Deep Single-Image Portrait Relighting

GLoSH: Global-Local Spherical Harmonics for Intrinsic Image Decomposition

Sign Language Translation with Iterative Prototype

Out-of-Distribution Identification: Let Detector Tell Which I Am Not Sure

PSS: Progressive Sample Selection for Open-World Visual Representation Learning

Towards Regression-Free Neural Networks for Diverse Compute Platforms

Compatibility-Aware Heterogeneous Visual Search

Erase Diffusion: Empowering Object Removal Through Calibrating Diffusion Pathways

Hints of Prompt: Enhancing Visual Representation for Multimodal LLMs in Autonomous Driving

HRScene: How Far Are VLMs from Effective High-Resolution Image Understanding?

CO2-Net: A Physics-Informed Spatio-Temporal Model for Global Surface CO2 Reconstruction

Core-to-Global Reasoning for Compositional Visual Question Answering

BRITS: Bidirectional Recurrent Imputation for Time Series

Kernelized Bayesian Softmax for Text Generation

Duplex Sequence-to-Sequence Learning for Reversible Machine Translation

Regularized Molecular Conformation Fields

Zero-Shot 3D Drug Design by Sketching and Generating

Equivariant Flow Matching with Hybrid Probability Transport for 3D Molecule Generation

HAP: Structure-Aware Masked Image Modeling for Human-Centric Perception

Fed-FA: Theoretically Modeling Client Data Divergence for Federated Language Backdoor Defense