Jun Zhou

20

Papers

306

Total Citations

Papers (20)

DNGaussian: Optimizing Sparse-View 3D Gaussian Radiance Fields with Global-Local Depth Normalization

STAR: Spatial-Temporal Augmentation with Text-to-Video Models for Real-World Video Super-Resolution

FireEdit: Fine-grained Instruction-based Image Editing via Region-aware Vision Language Model

Audio-visual Controlled Video Diffusion with Masked Selective State Spaces Modeling for Natural Talking Head Generation

Effective and Efficient Masked Image Generation Models

Backdoor Adjustment via Group Adaptation for Debiased Coupon Recommendations

SAM-R1: Leveraging SAM for Reward Feedback in Multimodal Segmentation via Reinforcement Learning

Improving Natural Language Understanding for LLMs via Large-Scale Instruction Synthesis

Structural Information Enhanced Graph Representation for Link Prediction

GMP-AR: Granularity Message Passing and Adaptive Reconciliation for Temporal Hierarchy Forecasting

LLMRG: Improving Recommendations through Large Language Model Reasoning Graphs

FC-GNN: Recovering Reliable and Accurate Correspondences from Interferences

Learning Causal Transition Matrix for Instance-dependent Label Noise

InsTaG: Learning Personalized 3D Talking Head from Few-Second Video

Hunyuan-Portrait: Implicit Condition Control for Enhanced Portrait Animation

HeMeNet: Heterogeneous Multichannel Equivariant Network for Protein Multi-task Learning

Making Large Vision Language Models to Be Good Few-Shot Learners

CREST: An Efficient Conjointly-trained Spike-driven Framework for Event-based Object Detection Exploiting Spatiotemporal Dynamics

SATA: Spatial Autocorrelation Token Analysis for Enhancing the Robustness of Vision Transformers

Explore What LLM Does Not Know in Complex Question Answering