Tong Zhang

28

Papers

157

Total Citations

Papers (28)

PerceptionGPT: Effectively Fusing Visual Perception into LLM

ASGO: Adaptive Structured Gradient Optimization

NeurIPS 2025arXiv

AdaGrad under Anisotropic Smoothness

MergeBench: A Benchmark for Merging Domain-Specialized LLMs

NeurIPS 2025arXiv

Data Augmentation via Latent Diffusion for Saliency Prediction

Accelerated Convergence of Stochastic Heavy Ball Method under Anisotropic Gradient Noise

Refining CLIP's Spatial Awareness: A Visual-Centric Perspective

Generating Multimodal Driving Scenes via Next-Scene Prediction

TagFog: Textual Anchor Guidance and Fake Outlier Generation for Visual Out-of-Distribution Detection

FDS: Frequency-Aware Denoising Score for Text-Guided Latent Diffusion Image Editing

Rotated Runtime Smooth: Training-Free Activation Smoother for accurate INT4 inference

Faster Sampling via Stochastic Gradient Proximal Sampler

Self-Ensembling Gaussian Splatting for Few-Shot Novel View Synthesis

Controlling the Fidelity and Diversity of Deep Generative Models via Pseudo Density

Understanding Overadaptation in Supervised Fine-Tuning: The Role of Ensemble Methods

Iterative Preference Learning from Human Feedback: Bridging Theory and Practice for RLHF under KL-constraint

Distribution Prototype Diffusion Learning for Open-set Supervised Anomaly Detection

TimeBooth: Disentangled Facial Invariant Representation for Diverse and Personalized Face Aging

MatchDiffusion: Training-free Generation of Match-Cuts

Scene Graph-Grounded Image Generation

Desigen: A Pipeline for Controllable Design Template Generation

InNeRF360: Text-Guided 3D-Consistent Object Inpainting on 360-degree Neural Radiance Fields

DVMNet: Computing Relative Pose for Unseen Objects Beyond Hypotheses

Mitigating Object Dependencies: Improving Point Cloud Self-Supervised Learning through Object Exchange

The Non-linear $F$-Design and Applications to Interactive Learning

Towards Robust Model-Based Reinforcement Learning Against Adversarial Corruption

Pessimism Meets Risk: Risk-Sensitive Offline Reinforcement Learning

Scaling Mesh Generation via Compressive Tokenization