Hao Zhang
- Alleviating Hallucinations in Large Language Models through Multi-Model Contrastive Decoding and Dynamic Hallucination Detection
- Efficiently Scaling LLM Reasoning Programs with Certaindex
- Faster Video Diffusion with Trainable Sparse Attention
- Local Learning for Covariate Selection in Nonparametric Causal Effect Estimation with Latent Variables
- MoPFormer: Motion-Primitive Transformer for Wearable-Sensor Activity Recognition
- Projection-Manifold Regularized Latent Diffusion for Robust General Image Fusion
- RESAnything: Attribute Prompting for Arbitrary Referring Segmentation
- RGB-Only Supervised Camera Parameter Optimization in Dynamic Scenes
- SAMA: Towards Multi-Turn Referential Grounded Video Chat with Large Language Models
- Scaling Language-centric Omnimodal Representation Learning
- Scaling Speculative Decoding with Lookahead Reasoning
- Stable Part Diffusion 4D: Multi-View RGB and Kinematic Parts Video Generation