collaborators

5 papers

cs.LG2026

Reinforcement Learning via Value Gradient Flow

Haoran Xu, Kaiwen Hu, Somayeh Sojoudi +1

We study behavior-regularized reinforcement learning (RL), where regularization toward a reference distribution (the dataset in offline RL or the base model in LLM RL finetuning) i…

cs.AI2026

Beyond Monologue: Interactive Talking-Listening Avatar Generation with Conversational Audio Context-Aware Kernels

Yuzhe Weng, Haotian Wang, Xinyi Yu +4

Audio-driven human video generation has achieved remarkable success in monologue scenarios, largely driven by advancements in powerful video generation foundation models. Moving be…

cs.CV2026

EARTalking: End-to-end GPT-style Autoregressive Talking Head Synthesis with Frame-wise Control

Yuzhe Weng, Haotian Wang, Yuanhong Yu +4

Audio-driven talking head generation aims to create vivid and realistic videos from a static portrait and speech. Existing AR-based methods rely on intermediate facial representati…

cs.CV2026

REST: Diffusion-based Real-time End-to-end Streaming Talking Head Generation via ID-Context Caching and Asynchronous Streaming Distillation

Haotian Wang, Yuzhe Weng, Jun Du +6

Diffusion models have significantly advanced the field of talking head generation (THG). However, slow inference speeds and prevalent non-autoregressive paradigms severely constrai…

cs.GR2025

READ: Real-time and Efficient Asynchronous Diffusion for Audio-driven Talking Head Generation

Haotian Wang, Yuzhe Weng, Jun Du +7

The introduction of diffusion models has brought significant advances to the field of audio-driven talking head generation. However, the extremely slow inference speed severely lim…