5 papers
FlowPortrait: Reinforcement Learning for Audio-Driven Portrait Video Generation
Weiting Tan, Andy T. Liu, Ming Tu +3
Generating realistic talking-head videos remains challenging due to persistent issues such as imperfect lip synchronization, unnatural motion, and evaluation metrics that correlate…
Process-Supervised Reinforcement Learning for Interactive Multimodal Tool-Use Agents
Weiting Tan, Xinghua Qu, Ming Tu +4
Effective interactive tool use requires agents to master Tool Integrated Reasoning (TIR): a complex process involving multi-turn planning and long-context dialogue management. To t…
Streaming Sequence Transduction through Dynamic Compression
Weiting Tan, Yunmo Chen, Tongfei Chen +5
We introduce STAR (Stream Transduction with Anchor Representations), a novel Transformer-based model designed for efficient sequence-to-sequence transduction over streams. STAR dyn…
SSR: Alignment-Aware Modality Connector for Speech Language Models
Weiting Tan, Hirofumi Inaguma, Ning Dong +2
Fusing speech into pre-trained language model (SpeechLM) usually suffers from inefficient encoding of long-form speech and catastrophic forgetting of pre-trained text modality. We…
Upsample or Upweight? Balanced Training on Heavily Imbalanced Datasets
Tianjian Li, Haoran Xu, Weiting Tan +2
Data abundance across different domains exhibits a long-tailed distribution: few domains have abundant data, while most face data scarcity. Our work focuses on a multilingual setti…