1 citations · 1 across the 8 of their papers we have counts for
7 papers · 1 filter
Tracing a Sparse Emotion-Control Circuit in LLM-Based Text-to-Speech
Hongfei Du, Jiacheng Shi, Yanfu Zhang +1
LLM-based text-to-speech (TTS) models can generate emotionally expressive speech, but how reference emotion is routed through the model and realized in decoded speech remains uncle…
Usage-Modulated Sentiment Representations in Large Language Models
Hongfei Du, Jiacheng Shi, Yanfu Zhang +2
Prior work suggests that sentiment can often be captured by approximately linear directions in LLM activation spaces, but a single direction may not fully capture sentiment represe…
EgoMonth: A Month-Level Egocentric Video Benchmark for Long-Term Spatiotemporal Memory
Weitao Chen, Hu Jiaxin, Xie Tianyidan +15
Recent advances in Multimodal Large Language Models (MLLMs) have led to substantial progress in video understanding, accompanied by a growing number of long video benchmarks. Howev…
DocPO: Advancing Document Policy Optimization via Tailored Step-Aware Rewards
Yunhao Wang, Binghong Wu, Zhenyu Huang +4
Reinforcement learning (RL) for document parsing often relies on reference-based rewards rooted in edit distance (e.g., tree edit distance), yet it remains hard to optimize in the…
Sparse Autoencoders for Interpretable Emotion Control in Text-to-Speech
Hongfei Du, Jiacheng Shi, Sidi Lu +2
Integrating large language models (LLMs) into text-to-speech (TTS) systems has improved speech expressiveness, yet interpretable emotional control remains challenging. Existing app…
Hy-MT2: A Family of Fast, Efficient and Powerful Multilingual Translation Models in the Wild
Mao Zheng, Zheng Li, Tao Chen +10
Hy-MT2 is a family of fast-thinking multilingual translation models designed for complex real-world scenarios. It includes three model sizes: 1.8B, 7B, and 30B-A3B (MoE), all of wh…
AffectCodec: Emotion-Preserving Neural Speech Codec for Expressive Speech Modeling
Jiacheng Shi, Hongfei Du, Xinyuan Song +3
Neural speech codecs provide discrete representations for speech language models, but emotional cues are often degraded during quantization. Existing codecs mainly optimize acousti…