5 papers
Heterogeneous Co-Evolution Learning for Tool-Efficient Search Agents with Zero Labels
Qin-Wen Luo, Sheng Ren, Xiang Chen +6
Deep search agents extend language models by interleaving reasoning with external retrieval. However, effective search-agent training requires addressing two challenges beyond fina…
Phoenix TTS: High-Fidelity Synthesis and Voice Conversion via Flow-Matching-Driven Speech Tokenization
Peijie Chen, Zhuanling Zha, Zhipeng Nie +8
In current zero-shot text-to-speech systems, conventional semantic tokenizers are typically optimized using supervised automatic speech recognition or self-supervised learning obje…
Darwinian Memory: A Training-Free Self-Regulating Memory System for GUI Agent Evolution
Hongze Mi, Yibo Feng, WenJie Lu +11
Multimodal Large Language Model (MLLM) agents facilitate Graphical User Interface (GUI) automation but struggle with long-horizon, cross-application tasks due to limited context wi…
DiMA: An LLM-Powered Ride-Hailing Assistant at DiDi
Yansong Ning, Shuowei Cai, Wei Li +4
On-demand ride-hailing services like DiDi, Uber, and Lyft have transformed urban transportation, offering unmatched convenience and flexibility. In this paper, we introduce DiMA, a…
GRASS: Unified Generation Model for Speech-to-Semantic Tasks
Aobo Xia, Shuyu Lei, Yushu Yang +2
This paper explores the instruction fine-tuning technique for speech-to-semantic tasks by introducing a unified end-to-end (E2E) framework that generates target text conditioned on…