4 papers
LiveMem: Maintaining Memory State Continuity in Long-Running LLM Inference
Zhichen Liu, Ruihan Sun, Hengjie Yang +4
Long-running assistants and agents consume interaction streams that eventually outgrow the context. Existing context retention, summarization, and retrieval preserve access to sele…
MICA: Multi-granularity Intertemporal Credit Assignment for Long-Horizon Emotional Support Dialogue
Naifan Zhang, Ruihan Sun, Jinwei Su +4
Reinforcement learning (RL) for large language models (LLMs) has shown strong performance in single-turn tasks, but extending it to multi-turn interaction remains challenging due t…
Echo-N1: Affective RL Frontier
Naifan Zhang, Ruihan Sun, Ruixi Su +9
The LLM field has spent a year perfecting RL for tasks machines already excel at, math, code, and deterministic reasoning, while completely sidestepping the domain that actually de…
SFOOD: A Multimodal Benchmark for Comprehensive Food Attribute Analysis Beyond RGB with Spectral Insights
Zhenbo Xu, Jinghan Yang, Gong Huang +6
With the rise and development of computer vision and LLMs, intelligence is everywhere, especially for people and cars. However, for tremendous food attributes (such as origin, quan…