7 papers
Free energy and spectral edge of the SYK model
Yukun He
We introduce a microscopic framework that gives the first rigorous derivation of the Schwinger--Dyson thermodynamics of the Sachdev--Ye--Kitaev model. For fixed, even interaction o…
APeB: Benchmarking Personalization Ability of Large Language Model Agents
Garry Yang, Zizhe Chen, Xinru Chen +9
LLM-powered agents struggle with personalization when users issue raw, underspecified queries. In this setting, agents must infer latent intent, extract preferences from noisy inte…
VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding
Xinhao Li, Yuhan Zhu, Xiangyu Zeng +24
Recent advances in video understanding have spanned motion, long video, and streaming interaction, driving this field toward real-world applications. Despite this progress, current…
ReasFlow: Assisting Reasoning-Centric Scientific Discovery in Applied Mathematics via a Knowledge-Based Multi-Agent System
Yutong He, Daibo Li, Guohong Li +15
Recent advances in Large Language Models have fueled autonomous AI agents capable of tackling complex scientific tasks, yet existing automated research systems remain predominantly…
Hierarchical Acoustic-Semantic Modeling: Modality Separation and Semantic Coherence for Full-Duplex SLMs
Zhenyu Liu, Xuanyu Zhang, Yunxin Li +10
Developing seamless, high-performance, native intelligent full-duplex Spoken Language Models (SLMs) remains a critical challenge and long-standing goal for the speech and NLP commu…
A General Exposure-Mapping-Agnostic Framework for Causal Inference under Interference
Yihui He, Eric J. Tchetgen Tchetgen
We develop a general framework for design-based causal inference under interference in cluster experiments conducted via two-stage randomization on a network of interconnected unit…