papers

Publications (10)

cs.CL2024

LEMMA: Towards LVLM-Enhanced Multimodal Misinformation Detection with External Knowledge Augmentation

Keyang Xuan, Li Yi, Fan Yang +3

The rise of multimodal misinformation on social platforms poses significant challenges for individuals and societies. Its increased credibility and broader impact compared to textu…

cs.CL2025

TinyScientist: An Interactive, Extensible, and Controllable Framework for Building Research Agents

Haofei Yu, Keyang Xuan, Fenghai Li +6

Automatic research with Large Language Models (LLMs) is rapidly gaining importance, driving the development of increasingly complex workflows involving multi-agent systems, plannin…

cs.CL2025

ResearchTown: Simulator of Human Research Community

Haofei Yu, Zhaochen Hong, Zirui Cheng +5

Large Language Models (LLMs) have demonstrated remarkable potential in scientific domains, yet a fundamental question remains unanswered: Can we simulate human research communities…

cs.AI2026

Steer2Adapt: Dynamically Composing Steering Vectors Elicits Efficient Adaptation of LLMs

Pengrui Han, Xueqiang Xu, Keyang Xuan +12

Activation steering has emerged as a promising approach for efficiently adapting large language models (LLMs) to downstream behaviors. However, most existing steering methods rely…

cs.CR2024

APILOT: Navigating Large Language Models to Generate Secure Code by Sidestepping Outdated API Pitfalls

Weiheng Bai, Keyang Xuan, Pengxiang Huang +4

With the rapid development of large language models (LLMs), their applications have expanded into diverse fields, such as code assistance. However, the substantial size of LLMs mak…

cs.AI2026

Interactive Evaluation Requires a Design Science

Keyang Xuan, Peiyang Song, Pan Lu +10

AI evaluation is undergoing a structural change. Large language models (LLMs) are increasingly deployed as systems that act over time through tools, environments, users, and other…

cs.CV2025

TAMP: Token-Adaptive Layerwise Pruning in Multimodal Large Language Models

Jaewoo Lee, Keyang Xuan, Chanakya Ekbote +3

Multimodal Large Language Models (MLLMs) have shown remarkable versatility in understanding diverse multimodal data and tasks. However, these capabilities come with an increased mo…

cs.LG2022

Spatiotemporal Classification with limited labels using Constrained Clustering for large datasets

Praveen Ravirathinam, Rahul Ghosh, Ke Wang +5

Creating separable representations via representation learning and clustering is critical in analyzing large unstructured datasets with only a few labels. Separable representations…

cs.CL2025

Sotopia-RL: Reward Design for Social Intelligence

Haofei Yu, Zhengyang Qi, Yining Zhao +6

Social intelligence has become a critical capability for large language models (LLMs), enabling them to engage effectively in real-world social tasks such as collaboration and nego…

cs.AI2026

SocialVeil: Probing Social Intelligence of Language Agents under Communication Barriers

Keyang Xuan, Pengda Wang, Chongrui Ye +3

Large language models (LLMs) are increasingly evaluated in interactive environments to test their social intelligence. However, existing benchmarks often assume idealized communica…