collaborators
Showing cs.AIShow all

5 papers · 1 filter

cs.AI2026

Who Bridges Safety? Identifying and Targeting Cross-Lingual Shared Safety Pathways

Shuyi Miao, Wangjie Qiu, Pengyang Shao +4

Uncovering the internal mechanisms underlying the safety capabilities of large language models (LLMs) is crucial for developing trustworthy artificial intelligence. Currently, mech…

cs.AI2026

Hidden APIs in Language Models: Discovering Reusable Causal Interfaces from Forked Futures

SiYuan Ma, Yiqin Luo, Zhangji +8

Identical language-model answers can arise from hidden states that support different future computations, so current-answer probes do not establish a reusable internal interface. W…

cs.AI2026

Hidden Forgetting in Continual Multimodal Learning: When Accuracy Survives but Grounding Fails

Qianyu Chen, Canran Xiao, Runxuan Tang

Multimodal large language models must continually adapt to evolving tasks and domains, yet standard continual learning metrics mainly measure whether old answers remain correct, le…

cs.AI2026

InduceKV: Fixed-Footprint Continual Adaptation of Multimodal LLMs via Inducing KV Memories

Qianyu Chen, Ziteng Feng, Canran Xiao +1

Multimodal large language models must adapt to evolving tasks and domains, yet continual improvement under bounded deployment footprint remains difficult because repeated parameter…

cs.AI2026

Seeing through the Conflict: Transparent Knowledge Conflict Handling in Retrieval-Augmented Generation

Hua Ye, Siyuan Chen, Ziqi Zhong +4

Large language models (LLMs) equipped with retrieval--the Retrieval-Augmented Generation (RAG) paradigm--should combine their parametric knowledge with external evidence, yet in pr…