collaborators

8 papers

cs.CL2026

LLMs Encode Harmfulness and Refusal Separately

Jiachen Zhao, Jing Huang, Zhengxuan Wu +2

LLMs are trained to refuse harmful instructions, but do they truly understand harmfulness beyond just refusing? Prior work has shown that LLMs' refusal behaviors can be mediated by…

cs.CR2026

Unsafer in Many Turns: Benchmarking and Defending Multi-Turn Safety Risks in Tool-Using Agents

Xu Li, Simon Yu, Minzhou Pan +5

LLM-based agents are becoming increasingly capable, yet their safety lags behind. This creates a gap between what agents can do and should do. This gap widens as agents engage in m…

cs.LG2026

Can Aha Moments Be Fake? Towards Quantifying Decorative and True Thinking in Chain-of-Thought

Jiachen Zhao, Yiyou Sun, Weiyan Shi +1

Large language models can generate long chain-of-thought (CoT) reasoning, yet prior work suggests that CoT can be post-hoc rationalization rather than a faithful reflection of the…

cs.CL2026

ConvApparel: A Benchmark Dataset and Validation Framework for User Simulators in Conversational Recommenders

Ofer Meshi, Krisztian Balog, Sally Goldman +5

The promise of LLM-based user simulators to improve conversational AI is hindered by a critical "realism gap," leading to systems that are optimized for simulated interactions, but…

cs.CL2026

Open-Source Multimodal Moxin Models with Moxin-VLM and Moxin-VLA

Pu Zhao, Arash Akbari, Xuan Shen +16

Recently, Large Language Models (LLMs) have undergone a significant transformation, marked by a rapid rise in both their popularity and capabilities. Leading this evolution are pro…

cs.CV2026

SocialFusion: Addressing Social Degradation in Pre-trained Vision-Language Models

Hamza Tahboub, Weiyan Shi, Gang Hua +1

Understanding social interactions from visual cues is a fundamental challenge for a socially competent AI. While powerful pre-trained vision-language models (VLMs) have shown remar…