activity
20242026
collaborators

12 papers

cs.AI2026

Listen, See and Track: Spatio-Temporal Audio-Visual Sound Event Reasoning for Omni-Modal Language Models

Zhi Zeng, Cheng Zhang, Zesheng Yang +9

Understanding dynamic sound sources requires jointly determining what produces a sound, where the source is located, and how it moves over time. Yet existing audio-language models…

cs.CL2026

Why Knowing Both Hops Is Not Enough: Understanding Two-Hop Generalization in Language Models

Zili Zhang, Yilin Wang, Heng Wang +2

Large language models (LLMs) can solve complex multi-hop problems yet exhibit puzzling failures on simple two-hop queries: although a model may correctly store each individual hop,…

cs.CL2026

The Deliberative Illusion: Diagnosing Factual Attrition and Stance Homogenization in Multi-Agent LLM Deliberation

Herun Wan, Jiaying Wu, Minnan Luo +4

Multi-agent LLM systems often treat consensus as evidence of successful interaction. For deliberative problems, however, reliability depends on whether agents preserve the facts an…

cs.SI2026

From Manipulation to Mistrust: Explaining Diverse Micro-Video Misinformation for Robust Debunking in the Wild

Zhi Zeng, Yifei Yang, Jiaying Wu +5

The rise of micro-videos has reshaped how misinformation spreads, amplifying its speed, reach, and impact on public trust. Existing benchmarks typically focus on a single deception…

cs.CL2026

Bot Meets Shortcut: How Can LLMs Aid in Handling Unknown Invariance OOD Scenarios?

Shiyan Zheng, Herun Wan, Minnan Luo +1

While existing social bot detectors perform well on benchmarks, their robustness across diverse real-world scenarios remains limited due to unclear ground truth and varied misleadi…

cs.CL2026

The Facade of Truth: Uncovering and Mitigating LLM Susceptibility to Deceptive Evidence

Herun Wan, Jiaying Wu, Minnan Luo +3

To reliably assist human decision-making, LLMs must maintain factual internal beliefs against misleading injections. While current models resist explicit misinformation, we uncover…