activity
20242026
collaborators

7 papers

cs.AI2026

The Low Frequency Trap: Video Language Models Fail at Simple Event Bookkeeping

Sarvesh Baskar, Zikui Cai, Shayan Shabihi +5

Real-world video benchmarks provide broad coverage, but their fixed clips entangle event count, rate, duration, and visual complexity, making failure modes hard to isolate. While e…

cs.RO2026

Beyond Episodic Evaluation: Memory Architectural Bottlenecks in Sequential Embodied Question Answering

Zikui Cai, Kaushal Janga, Tan Dat Dao +15

Embodied question answering (EQA) is traditionally evaluated under an episodic formulation, where agents solve each task independently and reset internal state between episodes. Ho…

cs.CV2025

Zebra-CoT: A Dataset for Interleaved Vision Language Reasoning

Ang Li, Charles Wang, Deqing Fu +9

Humans often use visual aids, for example diagrams or sketches, when solving complex problems. Training multimodal models to do the same, known as Visual Chain of Thought (Visual C…

cs.LG2025

AegisLLM: Scaling Agentic Systems for Self-Reflective Defense in LLM Security

Zikui Cai, Shayan Shabihi, Bang An +5

We introduce AegisLLM, a cooperative multi-agent defense against adversarial attacks and information leakage. In AegisLLM, a structured workflow of autonomous agents - orchestrator…

cs.CV2025

MORSE-500: A Programmatically Controllable Video Benchmark to Stress-Test Multimodal Reasoning

Zikui Cai, Andrew Wang, Anirudh Satheesh +10

Despite rapid advances in vision-language models (VLMs), current benchmarks for multimodal reasoning fall short in three key dimensions. First, they overwhelmingly rely on static i…

cs.LG2025

Can Watermarking Large Language Models Prevent Copyrighted Text Generation and Hide Training Data?

Michael-Andrei Panaitescu-Liess, Zora Che, Bang An +6

Large Language Models (LLMs) have demonstrated impressive capabilities in generating diverse and contextually rich text. However, concerns regarding copyright infringement arise as…