activity
20242026
collaborators

11 papers

cs.CV2026

Query-Conditioned Evidential Keyframe Sampling for MLLM-Based Long-Form Video Understanding

Yiheng Wang, Lichen Zhu, Yueqian Lin +4

Multimodal Large Language Models (MLLMs) have shown strong performance on video question answering, but their application to long-form videos is constrained by limited context leng…

cs.LG2026

MUSE: A Run-Centric Platform for Multimodal Unified Safety Evaluation of Large Language Models

Zhongxi Wang, Yueqian Lin, Jingyang Zhang +2

Safety evaluation and red-teaming of large language models remain predominantly text-centric, and existing frameworks lack the infrastructure to systematically test whether alignme…

cs.LG2025

SADA: Stability-guided Adaptive Diffusion Acceleration

Ting Jiang, Yixiao Wang, Hancheng Ye +7

Diffusion models have achieved remarkable success in generative tasks but suffer from high computational costs due to their iterative sampling process and quadratic attention costs…

cs.MA2025

Which Agent Causes Task Failures and When? On Automated Failure Attribution of LLM Multi-Agent Systems

Shaokun Zhang, Ming Yin, Jieyu Zhang +8

Failure attribution in LLM multi-agent systems-identifying the agent and step responsible for task failures-provides crucial clues for systems debugging but remains underexplored a…

cs.CR2025

LoBAM: LoRA-Based Backdoor Attack on Model Merging

Ming Yin, Jingyang Zhang, Jingwei Sun +3

Model merging is an emerging technique that integrates multiple models fine-tuned on different tasks to create a versatile model that excels in multiple domains. This scheme, in th…

cs.AR2025

Phi: Leveraging Pattern-based Hierarchical Sparsity for High-Efficiency Spiking Neural Networks

Chiyue Wei, Bowen Duan, Cong Guo +4

Spiking Neural Networks (SNNs) are gaining attention for their energy efficiency and biological plausibility, utilizing 0-1 activation sparsity through spike-driven computation. Wh…