11 papers
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…
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…
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…
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…
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…
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…