3 papers
cs.CV2026
STEAR: Layer-Aware Spatiotemporal Evidence Intervention for Hallucination Mitigation in Video Large Language Models
Linfeng Fan, Yuan Tian, Ziwei Li +1
Video Large Language Models (Video-LLMs) remain prone to spatiotemporal hallucinations, often generating visually unsupported details or incorrect temporal relations. Existing miti…
cs.DC2025
Lazarus: Resilient and Elastic Training of Mixture-of-Experts Models
Yongji Wu, Wenjie Qu, Xueshen Liu +10
Sparsely-activated Mixture-of-Experts (MoE) architecture has increasingly been adopted to further scale large language models (LLMs). However, frequent failures still pose signific…
cs.CR2025
VulBinLLM: LLM-powered Vulnerability Detection for Stripped Binaries
Nasir Hussain, Haohan Chen, Chanh Tran +6
Recognizing vulnerabilities in stripped binary files presents a significant challenge in software security. Although some progress has been made in generating human-readable inform…