5 papers
KnowHal: A Knowledge-Driven Benchmark for Comprehensive Multimodal Hallucination Evaluation
Ruihan Li, Jiyang Tan, Kailin Jiang +5
Hallucination remains a critical challenge for developing trustworthy Multimodal Large Language Models (MLLMs). While existing benchmarks mainly focus on entity, attribute, and rel…
AgenticVAU: Multi-Agent Explore-Verify Reasoning for Video Anomaly Understanding
Yuxiang Duan, Huining Li, Ao Li +6
Video anomaly understanding (VAU) focuses on comprehensively interpreting abnormal events in videos, requiring models to identify anomalous occurrences, discover their supporting e…
Delineating Knowledge Boundaries for Honest Large Vision-Language Models
Junru Song, Yimeng Hu, Yijing Chen +4
Large Vision-Language Models (VLMs) have achieved remarkable multimodal performance yet remain prone to factual hallucinations, particularly in long-tail or specialized domains. Mo…
Unlocking the Address Book: Dissecting the Sparse Semantic Structure of LLM Key-Value Caches via Sparse Autoencoders
Qingsen Ma, Dianyun Wang, Jiaming Lyu +8
The Key-Value (KV) cache is the primary memory bottleneck in long-context Large Language Models, yet it is typically treated as an opaque numerical tensor. In this work, we propose…
Stroke2Sketch: Harnessing Stroke Attributes for Training-Free Sketch Generation
Rui Yang, Huining Li, Yiyi Long +2
Generating sketches guided by reference styles requires precise transfer of stroke attributes, such as line thickness, deformation, and texture sparsity, while preserving semantic…