Visual Memory Injection Attacks for Multi-Turn Conversations Paper • 2602.15927 • Published 2 days ago • 3
Robustness in Both Domains: CLIP Needs a Robust Text Encoder Paper • 2506.03355 • Published Jun 3, 2025 • 6
FuseLIP: Multimodal Embeddings via Early Fusion of Discrete Tokens Paper • 2506.03096 • Published Jun 3, 2025 • 4
RePOPE: Impact of Annotation Errors on the POPE Benchmark Paper • 2504.15707 • Published Apr 22, 2025 • 8
DASH: Detection and Assessment of Systematic Hallucinations of VLMs Paper • 2503.23573 • Published Mar 30, 2025 • 12