High AUC from linear probes on model activations for indirect prompt injection does not license an unqualified claim of malicious-content detection, per a Qwen2.5-VL-7B case study with text and visual controls.
Mrag-suite: A di- agnostic evaluation platform for visual retrieval-augmented generation
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
years
2026 6representative citing papers
Forced CoT produces video-dependent reasoning chains but does not improve MCQ accuracy on Qwen2.5-VL with Video-MME and causes a small drop on the 7B variant.
BCL introduces a particle-filtering Bayesian update framework to systematically refine label representations in in-context learning for information extraction, claiming consistent gains over prior methods.
Configuration choices alone flip pairwise safety verdicts on every tested alignment benchmark, isolated via a finite-envelope proposition linking disagreement rate to strict ordering reversal.
KARITA integrates knowledge-driven augmentation and retrieval to improve classification performance under temporal shifts across clinical, legal, and scientific domains.
RAM outperforms prior methods on PoseTrack and 3DPW for zero-shot multi-person 3D motion tracking and reconstruction by fusing semantic tracking, memory-augmented pose estimation, and predictive fusion.
citing papers explorer
-
When AUC 0.998 Is Not Enough: A Candidate Evaluation Protocol for Hidden-State Probes of Indirect Prompt Injection in Multimodal Computer-Use Agents
High AUC from linear probes on model activations for indirect prompt injection does not license an unqualified claim of malicious-content detection, per a Qwen2.5-VL-7B case study with text and visual controls.
-
Chains That See, Answers That Don't: A Multi-Aspect Evaluation Recipe for Forced Chain-of-Thought on Video-MME
Forced CoT produces video-dependent reasoning chains but does not improve MCQ accuracy on Qwen2.5-VL with Video-MME and causes a small drop on the 7B variant.
-
BCL: Bayesian In-Context Learning Framework for Information Extraction
BCL introduces a particle-filtering Bayesian update framework to systematically refine label representations in in-context learning for information extraction, claiming consistent gains over prior methods.
-
SafetyRepro: Configuration-Conditional Rank Instability on Alignment Benchmarks
Configuration choices alone flip pairwise safety verdicts on every tested alignment benchmark, isolated via a finite-envelope proposition linking disagreement rate to strict ordering reversal.
-
Knowledge-driven Augmentation and Retrieval for Integrative Temporal Adaptation
KARITA integrates knowledge-driven augmentation and retrieval to improve classification performance under temporal shifts across clinical, legal, and scientific domains.
-
RAM: Recover Any 3D Human Motion in-the-Wild
RAM outperforms prior methods on PoseTrack and 3DPW for zero-shot multi-person 3D motion tracking and reconstruction by fusing semantic tracking, memory-augmented pose estimation, and predictive fusion.