ReShift is a reasoning-level backdoor framework for VLMs that uses poisoned data construction and joint optimization to shift CoT trajectories on trigger while preserving surface coherence.
Tokenswap: Backdoor attack on the com- positional understanding of large vision-language models
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
other 1
citation-polarity summary
years
2026 4verdicts
UNVERDICTED 4roles
other 1polarities
unclear 1representative citing papers
POISE is a stealthy skill-poisoning attack achieving 89.3% ASR on Skill-Inject by blending a compressed trigger into contextually appropriate positions in skill bodies, outperforming YAML and random-placement baselines while evading static scanners.
VideoStir introduces a spatio-temporal graph-based structure and intent-aware retrieval for long-video RAG, achieving competitive performance with SOTA methods via a new IR-600K dataset.
CogniVerse is a proposed MMRAG framework that combines cognitive reflection for retrieval filtering, Riemannian manifold alignment plus spectral graphs for retrieval, and optimal transport loss for generation, claiming better accuracy, coherence, and lower latency than prior systems.
citing papers explorer
-
VideoStir: Understanding Long Videos via Spatio-Temporally Structured and Intent-Aware RAG
VideoStir introduces a spatio-temporal graph-based structure and intent-aware retrieval for long-video RAG, achieving competitive performance with SOTA methods via a new IR-600K dataset.