MirrorCheck detects adversarial attacks on VLMs via T2I regeneration for semantic consistency checks, using stochastic model selection and one-time perturbations for robustness against adaptive attacks.
Vl-bert: Pre-training of generic visual-linguistic representations
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
fields
cs.CV 6verdicts
UNVERDICTED 6roles
background 2representative citing papers
Flamingo models reach new state-of-the-art few-shot results on image and video tasks by bridging frozen vision and language models with cross-attention layers trained on interleaved web-scale data.
MiMIC mitigates visual modality collapse and semantic misalignment in universal multimodal retrieval via fusion-in-decoder architecture and robust single-modality training.
NaVid, a video-based VLM trained on 510k navigation and 763k web samples, achieves SOTA VLN performance using only monocular RGB video for next-step action planning in sim and real environments.
InterCMDM proposes a block-causal latent diffusion framework with dual-stream causal transformers and multi-task attention masks for autoregressive text-conditioned two-person interaction generation and reports SOTA results on InterHuman and Inter-X.
TASM proposes a task-aware structured memory framework using task-vector compression, bipartite token merging, and a Core Memory plus Latent Bank hierarchy to enable efficient dynamic multi-modal in-context learning.
citing papers explorer
-
MirrorCheck: Efficient Adversarial Defense for Vision-Language Models
MirrorCheck detects adversarial attacks on VLMs via T2I regeneration for semantic consistency checks, using stochastic model selection and one-time perturbations for robustness against adaptive attacks.
-
Flamingo: a Visual Language Model for Few-Shot Learning
Flamingo models reach new state-of-the-art few-shot results on image and video tasks by bridging frozen vision and language models with cross-attention layers trained on interleaved web-scale data.
-
MiMIC: Mitigating Visual Modality Collapse in Universal Multimodal Retrieval While Avoiding Semantic Misalignment
MiMIC mitigates visual modality collapse and semantic misalignment in universal multimodal retrieval via fusion-in-decoder architecture and robust single-modality training.
-
NaVid: Video-based VLM Plans the Next Step for Vision-and-Language Navigation
NaVid, a video-based VLM trained on 510k navigation and 763k web samples, achieves SOTA VLN performance using only monocular RGB video for next-step action planning in sim and real environments.
-
InterCMDM: Block-Causal Diffusion for Autoregressive Human Interaction Generation
InterCMDM proposes a block-causal latent diffusion framework with dual-stream causal transformers and multi-task attention masks for autoregressive text-conditioned two-person interaction generation and reports SOTA results on InterHuman and Inter-X.
-
Task-Aware Structured Memory for Dynamic Multi-modal In-Context Learning
TASM proposes a task-aware structured memory framework using task-vector compression, bipartite token merging, and a Core Memory plus Latent Bank hierarchy to enable efficient dynamic multi-modal in-context learning.