HyFL-CLIP distills Euclidean CLIP alignment into hyperbolic space using cross-manifold similarity and Einstein midpoint aggregation to capture hierarchical part-whole relations, achieving up to 19.5% gains in long-text retrieval under perturbations.
arXiv preprint arXiv:2004.00849 , year=
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
Sa2VA unifies SAM-2 segmentation with MLLM reasoning into a single model for referring segmentation and conversation on images and videos, supported by a new 72k-expression Ref-SAV dataset.
LanguageBind aligns video, infrared, depth, and audio to a frozen language encoder via contrastive learning on the new VIDAL-10M dataset, extending video-language pretraining to N modalities.
GIT achieves new state-of-the-art results on 12 vision-language benchmarks, including surpassing human performance on TextCaps, via a simplified single-encoder single-decoder transformer scaled on large pre-training data.
The paper defines Agent AI as interactive multimodal systems that perceive grounded data and generate embodied actions, arguing this approach can mitigate hallucinations in foundation models.
GPT-4V processes interleaved image-text inputs generically and supports visual referring prompting for new human-AI interaction.
citing papers explorer
-
HyFL-CLIP: Hyperbolic Fine-Tuning of CLIP for Robust Long-Context Understanding
HyFL-CLIP distills Euclidean CLIP alignment into hyperbolic space using cross-manifold similarity and Einstein midpoint aggregation to capture hierarchical part-whole relations, achieving up to 19.5% gains in long-text retrieval under perturbations.
-
Sa2VA: Marrying SAM2 with LLaVA for Dense Grounded Understanding of Images and Videos
Sa2VA unifies SAM-2 segmentation with MLLM reasoning into a single model for referring segmentation and conversation on images and videos, supported by a new 72k-expression Ref-SAV dataset.
-
LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment
LanguageBind aligns video, infrared, depth, and audio to a frozen language encoder via contrastive learning on the new VIDAL-10M dataset, extending video-language pretraining to N modalities.
-
GIT: A Generative Image-to-text Transformer for Vision and Language
GIT achieves new state-of-the-art results on 12 vision-language benchmarks, including surpassing human performance on TextCaps, via a simplified single-encoder single-decoder transformer scaled on large pre-training data.
-
Agent AI: Surveying the Horizons of Multimodal Interaction
The paper defines Agent AI as interactive multimodal systems that perceive grounded data and generate embodied actions, arguing this approach can mitigate hallucinations in foundation models.
-
The Dawn of LMMs: Preliminary Explorations with GPT-4V(ision)
GPT-4V processes interleaved image-text inputs generically and supports visual referring prompting for new human-AI interaction.