ConceptPose delivers state-of-the-art zero-shot relative pose estimation by matching open-vocabulary 3D concept vectors derived from VLM saliency maps, beating the strongest baseline by 62% in ADD(-S) without training.
hub
Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models
13 Pith papers cite this work. Polarity classification is still indexing.
13
Pith papers citing it
hub tools
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
Tracker is a self-supervised VL tracker that uses a Dynamic Token Aggregation Module to learn instance tracking from single language descriptions in unlabeled videos and outperforms prior self-supervised methods.
PolySLGen generates contextually appropriate and temporally coherent multimodal speaking and listening reactions for polyadic interactions by fusing group motion and social cues.
PLUME uses latent-state autoregressive rollouts and a progressive training curriculum to deliver efficient reasoning for universal multimodal embeddings without generating explicit rationales.
AV-SpeakerBench is a new speaker-centered benchmark showing that top multimodal models still struggle with fine-grained audiovisual speech understanding, with Gemini 2.5 Pro leading but open models lagging on fusion.
GLMap combines explicit 3D Gaussians with multi-scale language semantics in a dual-modality structure and uses an analytical Gaussian Estimator for incremental map building, improving zero-shot performance on navigation and reasoning tasks.
CheXmix combines masked autoencoder pretraining with early-fusion generative modeling to outperform prior models on chest X-ray classification by up to 8.6% AUROC, inpainting by 51%, and report generation by 45% on GREEN.
G-MIXER achieves state-of-the-art zero-shot composed image retrieval by using geodesic mixup to build diverse implicit candidates and MLLM-derived explicit semantics for re-ranking.
SpatialStack improves 3D spatial reasoning in vision-language models by stacking and synchronizing multi-level geometric features with the language backbone.
Nano-EmoX is a compact 2.2B multimodal model that unifies six core affective tasks across perception, understanding, and interaction levels via a curriculum framework, achieving competitive benchmark performance.
MedBridge adapts pretrained VLMs to multi-label medical diagnosis via query tokens for non-destructive alignment and expert routing, reporting 6-15% AUC gains on chest radiograph benchmarks across eight models.