arXiv:2610.09502v1 Announce Type: new Abstract: Open-vocabulary detection (OVD) recognizes categories unseen during training through textual category queries, yet achieving strong generalization with...
Open-vocabulary detection (OVD) recognizes categories unseen during training through textual category queries, yet achieving strong generalization with real-time efficiency remains challenging. Beyond...
arXiv:2608.14835v2 Announce Type: replace Abstract: Dynamic scene graphs (DSGs) capture spatio-temporal interactions across videos as $\langle$subject, predicate, object$\rangle$ triplets, and underp...
arXiv:2606. 15134v1 Announce Type: cross Abstract: Vision encoders for retrieval are typically trained with class-label supervision: each training pair reduces to a scalar that uniformly pushes the embedding apart or pulls it together, as if every visual attribute either differed or matched.
arXiv:2610.16182v1 Announce Type: new Abstract: Flagship large language models (LLMs) offer rich general knowledge and strong reasoning capabilities, but their high inference cost and latency limit t...
arXiv:2608. 07886v1 Announce Type: cross Abstract: Vision-language grounding connects language to visual content, yet most existing formulations reduce grounding to a unidirectional localization problem: given a prespecified text phrase or category name, identify the corresponding image region.
arXiv:2606. 24716v1 Announce Type: cross Abstract: Sparse autoencoders (SAEs) are increasingly used to extract interpretable concepts from vision and vision language models, yet existing evaluation methods largely rely on proxy metrics or qualitative inspection rather than measuring semantic correspondence.
arXiv:2607. 23052v1 Announce Type: cross Abstract: Dual-encoder vision-language models (VLMs) expose a similarity interface that enables zero-shot retrieval but fails compositional constraints: queries like "umbrella and no person" retrieve images containing both, even when concept detection is reliable.
Source-Free Domain Adaptation with Vision-Language Prior proposes DIFO++, a two-step adaptation framework that customizes a vision‑language model (e.g., CLIP) to a target domain via prompt learning and then distills its knowledge into a target model. The method focuses on a gap region where features are entangled and class‑ambiguous, generating reliable pseudo‑labels by fusing predictions from both models and employing memory, category attention, predictive consistency, and entropy minimization to align semantics. Experiments demonstrate that DIFO++ outperforms existing state‑of‑the‑art approaches.
arXiv:2512. 10092v2 Announce Type: replace Abstract: Analyzing large-scale text corpora is a core challenge in machine learning, crucial for tasks like identifying undesirable model behaviors or biases in training data.
arXiv:2605.16893v2 Announce Type: replace Abstract: Recent studies have introduced memory-augmented architectures that decouple knowledge storage from neural computation, enabling more direct access...
arXiv:2512. 10244v2 Announce Type: replace-cross Abstract: Semi-supervised few-shot learning (SSFSL) resembles real-world applications such as auto-annotation, as it aims to learn a model from a few labeled and abundant unlabeled task-specific examples to annotate the unlabeled ones.