The paper introduces CLEAR, a CLoze-style rEAsoning-based Re-ranking framework for Compositional Zero-Shot Learning. CLEAR treats primitive variations as context-driven activations of concrete visual cues rather than independent entities, extracting conditional variants in a coarse-to-fine manner and performing cloze-style reasoning to infer high-level semantics. Experiments show that CLEAR consistently improves base models and surpasses state-of-the-art methods on the C-GQA and MIT-States datasets.
Compositional Zero-Shot Learning (CZSL) aims to combine known attributes and objects as primitives for recognizing previously unseen attribute-object pairs. Prior works either predict attributes and objects independently, missing their strong contextual dependency, or use unidirectional conditional modeling (e.
arXiv:2607. 00374v1 Announce Type: cross Abstract: Composed Image Retrieval (CIR) retrieves a target image from a reference image and a textual modification.
arXiv:2606. 31222v1 Announce Type: new Abstract: Composed image retrieval requires identifying a target image from a gallery by integrating a reference image with a textual modification instruction.
Compositional Zero-Shot Learning (CZSL) aims to recognize unseen attribute-object compositions by leveraging knowledge of primitive concepts learned from seen compositions. Although recent works achieve impressive performance in CZSL by leveraging large vision-language models, they primarily rely on discriminative representations that may not explicitly preserve the structured relationships between primitive concepts and their compositions.
arXiv:2608. 19871v1 Announce Type: new Abstract: Compositional Zero-Shot Learning (CZSL) aims to recognize unseen attribute-object compositions by leveraging knowledge of primitive concepts learned from seen compositions.
The paper introduces a progressive training strategy for embodied vision‑language models aimed at reducing spatio‑temporal hallucinations. It first creates a Chain‑of‑Thought dataset that breaks complex reasoning into detailed spatiotemporal steps, then uses supervised pre‑training on this dataset followed by fine‑tuning with weakly‑labeled data. Experiments show the method improves backbone accuracy and narrows the forward‑backward performance gap from over 70% to 6.53%, indicating stronger dynamic reasoning and fewer temporal biases.
CS-CLIP is a vision‑language model that improves compositional reasoning by using scene graphs to identify compositional elements and create structured negative examples through selective masking. The approach retains only the most contradictory negatives, encouraging the model to depend on compositional structure instead of surface cues. CS-CLIP achieves state‑of‑the‑art performance on compositional reasoning benchmarks while maintaining strong cross‑modal retrieval and downstream visual reasoning capabilities with fewer training samples.
arXiv:2603.26737v2 Announce Type: replace-cross Abstract: Current multimodal LLMs encode images as static visual prefixes and rely on text-based reasoning, lacking goal-driven and adaptive visual acc...
arXiv:2606. 26794v1 Announce Type: cross Abstract: CLIP and its variants are widely adopted visual backbones in multimodal systems, but their pretraining remains dominated by descriptive image-text alignment.
arXiv:2607. 09061v1 Announce Type: cross Abstract: A striking feature of the human visual system is that it ingests visual information through a series of local foveated glimpses, rather than a single global computation.
The paper introduces EvoPrompt, a framework for adapting vision‑language models to new tasks with limited data while preventing catastrophic forgetting. EvoPrompt uses a Modality‑Shared Prompt Projector to create hierarchical prompts and an evolutionary training strategy that separates low‑rank updates into directional and magnitude components, preserving learned semantic directions. Experiments show that EvoPrompt achieves state‑of‑the‑art few‑shot performance while maintaining the original zero‑shot capabilities of the pre‑trained models.
Zero-shot composed image retrieval (ZS-CIR) aims to retrieve a target image by editing a reference image with a natural-language instruction, without relying on domain-specific annotated triplets. Most existing ZS-CIR methods rely on textual inversion to translate the reference image into pseudo-text tokens and then compose them with the instruction via simple concatenation in the text space, which can be lossy and brittle for fine-grained semantics.