26 articles mentioning clip-vit-base-patch32
arXiv:2509.20712v5 Announce Type: replace-cross Abstract: Reinforcement learning (RL) has become a powerful paradigm for optimizing large language models (LLMs) to handle complex reasoning tasks. A core challenge in this process lies in managing policy entropy, which reflects the balance between exp
arXiv:2512.05591v2 Announce Type: replace-cross Abstract: Large language model post-training relies on reinforcement learning to improve model capability and alignment quality. However, the off-policy training paradigm introduces distribution shift, which often pushes the policy beyond the trust reg
arXiv:2509.03740v3 Announce Type: replace-cross Abstract: Vision-language models (VLMs) like CLIP have shown impressive zero-shot and few-shot learning capabilities across diverse applications. However, adapting these models to new fine-grained domains remains difficult due to reliance on prompt eng
arXiv:2604.16487v2 Announce Type: replace-cross Abstract: CLIP retrieval is typically framed as a pointwise similarity problem in a shared embedding space. While CLIP achieves strong global cross-modal alignment, many retrieval failures arise from local geometric inconsistencies: nearby items are in
arXiv:2602.20409v2 Announce Type: replace-cross Abstract: Recent vision-language models (VLMs) such as CLIP demonstrate impressive cross-modal reasoning, extending beyond images to 3D perception. Yet, these models remain fragile under domain shifts, especially when adapting from synthetic to real-wo
arXiv:2603.14389v2 Announce Type: replace Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has catalyzed a leap in Large Language Model (LLM) reasoning, yet its optimization dynamics remain fragile. Standard algorithms like GRPO enforce stability via "hard clipping", which inadvertent
arXiv:2604.16410v1 Announce Type: new Abstract: CLIP adaptation can improve in-domain accuracy while degrading out-of-domain transfer, but comparisons between Full Fine-Tuning (Full FT) and LoRA are often confounded by different learning-rate conventions. We study how adaptation method and optimizat
arXiv:2604.18276v1 Announce Type: cross Abstract: Block-encoding is a foundational technique in modern quantum algorithms, enabling the implementation of non-unitary operations by embedding them into larger unitary matrices. While theoretically powerful and essential for advanced protocols like Quan
arXiv:2604.16370v1 Announce Type: new Abstract: Decoding natural language from non-invasive electroencephalography (EEG) remains fundamentally limited by low signal-to-noise ratio and restricted information bandwidth. This raises a fundamental question regarding whether sentence-level linguistic str
arXiv:2604.18444v1 Announce Type: new Abstract: Zero-shot vision-language models (VLMs) have shown promise for chest radiograph classification, but their performance is often limited by confounding label co-occurrence, long-tail class imbalance, and transfer instability under domain shift. We propos
arXiv:2604.13561v1 Announce Type: cross Abstract: Vision-language models trained with contrastive learning on paired medical images and reports show strong zero-shot diagnostic capabilities, yet the effect of training batch composition on learned representations remains unexplored for 3D medical ima
arXiv:2603.08942v2 Announce Type: replace-cross Abstract: Recent advances in vision-language models (VLMs) have demonstrated remarkable zero-shot capabilities, yet adapting these models to specialized domains remains a significant challenge. Building on recent theoretical insights suggesting that in
arXiv:2604.09101v1 Announce Type: cross Abstract: Organisations with limited data and computational resources increasingly outsource model training to Machine Learning as a Service (MLaaS) providers, who adapt vision-language models (VLMs) such as CLIP to downstream tasks via prompt tuning rather th
arXiv:2509.26036v3 Announce Type: replace-cross Abstract: While Contrastive Language-Image Pretraining (CLIP) excels at zero-shot tasks by aligning image and text embeddings, its performance in few-shot classification is hindered by a critical limitation: intra-modal misalignment. This issue, caused
arXiv:2510.05261v2 Announce Type: replace Abstract: The Lipschitz constant is a key measure for certifying the robustness of neural networks to input perturbations. However, computing the exact constant is NP-hard, and standard approaches to estimate the Lipschitz constant involve solving a large ma
arXiv:2407.14971v3 Announce Type: replace-cross Abstract: Vision-Language Models (VLMs) rely heavily on pretrained vision encoders to support downstream tasks such as image captioning, visual question answering, and zero-shot classification. Despite their strong performance, these encoders remain hi
arXiv:2604.05971v1 Announce Type: cross Abstract: Recent research has shown that contrastive vision-language models such as CLIP often lack fine-grained understanding of visual content. While a growing body of work has sought to address this limitation, we identify a distinct failure mode in the CLI
arXiv:2507.22264v2 Announce Type: replace-cross Abstract: Contrastive Language-Image Pre-training (CLIP)~\citep{radford2021learning} has emerged as a pivotal model in computer vision and multimodal learning, achieving state-of-the-art performance at aligning visual and textual representations throug
arXiv:2508.07629v4 Announce Type: replace-cross Abstract: We present Klear-Reasoner, a model with long reasoning capabilities that demonstrates careful deliberation during problem solving, achieving outstanding performance across multiple benchmarks. Although there are already many excellent works r
arXiv:2604.01118v1 Announce Type: cross Abstract: Leveraging the rich semantic features of vision-language models (VLMs) like CLIP for monocular depth estimation tasks is a promising direction, yet often requires extensive fine-tuning or lacks geometric precision. We present a parameter-efficient fr
arXiv:2603.29258v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) have demonstrated strong capabilities across a wide range of multimodal tasks. However, recent studies have shown that VLMs, such as CLIP, perform poorly in understanding negation expressions, which are common in natural
arXiv:2603.28575v1 Announce Type: cross Abstract: The discovery of anticancer therapeutics has traditionally treated organic small molecules and metal-based coordination complexes as separate chemical domains, limiting knowledge transfer despite their shared biological objectives. This disparity is
We’re introducing a neural network called CLIP which efficiently learns visual concepts from natural language supervision. CLIP can be applied to any visual classification benchmark by simply providing the names of the visual categories to be recognized, similar to the “zero-shot” capabilities of GP