Negative Entity Suppression for Zero-Shot Captioning with Synthetic Images

arXiv — cs.CV•Thursday, November 13, 2025 at 5:00:00 AM

The recent publication on Negative Entity Suppression (NES) for zero-shot image captioning presents a novel methodology to tackle the limitations of traditional approaches that often struggle with cross-domain generalization. By utilizing synthetic images, NES ensures consistent image-to-text retrieval, which is crucial for improving the accuracy of generated captions. The method also filters out negative entities—irrelevant objects that may appear in captions but are not present in the input images—thereby minimizing hallucination rates. This innovative approach has demonstrated its effectiveness by achieving new state-of-the-art results in zero-shot captioning, highlighting its potential to significantly enhance the accuracy and reliability of automated image captioning systems.

— via World Pulse Now AI Editorial System

Read Original

Was this article worth reading? Share it

Recommended Readings

arXiv — cs.CV2 days ago

Bridging Hidden States in Vision-Language Models

PositiveArtificial Intelligence

Vision-Language Models (VLMs) are emerging models that integrate visual content with natural language. Current methods typically fuse data either early in the encoding process or late through pooled embeddings. This paper introduces a lightweight fusion module utilizing cross-only, bidirectional attention layers to align hidden states from both modalities, enhancing understanding while keeping encoders non-causal. The proposed method aims to improve the performance of VLMs by leveraging the inherent structure of visual and textual data.

Read full article

via arXiv — cs.CV

arXiv — cs.LG2 days ago

Bias-Restrained Prefix Representation Finetuning for Mathematical Reasoning

PositiveArtificial Intelligence

The paper titled 'Bias-Restrained Prefix Representation Finetuning for Mathematical Reasoning' introduces a new method called Bias-REstrained Prefix Representation FineTuning (BREP ReFT). This approach aims to enhance the mathematical reasoning capabilities of models by addressing the limitations of existing Representation finetuning (ReFT) methods, which struggle with mathematical tasks. The study demonstrates that BREP ReFT outperforms both standard ReFT and weight-based Parameter-Efficient finetuning (PEFT) methods through extensive experiments.

Read full article

via arXiv — cs.LG

arXiv — cs.LG2 days ago

Transformers know more than they can tell -- Learning the Collatz sequence

NeutralArtificial Intelligence

The study investigates the ability of transformer models to predict long steps in the Collatz sequence, a complex arithmetic function that maps odd integers to their successors. The accuracy of the models varies significantly depending on the base used for encoding, achieving up to 99.7% accuracy for bases 24 and 32, while dropping to 37% and 25% for bases 11 and 3. Despite these variations, all models exhibit a common learning pattern, accurately predicting inputs with similar residuals modulo 2^p.

Read full article

via arXiv — cs.LG

arXiv — cs.LG2 days ago

Higher-order Neural Additive Models: An Interpretable Machine Learning Model with Feature Interactions

PositiveArtificial Intelligence

Higher-order Neural Additive Models (HONAMs) have been introduced as an advancement over Neural Additive Models (NAMs), which are known for their predictive performance and interpretability. HONAMs address the limitation of NAMs by effectively capturing feature interactions of arbitrary orders, enhancing predictive accuracy while maintaining interpretability, crucial for high-stakes applications. The source code for HONAM is publicly available on GitHub.

Read full article

via arXiv — cs.LG