Recurrence Meets Transformers for Universal Multimodal Retrieval

[BMVC 2025] Mitigating Hallucinations in Multimodal LLMs via Object-aware Preference Optimization

arXiv LaTeX Cleaner: Easily clean the LaTeX code of your paper to submit to arXiv

[CVPR 2025] Recurrence-Enhanced Vision-and-Language Transformers for Robust Multimodal Document Retrieval

This repository contains a curated list of research papers and resources focusing on saliency and scanpath prediction, human attention, human visual search.

[ECCV 2024] BRIDGE: Bridging Gaps in Image Captioning Evaluation with Stronger Visual Cues.

[CVPR 2025] Augmenting Multimodal LLMs with Self-Reflective Tokens for Knowledge-based Visual Question Answering

[BMVC 2024 Oral ✨] Revisiting Image Captioning Training Paradigm via Direct CLIP-based Optimization

[ICCVW 25] LLaVA-MORE: A Comparative Study of LLMs and Visual Backbones for Enhanced Visual Instruction Tuning

Pytorch code for ECCVW 2022 paper "Consistency-based Self-supervised Learning for Temporal Anomaly Localization"