相关论文: DVMap: Fine-Grained Pluralistic Value Alignment vi…

Integrating large language models (LLMs) with knowledge graphs derived from domain-specific data represents an important advancement towards more powerful and factual reasoning. As these models grow more capable, it is crucial to enable…

Large language models (LLMs) have demonstrated remarkable capabilities but often struggle to align with human preferences, leading to harmful or undesirable outputs. Preference learning, which trains models to distinguish between preferred…

Reinforcement learning with verifiable rewards (RLVR) has achieved remarkable success in logical reasoning tasks, yet whether large language model (LLM) alignment requires fundamentally different approaches remains unclear. Given the…

Multimodal large language models (MLLMs) have demonstrated remarkable capabilities in visual understanding, but their application to long-term Earth observation analysis remains limited, primarily focusing on single-temporal or bi-temporal…

Classification tasks are typically handled using Machine Learning (ML) models, which lack a balance between accuracy and interpretability. This paper introduces a new approach for classification tasks using Large Language Models (LLMs) in…

With the advent of multi-modal large language models (MLLMs), datasets used for visual question answering (VQA) and referring expression comprehension have seen a resurgence. However, the most popular datasets used to evaluate MLLMs are…

Large Language Models (LLMs) aim to serve as versatile assistants aligned with human values, as defined by the principles of being helpful, honest, and harmless (hhh). However, in terms of Multimodal Large Language Models (MLLMs), despite…

This paper introduces a multi-label visual emotion analysis benchmark dataset for comprehensively evaluating the ability of multimodal large language models (MLLMs) to predict the emotions evoked by images. Recent user studies report an…

Large Vision-Language Models (LVLMs) or multimodal large language models represent a significant advancement in artificial intelligence, enabling systems to understand and generate content across both visual and textual modalities. While…

Recent deep learning approaches for multi-view depth estimation are employed either in a depth-from-video or a multi-view stereo setting. Despite different settings, these approaches are technically similar: they correlate multiple source…

Albeit worryingly underrated in the recent literature on machine learning in general (and, on deep learning in particular), multivariate density estimation is a fundamental task in many applications, at least implicitly, and still an open…

Recently, Visual Programming (VP) based on large language models (LLMs) has rapidly developed and demonstrated significant potential in complex Visual Reasoning (VR) tasks. Previous works to enhance VP have primarily focused on improving…

Multimodal large language models (MLLMs) are now routinely deployed for visual understanding, generation, and curation. A substantial fraction of these applications require an explicit aesthetic judgment. Most existing solutions reduce this…

Multi-view multi-label classification (MvMLC) has recently garnered significant research attention due to its wide range of real-world applications. However, incompleteness in views and labels is a common challenge, often resulting from…

Vision-Language Models (VLMs) excel at 2D tasks such as grounding and captioning, yet remain limited in 3D understanding. A key limitation is their text-only supervision paradigm, which under-constrains fine-grained visual perception and…

In recent years, Fine-Grained Visual Classification (FGVC) has achieved impressive recognition accuracy, despite minimal inter-class variations. However, existing methods heavily rely on instance-level labels, making them impractical in…

Obtaining large pre-trained models that can be fine-tuned to new tasks with limited annotated samples has remained an open challenge for medical imaging data. While pre-trained deep networks on ImageNet and vision-language foundation models…

The rapid advancement of GenAI technology over the past few years has significantly contributed towards highly realistic deepfake content generation. Despite ongoing efforts, the research community still lacks a large-scale and reasoning…

Recent work in large language modeling (LLMs) has used fine-tuning to align outputs with the preferences of a prototypical user. This work assumes that human preferences are static and homogeneous across individuals, so that aligning to a a…

Vision-Language Models (VLMs) have demonstrated remarkable capabilities in aligning and understanding multimodal signals, yet their potential to reason over structured data, where multimodal entities are connected through explicit…