相关论文: DataProphet: Demystifying Supervision Data General…

Large Vision-Language Models (LVLMs) have shown promising capabilities in understanding and generating information by integrating both visual and textual data. However, current models are still prone to hallucinations, which degrade the…

The popularity of multimodal large language models (MLLMs) has triggered a recent surge in research efforts dedicated to evaluating these models. Nevertheless, existing evaluation studies of MLLMs primarily focus on the comprehension and…

With recent advancements in Large Multimodal Models (LMMs) across various domains, a novel prompting method called visual referring prompting has emerged, showing significant potential in enhancing human-computer interaction within…

Achieving deep alignment between vision and language remains a central challenge for Multimodal Large Language Models (MLLMs). These models often fail to fully leverage visual input, defaulting to strong language priors. Our approach first…

Finding general evaluation metrics for unsupervised representation learning techniques is a challenging open research question, which recently has become more and more necessary due to the increasing interest in unsupervised methods. Even…

Preference learning is a widely adopted post-training technique that aligns large language models (LLMs) to human preferences and improves specific downstream task capabilities. In this work we systematically investigate how specific…

Recent work has investigated the capabilities of large language models (LLMs) as zero-shot models for generating individual-level characteristics (e.g., to serve as risk models or augment survey datasets). However, when should a user have…

For protein sequence datasets, unlabeled data has greatly outpaced labeled data due to the high cost of wet-lab characterization. Recent deep-learning approaches to protein prediction have shown that pre-training on unlabeled data can yield…

Long-context modeling capabilities are important for large language models (LLMs) in various applications. However, directly training LLMs with long context windows is insufficient to enhance this capability since some training samples do…

In this paper we present an exploratory research on quantifying the impact that data distribution has on the performance and evaluation of NLP models. We propose an automated framework that measures the data point distribution across 6…

Every data selection method inherently has a target. In practice, these targets often emerge implicitly through benchmark-driven iteration: researchers develop selection strategies, train models, measure benchmark performance, then refine…

The rapid development of Multimodal Large Language Models (MLLMs), such as GPT-4o, marks a significant step toward artificial general intelligence. Existing methods typically align vision encoders with LLMs via supervised fine-tuning (SFT),…

Fine-tuning large language models (LLMs) on multi-task instruction-following data has been proven to be a powerful learning paradigm for improving their zero-shot capabilities on new tasks. Recent works about high-quality…

Contrary to the conventional emphasis on dataset size, we explore the role of data alignment -- an often overlooked aspect of data quality -- in training capable Large Language Models (LLMs). To do so, we use the Task2Vec-based alignment…

Large pre-trained language models (LPLM) have shown spectacular success when fine-tuned on downstream supervised tasks. Yet, it is known that their performance can drastically drop when there is a distribution shift between the data used…

Large Vision-Language Models (LVLMs) are rapidly evolving toward true multimodal reasoning, with visual search representing a concrete instantiation of the thinking-with-images paradigm. However, LVLM visual search faces two key challenges:…

Measuring the generalization ability of Large Language Models (LLMs) is challenging due to data contamination. As models grow and computation becomes cheaper, ensuring tasks and test cases are unseen during training phases will become…

Multi-Source Domain Generalization (DG) is the task of training on multiple source domains and achieving high classification performance on unseen target domains. Recent methods combine robust features from web-scale pretrained backbones…

Thousands of diverse benchmarks have been developed to measure the quality of large language models (LLMs). Yet prior work has demonstrated that LLM performance is often sufficiently explained by a small set of latent factors, or abilities.…

LLMs increasingly excel on AI benchmarks, but doing so does not guarantee validity for downstream tasks. This study contrasts LLM alignment on benchmarks, downstream tasks, and, importantly the intended impact of those tasks. We evaluate…