Related papers: KoCo: Conditioning Language Model Pre-training on …

We propose to build omni-modal intelligence, which is capable of understanding any modality and learning universal representations. In specific, we propose a scalable pretraining paradigm, named Multimodal Context (MiCo), which can scale up…

Document understanding with multimodal large language models (MLLMs) requires not only accurate answers but also explicit, evidence-grounded reasoning, especially in high-stakes scenarios. However, current document MLLMs still fall short of…

Most existing large language models (LLMs) are expensive to adapt after deployment, especially when a task requires newly produced information or niche domain knowledge. Recent work has shown that, by manipulating and optimizing their…

To deliver high-quality, personalized responses, large language models (LLMs) must effectively incorporate context -- personal, demographic, and cultural information specific to an end-user. For example, asking the model to explain Newton's…

Long-context modeling is becoming a core capability of modern large vision-language models (LVLMs), enabling sustained context management across long-document understanding, video analysis, and multi-turn tool use in agentic workflows. Yet…

Most language models (LMs) are trained and applied in an autoregressive left-to-right fashion, assuming that the next token only depends on the preceding ones. However, this assumption ignores the potential benefits of using the full…

Masked language modeling (MLM), a self-supervised pretraining objective, is widely used in natural language processing for learning text representations. MLM trains a model to predict a random sample of input tokens that have been replaced…

As the use of interactive machines grow, the task of Emotion Recognition in Conversation (ERC) became more important. If the machine-generated sentences reflect emotion, more human-like sympathetic conversations are possible. Since emotion…

Large language models (LLMs) have recently attracted considerable interest for their ability to perform complex reasoning tasks, such as chain-of-thought (CoT) reasoning. However, most of the existing approaches to enhance this ability rely…

The capacity of existing human keypoint localization models is limited by keypoint priors provided by the training data. To alleviate this restriction and pursue more general model, this work studies keypoint localization from a different…

Recent work exploring the capabilities of pre-trained large language models (LLMs) has demonstrated their ability to act as general pattern machines by completing complex token sequences representing a wide array of tasks, including…

Optimizing black-box functions is a fundamental problem in science and engineering. To solve this problem, many approaches learn a surrogate function that estimates the underlying objective from limited historical evaluations. Large…

Fine-grained skill representations, commonly referred to as knowledge components (KCs), are fundamental to many approaches in student modeling and learning analytics. However, KC-level correctness labels are rarely available in real-world…

Large Language Models (LLMs) often suffer from performance degradation when faced with domain shifts, primarily due to catastrophic forgetting. In this work, we propose KILO (Knowledge-Instructed Learning for Continual Adaptation), a novel…

Large Language Models (LLMs) have demonstrated remarkable capabilities in handling long texts and have almost perfect performance in traditional retrieval tasks. However, their performance significantly degrades when it comes to numerical…

Multimodal supervision has achieved promising results in many visual language understanding tasks, where the language plays an essential role as a hint or context for recognizing and locating instances. However, due to the defects of the…

Code-switching is a prevalent linguistic phenomenon in which multilingual individuals seamlessly alternate between languages. Despite its widespread use online and recent research trends in this area, research in code-switching presents…

In this paper, we study an emergent self-debiasing mechanisms against stereotypical content in Large Language Models (LLMs). Unlike traditional safety mechanisms that are primarily triggered by explicit input-level stimuli, self-debiasing…

While LLMs excel at reasoning over prompts using static pretrained knowledge, they struggle significantly with context learning-the ability to dynamically extract, internalize, and apply new knowledge from complex, task-specific contexts.…

As Large language models (LLMs) are increasingly deployed in diverse applications, faithfully integrating evolving factual knowledge into these models remains a critical challenge. Continued pre-training on paraphrased data has shown…