相关论文: Specificity-aware reinforcement learning for fine-…

Clearly explaining a rationale for a classification decision to an end-user can be as important as the decision itself. Existing approaches for deep visual recognition are generally opaque and do not output any justification text;…

Multimodal Large Language Models (MLLMs) have achieved notable performance in computer vision tasks that require reasoning across visual and textual modalities, yet their capabilities are limited to their pre-trained data, requiring…

Understanding real-world videos with complex semantics and long temporal dependencies remains a fundamental challenge in computer vision. Recent progress in multimodal large language models (MLLMs) has demonstrated strong capabilities in…

Reinforcement learning has substantially improved the performance of LLM agents on tasks with verifiable outcomes, but it still struggles on open-ended agent tasks with vast solution spaces (e.g., complex travel planning). Due to the…

Through reinforcement learning with verifiable rewards (RLVR), large language models have achieved substantial progress in domains with easily verifiable outcomes, such as mathematics and coding. However, when applied to more complex tasks…

Large Language Models (LLMs) are so powerful that they sometimes learn correlations between labels and features that are irrelevant to the task, leading to poor generalization on out-of-distribution data. We propose explanation-based…

Learning generalist embodied agents, able to solve multitudes of tasks in different domains is a long-standing problem. Reinforcement learning (RL) is hard to scale up as it requires a complex reward design for each task. In contrast,…

Uncertainty estimation plays an important role for future reliable deployment of deep segmentation models in safety-critical scenarios such as medical applications. However, existing methods for uncertainty estimation have been limited by…

Reinforcement learning (RL) is a branch of machine learning which is employed to solve various sequential decision making problems without proper supervision. Due to the recent advancement of deep learning, the newly proposed Deep-RL…

This tutorial provides a comprehensive survey of methods for fine-tuning diffusion models to optimize downstream reward functions. While diffusion models are widely known to provide excellent generative modeling capability, practical…

This paper introduces a causal attribution model to enhance the interpretability of large language models (LLMs) and improve their causal reasoning abilities via precise fine-tuning. Despite LLMs' proficiency in diverse tasks, their…

Large Language Model (LLM) image recognition is a powerful tool for extracting data from images, but accuracy depends on providing sufficient cues in the prompt - requiring a domain expert for specialized tasks. We introduce Cue Learning…

Recent breakthroughs in reasoning models have markedly advanced the reasoning capabilities of large language models, particularly via training on tasks with verifiable rewards. Yet, a significant gap persists in their adaptation to real…

Traditional image classification requires a predefined list of semantic categories. In contrast, Large Multimodal Models (LMMs) can sidestep this requirement by classifying images directly using natural language (e.g., answering the prompt…

Fine-grained Visual Recognition (FGVR) involves distinguishing between visually similar categories, which is inherently challenging due to subtle inter-class differences and the need for large, expert-annotated datasets. In domains like…

A central goal of cognitive modeling is to develop models that not only predict human behavior but also provide insight into the underlying cognitive mechanisms. While neural network models trained on large-scale behavioral data often…

Fine-tuned vision-language models (VLMs) often capture spurious correlations between image features and textual attributes, resulting in degraded zero-shot performance at test time. Existing approaches for addressing spurious correlations…

Efficiently adapting to new environments and changes in dynamics is critical for agents to successfully operate in the real world. Reinforcement learning (RL) based approaches typically rely on external reward feedback for adaptation.…

Reinforcement Learning (RL) has become the de facto standard for tuning LLMs to solve tasks involving reasoning. However, growing evidence shows that models trained in such way often suffer from a significant loss in diversity. We argue…

Referring Expression Comprehension (REC) is a foundational cross-modal task that evaluates the interplay of language understanding, image comprehension, and language-to-image grounding. It serves as an essential testing ground for…