相关论文: Meta-TTRL: A Metacognitive Framework for Self-Impr…

In recent years deep reinforcement learning (RL) systems have attained superhuman performance in a number of challenging task domains. However, a major limitation of such applications is their demand for massive amounts of training data. A…

Adapting large language models (LLMs) to unseen tasks with in-context training samples without fine-tuning remains an important research problem. To learn a robust LLM that adapts well to unseen tasks, multiple meta-training approaches have…

Multi-task learning (MTL) trains deep neural networks to optimize several objectives simultaneously using a shared backbone, which leads to reduced computational costs, improved data efficiency, and enhanced performance through cross-task…

Test-Time Learning (TTL) enables language agents to iteratively refine their performance through repeated interactions with the environment at inference time. At the core of TTL is an adaptation policy that updates the actor policy based on…

The Contrastive Language-Image Pre-training (CLIP) framework has become a widely used approach for multimodal representation learning, particularly in image-text retrieval and clustering. However, its efficacy is constrained by three key…

Most meta reinforcement learning (meta-RL) methods learn to adapt to new tasks by directly optimizing the parameters of policies over primitive action space. Such algorithms work well in tasks with relatively slight difference. However,…

Reinforcement learning (RL) with verifiable rewards (RLVR) has demonstrated the great potential of enhancing the reasoning abilities in multimodal large language models (MLLMs). However, the reliance on language-centric priors and expensive…

Vision-Language Models (VLMs) have achieved remarkable progress in integrating visual perception with language understanding. However, effective multimodal reasoning requires both accurate perception and robust reasoning, and weakness in…

The transformer architecture and variants presented remarkable success across many machine learning tasks in recent years. This success is intrinsically related to the capability of handling long sequences and the presence of…

Recent advances in Large Language Models (LLMs) have shown impressive capabilities in various applications, yet LLMs face challenges such as limited context windows and difficulties in generalization. In this paper, we introduce a…

Human Mesh Recovery (HMR) is the task of estimating a parameterized 3D human mesh from an image. There is a kind of methods first training a regression model for this problem, then further optimizing the pretrained regression model for any…

The application of reinforcement learning (RL) to enhance the reasoning capabilities of Multimodal Large Language Models (MLLMs) constitutes a rapidly advancing research area. While MLLMs extend Large Language Models (LLMs) to handle…

Multi-task learning (MTL) enables simultaneous training across related tasks, leveraging shared information to improve generalization, efficiency, and robustness, especially in data-scarce or high-dimensional scenarios. While deep learning…

Large Reasoning Models (LRMs) demonstrate remarkable capabilities on complex tasks, exhibiting emergent, human-like thinking patterns. Despite their advances, we identify a fundamental limitation: current LRMs lack a dedicated meta-level…

Recently, Large Language Models (LLMs) have made significant progress in IQ-related domains that require careful thinking, such as mathematics and coding. However, enhancing LLMs' cognitive development in social domains, particularly from a…

Reinforcement learning (RL) is central to improving reasoning in large language models (LLMs) but typically requires ground-truth rewards. Test-Time Reinforcement Learning (TTRL) removes this need by using majority-vote rewards, but relies…

Recent advances in supervised learning and reinforcement learning have provided new opportunities to apply related methodologies to automated driving. However, there are still challenges to achieve automated driving maneuvers in dynamically…

Unified Multimodal Models (UMMs) integrate both visual understanding and generation within a single framework. Their ultimate aspiration is to create a cycle where understanding and generation mutually reinforce each other. While recent…

Meta-learning (ML) has emerged as a promising learning method under resource constraints such as few-shot learning. ML approaches typically propose a methodology to learn generalizable models. In this work-in-progress paper, we put the…

We introduce MetaICL (Meta-training for In-Context Learning), a new meta-training framework for few-shot learning where a pretrained language model is tuned to do in-context learning on a large set of training tasks. This meta-training…