Related papers: Local Feature Swapping for Generalization in Reinf…

Globally normalized neural sequence models are considered superior to their locally normalized equivalents because they may ameliorate the effects of label bias. However, when considering high-capacity neural parametrizations that condition…

We study how vision-language-action (VLA) models can improve through real-world deployments via reinforcement learning (RL). We present a general-purpose method, RL with Experience and Corrections via Advantage-conditioned Policies (RECAP),…

Contrastive learning has emerged as a powerful method in deep learning, excelling at learning effective representations through contrasting samples from different distributions. However, neural collapse, where embeddings converge into a…

While modern convolutional neural networks achieve outstanding accuracy on many image classification tasks, they are, compared to humans, much more sensitive to image degradation. Here, we describe a variant of Batch Normalization,…

In convolutional neural networks (CNNs), pooling operations play important roles such as dimensionality reduction and deformation compensation. In general, max pooling, which is the most widely used operation for local pooling, is performed…

Pre-trained large vision-language models (VLMs) like CLIP demonstrate impressive generalization ability. Existing prompt-based and adapter-based works have made significant progress in fine-tuning VLMs but still face the challenges of…

Recent advances in multimodal learning has resulted in powerful vision-language models, whose representations are generalizable across a variety of downstream tasks. Recently, their generalization ability has been further extended by…

Generalization remains a central challenge in machine learning. In this work, we propose Learning from Teaching (LoT), a novel regularization technique for deep neural networks to enhance generalization. Inspired by the human ability to…

Vision Transformers have emerged as powerful, scalable and versatile representation learners. To capture both global and local features, a learnable [CLS] class token is typically prepended to the input sequence of patch tokens. Despite…

With the rise of powerful pre-trained vision-language models like CLIP, it becomes essential to investigate ways to adapt these models to downstream datasets. A recently proposed method named Context Optimization (CoOp) introduces the…

Continual reinforcement learning must balance retention with adaptation, yet many methods still rely on \emph{single-model preservation}, committing to one evolving policy as the main reusable solution across tasks. Even when a previously…

Over-parameterized neural network models often lead to significant performance discrepancies between training and test sets, a phenomenon known as overfitting. To address this, researchers have proposed numerous regularization techniques…

Reinforcement Learning is an area of Machine Learning focused on how agents can be trained to make sequential decisions, and achieve a particular goal within an arbitrary environment. While learning, they repeatedly take actions based on…

In modern chip design, placement aims at placing millions of circuit modules, which is an essential step that significantly influences power, performance, and area (PPA) metrics. Recently, reinforcement learning (RL) has emerged as a…

The past decade has seen vast progress in deep reinforcement learning (RL) on the back of algorithms manually designed by human researchers. Recently, it has been shown that it is possible to meta-learn update rules, with the hope of…

Advancements in the generation quality of various Generative Models (GMs) has made it necessary to not only perform binary manipulation detection but also localize the modified pixels in an image. However, prior works termed as passive for…

Some reinforcement learning (RL) algorithms can stitch pieces of experience to solve a task never seen before during training. This oft-sought property is one of the few ways in which RL methods based on dynamic-programming differ from RL…

Deep reinforcement learning (DRL) frameworks are increasingly used to solve high-dimensional continuous control tasks in robotics. However, due to the lack of sample efficiency, applying DRL for online learning is still practically…

Inspired by the success of reinforcement learning (RL) in refining large language models (LLMs), we propose AR-GRPO, an approach to integrate online RL training into autoregressive (AR) image generation models. We adapt the Group Relative…

Class-incremental learning is a challenging problem, where the goal is to train a model that can classify data from an increasing number of classes over time. With the advancement of vision-language pre-trained models such as CLIP, they…