Related papers: Easy Samples Are All You Need: Self-Evolving LLMs …

We propose Reinforcement Learning with Explicit Human Values (RLEV), a method that aligns Large Language Model (LLM) optimization directly with quantifiable human value signals. While Reinforcement Learning with Verifiable Rewards (RLVR)…

Sample inefficiency is a long-lasting challenge in deep reinforcement learning (DRL). Despite dramatic improvements have been made, the problem is far from being solved and is especially challenging in environments with sparse or delayed…

Like humans, deep networks have been shown to learn better when samples are organized and introduced in a meaningful order or curriculum. Conventional curriculum learning schemes introduce samples in their order of difficulty. This forces…

Self-training is a simple yet effective method within semi-supervised learning. The idea is to iteratively enhance training data by adding pseudo-labeled data. Its generalization performance heavily depends on the selection of these…

Instruction-driven image editing with unified multimodal generative models has advanced rapidly, yet their underlying visual reasoning remains limited, leading to suboptimal performance on reasoning-centric edits. Reinforcement learning…

Meta-reinforcement learning (RL) methods can meta-train policies that adapt to new tasks with orders of magnitude less data than standard RL, but meta-training itself is costly and time-consuming. If we can meta-train on offline data, then…

Existing adversarial learning approaches mostly use class labels to generate adversarial samples that lead to incorrect predictions, which are then used to augment the training of the model for improved robustness. While some recent works…

Reinforcement learning (RL) has demonstrated potential for enhancing reasoning in large language models (LLMs). However, effective RL training, which requires medium-difficulty training samples, faces two fundamental challenges: Effective…

Due to the limited and even imbalanced data, semi-supervised semantic segmentation tends to have poor performance on some certain categories, e.g., tailed categories in Cityscapes dataset which exhibits a long-tailed label distribution.…

Existing methods to enhance the reasoning capability of large language models predominantly rely on supervised fine-tuning (SFT) followed by reinforcement learning (RL) on reasoning-specific data. These approaches critically depend on…

The cost of annotating transcriptions for large speech corpora becomes a bottleneck to maximally enjoy the potential capacity of deep neural network-based automatic speech recognition models. In this paper, we present a new training…

In this work, we propose a simple yet effective semi-supervised learning approach called Augmented Distribution Alignment. We reveal that an essential sampling bias exists in semi-supervised learning due to the limited number of labeled…

Learning to solve tasks from a sparse reward signal is a major challenge for standard reinforcement learning (RL) algorithms. However, in the real world, agents rarely need to solve sparse reward tasks entirely from scratch. More often, we…

Offline reinforcement learning (RL) learns policies from a fixed dataset, but often requires large amounts of data. The challenge arises when labeled datasets are expensive, especially when rewards have to be provided by human labelers for…

We motivate weakly supervised learning as an effective learning paradigm for problems where curating perfectly annotated datasets is expensive and may require domain expertise such as fine-grained classification. We focus on Partial Label…

Reinforcement learning with verifiable rewards (RLVR) has proven effective in training large reasoning models (LRMs) by leveraging answer-verifiable signals to guide policy optimization, which, however, suffers from high annotation costs.…

Reinforcement learning from verifiable rewards (RLVR) has shown strong promise for LLM reasoning, but outcome-based RLVR remains inefficient on hard problems because correct final-answer rollouts are rare and sample-level credit assignment…

Active learning is an iterative labeling process that is used to obtain a small labeled subset, despite the absence of labeled data, thereby enabling to train a model for supervised tasks such as text classification. While active learning…

Recent trends in Reinforcement Learning (RL) highlight the need for agents to learn from reward-free interactions and alternative supervision signals, such as unlabeled or incomplete demonstrations, rather than relying solely on explicit…

As Large Language Models (LLMs) are pre-trained on ultra-large-scale corpora, the problem of data contamination is becoming increasingly serious, and there is a risk that static evaluation benchmarks overestimate the performance of LLMs. To…