Related papers: Learning from Language Feedback via Variational Po…

Applying probabilistic models to reinforcement learning (RL) enables the application of powerful optimisation tools such as variational inference to RL. However, existing inference frameworks and their algorithms pose significant challenges…

Reinforcement learning (RL) can be used to improve the policy (denoiser) of diffusion large language models (dLLMs), while being hindered by the intractability of the policy likelihood. A dominant and efficient family of methods replaces…

Recent advances in few-step diffusion distillation have enabled efficient image generation, yet aligning these models with human preferences remains challenging. We propose Reward-Tilted Distribution Matching Distillation (RTDMD), a…

Effective reinforcement learning (RL) for complex stochastic systems requires leveraging historical data collected in previous iterations to accelerate policy optimization. Classical experience replay treats all past observations uniformly…

Knowledge Distillation (KD) can transfer the reasoning abilities of large models to smaller ones, which can reduce the costs to generate Chain-of-Thoughts for reasoning tasks. KD methods typically ask the student to mimic the teacher's…

Large Language Models (LLMs) continue to set new standards in knowledge-intensive and complex reasoning tasks, yet their high computational demands limit widespread adoption. While distilling large models into smaller ones offers a…

Knowledge Distillation (KD) for Large Language Models (LLMs) has become increasingly important as models grow in size and complexity. While existing distillation approaches focus on imitating teacher behavior, they often overlook the…

Previous studies have pointed out that visual question answering (VQA) models are prone to relying on language priors for answer predictions. In this context, predictions often depend on linguistic shortcuts rather than a comprehensive…

Self-supervised speech representation learning enables the extraction of meaningful features from raw waveforms. These features can then be efficiently used across multiple downstream tasks. However, two significant issues arise when…

Growing efforts to improve knowledge distillation (KD) in large language models (LLMs) replace dense teacher supervision with selective distillation, which uses a subset of token positions, vocabulary classes, or training samples for…

In recent years, humanoid robots have garnered significant attention from both academia and industry due to their high adaptability to environments and human-like characteristics. With the rapid advancement of reinforcement learning,…

Partial observability is a notorious challenge in reinforcement learning (RL), due to the need to learn complex, history-dependent policies. Recent empirical successes have used privileged expert distillation--which leverages availability…

Large language models (LLMs) excel at logical and algorithmic reasoning, yet their emotional intelligence (EQ) still lags far behind their cognitive prowess. While reinforcement learning from verifiable rewards (RLVR) has advanced in other…

Language models trained with reinforcement learning (RL) can engage in reward hacking--the exploitation of unintended strategies for high reward--without revealing this behavior in their chain-of-thought reasoning. This makes the detection…

Reinforcement learning has emerged as a powerful tool for improving diffusion-based text-to-image models, but existing methods are largely limited to single-task optimization. Extending RL to multiple tasks is challenging: joint…

While deep reinforcement learning has achieved promising results in challenging decision-making tasks, the main bones of its success --- deep neural networks are mostly black-boxes. A feasible way to gain insight into a black-box model is…

Safe reinforcement learning (RL) aims to learn policies that satisfy certain constraints before deploying them to safety-critical applications. Previous primal-dual style approaches suffer from instability issues and lack optimality…

Large language models (LLMs) have achieved remarkable progress in mathematical reasoning, but this ability is not equally accessible across languages. Especially low-resource languages exhibit much lower reasoning performance. To address…

This paper proposes the DistillCSE framework, which performs contrastive learning under the self-training paradigm with knowledge distillation. The potential advantage of DistillCSE is its self-enhancing feature: using a base model to…

The success of Large Language Models (LLMs) has inspired the development of Multimodal Large Language Models (MLLMs) for unified understanding of vision and language. However, the increasing model size and computational complexity of…