Related papers: Demystifying OPD: Length Inflation and Stabilizati…

Vision-based deep reinforcement learning (RL) typically obtains performance benefit by using high capacity and relatively large convolutional neural networks (CNN). However, a large network leads to higher inference costs (power, latency,…

We present DistillFlow, a knowledge distillation approach to learning optical flow. DistillFlow trains multiple teacher models and a student model, where challenging transformations are applied to the input of the student model to generate…

Adversarial training is a widely adopted strategy to bolster the robustness of neural network models against adversarial attacks. This paper revisits the fundamental assumptions underlying image classification and suggests that representing…

Model distillation has been a popular method for producing interpretable machine learning. It uses an interpretable "student" model to mimic the predictions made by the black box "teacher" model. However, when the student model is sensitive…

DEtection TRansformer (DETR) becomes a dominant paradigm, mainly due to its common architecture with high accuracy and no post-processing. However, DETR suffers from unstable training dynamics. It consumes more data and epochs to converge…

Online continual learning (OCL) seeks to learn new tasks from data streams that appear only once, while retaining knowledge of previously learned tasks. Most existing methods rely on replay, focusing on enhancing memory retention through…

Reinforcement learning has been central to recent advances in large language model reasoning, but most algorithms rely on on-policy training that demands fresh rollouts at every update, limiting efficiency and scalability. Asynchronous RL…

Causal language models have demonstrated remarkable capabilities, but their size poses significant challenges for deployment in resource-constrained environments. Knowledge distillation, a widely-used technique for transferring knowledge…

Offline reinforcement learning often requires a quality dataset that we can train a policy on. However, in many situations, it is not possible to get such a dataset, nor is it easy to train a policy to perform well in the actual environment…

Consistency models have been proposed for fast generative modeling, achieving results competitive with diffusion and flow models. However, these methods exhibit inherent instability and limited reproducibility when training from scratch,…

Knowledge distillation is used, in generative language modeling, to train a smaller student model using the help of a larger teacher model, resulting in improved capabilities for the student model. In this paper, we formulate a more general…

Central to the development of universal learning systems is the ability to solve multiple tasks without retraining from scratch when new data arrives. This is crucial because each task requires significant training time. Addressing the…

Accurate prediction of future trajectories of traffic agents is essential for ensuring safe autonomous driving. However, partially observed trajectories can significantly degrade the performance of even state-of-the-art models. Previous…

Prior research on out-of-distribution detection (OoDD) has primarily focused on single-modality models. Recently, with the advent of large-scale pretrained vision-language models such as CLIP, OoDD methods utilizing such multi-modal…

Safe Reinforcement Learning (RL) aims to find a policy that achieves high rewards while satisfying cost constraints. When learning from scratch, safe RL agents tend to be overly conservative, which impedes exploration and restrains the…

Offline reinforcement learning (RL) is challenged by the distributional shift between learning policies and datasets. To address this problem, existing works mainly focus on designing sophisticated algorithms to explicitly or implicitly…

Dataset Distillation (DD), a newly emerging field, aims at generating much smaller but efficient synthetic training datasets from large ones. Existing DD methods based on gradient matching achieve leading performance; however, they are…

Recent advances in rule-based reinforcement learning (RL) have significantly improved the reasoning capability of language models (LMs) with rule-based rewards. However, existing RL methods -- such as GRPO, REINFORCE++, and RLOO -- often…

Knowledge distillation (KD) is widely used for compressing a teacher model to a smaller student model, reducing its inference cost and memory footprint while preserving model capabilities. However, current KD methods for auto-regressive…

On-policy reinforcement learning methods like GRPO suffer from mode collapse: they exhibit reduced solution diversity, concentrating probability mass on a single solution once discovered and ceasing exploration of alternative strategies. We…