Related papers: Asyncval: A Toolkit for Asynchronously Validating …

Long-horizon robotic manipulation requires dense feedback that reflects how a task advances through its procedural stages, not merely whether the final outcome is successful. Existing reward models often rely on trajectory-level success…

Self-play with large language models has emerged as a promising paradigm for achieving self-improving artificial intelligence. However, existing self-play frameworks often suffer from optimization instability, due to (i) non-stationary…

Test-time scaling (TTS) boosts LLM reasoning via long chain-of-thought (CoT), but the linear KV-cache growth amplifies the memory-bound bottleneck of LLM decoding. Query-aware page-level sparse decoding can achieve state-of-the-art…

Dense retrievers utilize pre-trained backbone language models (e.g., BERT, LLaMA) that are fine-tuned via contrastive learning to perform the task of encoding text into sense representations that can be then compared via a shallow…

We introduce DIP, a novel unsupervised post-training method designed to enhance dense image representations in large-scale pretrained vision encoders for in-context scene understanding. Unlike prior approaches that rely on complex…

This paper shows that further evaluation metrics during model training are needed to decide about its applicability in inference. As an example, a LayoutLM-based model is trained for token classification in documents. The documents are…

Distributed training of large deep-learning models often leads to failures, so checkpointing is commonly employed for recovery. State-of-the-art studies focus on frequent checkpointing for fast recovery from failures. However, it generates…

By leveraging a dual encoder architecture, Dense Passage Retrieval (DPR) has outperformed traditional sparse retrieval algorithms such as BM25 in terms of passage retrieval accuracy. Recently proposed methods have further enhanced DPR's…

Unmanned aerial vehicles (UAVs) have been widely used in military warfare. In this paper, we formulate the autonomous motion control (AMC) problem as a Markov decision process (MDP) and propose an advanced deep reinforcement learning (DRL)…

In recent years, large-scale models have demonstrated state-of-the-art performance across various domains. However, training such models requires various techniques to address the problem of limited computing power and memory on devices…

Reinforcement Learning (RL) has become the most effective post-training approach for improving the capabilities of Large Language Models (LLMs). In practice, because of the high demands on latency and memory, it is particularly challenging…

State-of-the-art machine learning often follows a two-stage process: $(i)$~pre-training on large, general-purpose datasets; $(ii)$~fine-tuning on task-specific data. In fine-tuning, selecting training examples that closely reflect the…

Although an ever-growing number of applications employ deep learning based systems for prediction, decision-making, or state estimation, almost no certification processes have been established that would allow such systems to be deployed in…

CleanRL is an open-source library that provides high-quality single-file implementations of Deep Reinforcement Learning algorithms. It provides a simpler yet scalable developing experience by having a straightforward codebase and…

When engineers train deep learning models, they are very much 'flying blind'. Commonly used methods for real-time training diagnostics, such as monitoring the train/test loss, are limited. Assessing a network's training process solely…

Autonomous surgical execution relieves tedious routines and surgeon's fatigue. Recent learning-based methods, especially reinforcement learning (RL) based methods, achieve promising performance for dexterous manipulation, which usually…

Training a neural network (NN) typically relies on some type of curve-following method, such as gradient descent (GD) (and stochastic gradient descent (SGD)), ADADELTA, ADAM or limited memory algorithms. Convergence for these algorithms…

Averaging checkpoints along the training trajectory is a simple yet powerful approach to improve the generalization performance of Machine Learning models and reduce training time. Motivated by these potential gains, and in an effort to…

Neural networks in safety-critical applications face increasing safety and security concerns due to their susceptibility to little disturbance. In this paper, we propose DeepCDCL, a novel neural network verification framework based on the…

Despite strong generalization capabilities, Vision-Language-Action (VLA) models remain constrained by the high cost of expert demonstrations and limited real-world interaction. While online reinforcement learning (RL) has shown promise, its…