Related papers: Where Does Warm-Up Come From? Adaptive Scheduling …

We investigate random feature models in which neural networks sampled from a prescribed initialization ensemble are frozen and used as random features, with only the readout weights optimized. Adopting a statistical-physics viewpoint, we…

Classical navigation systems typically operate using a fixed set of hand-picked parameters (e.g. maximum speed, sampling rate, inflation radius, etc.) and require heavy expert re-tuning in order to work in new environments. To mitigate this…

This paper presents a new learning framework that leverages the knowledge from imitation learning, deep reinforcement learning, and control theories to achieve human-style locomotion that is natural, dynamic, and robust for humanoids. We…

We study online linear optimization with matrix variables constrained by the operator norm, a setting where the geometry renders designing data-dependent and efficient adaptive algorithms challenging. The best-known adaptive regret bounds…

Trajectory optimization for motion planning requires good initial guesses to obtain good performance. In our proposed approach, we build a memory of motion based on a database of robot paths to provide good initial guesses. The memory of…

Scale has become a main ingredient in obtaining strong machine learning models. As a result, understanding a model's scaling properties is key to effectively designing both the right training setup as well as future generations of…

Current large language models (LLMs) are constrained by human-derived training data and limited by a single level of abstraction that impedes definitive truth judgments. This paper introduces a novel framework in which AI models…

Real-life parallel machine scheduling problems can be characterized by: (i) limited information about the exact task duration at scheduling time, and (ii) an opportunity to reschedule the remaining tasks each time a task processing is…

Large language models (LLMs) are increasingly used in social science simulations. While their performance on reasoning and optimization tasks has been extensively evaluated, less attention has been paid to their ability to simulate human…

Random forest regression is a powerful non-parametric method that adapts to local data characteristics through data-driven partitioning, making it effective across diverse application domains. However, the piecewise constant nature of…

Diffusion large language models (dLLMs) generate text via iterative denoising but consistently underperform on multi-step reasoning. We hypothesize this gap stems from a coordination problem: AR models build coherence token-by-token, while…

Deep Neural Networks are well known for efficiently fitting training data, yet experiencing poor generalization capabilities whenever some kind of bias dominates over the actual task labels, resulting in models learning "shortcuts". In…

Unpredictable sensor-to-estimator delays fundamentally distort what matters for wireless remote state estimation: not just freshness, but how delay interacts with sensor informativeness and energy efficiency. In this paper, we present a…

Instruction-following language models are trained to be helpful and safe, yet their safety behavior can deteriorate under benign fine-tuning and worsen under adversarial updates. Existing defenses often offer limited protection or force a…

Due to the scarcity of high-quality data, large language models (LLMs) are often trained on mixtures of data with varying quality levels, even after sophisticated data curation. A natural approach to better leverage high-quality data is…

Learning rate scheduling is crucial for training large language models, yet understanding the optimal annealing strategies across different model configurations remains challenging. In this work, we investigate the transferability of…

We propose and analyze a process that extracts useful work from a single active particle maintained at constant temperature in a harmonic potential by measuring the relative sign of the self-propulsion and the confining force and then…

We present Dynamic Skill Adaptation (DSA), an adaptive and dynamic framework to adapt novel and complex skills to Large Language Models (LLMs). Compared with previous work which learns from human-curated and static data in random orders, we…

Features in machine learning problems are often time-varying and may be related to outputs in an algebraic or dynamical manner. The dynamic nature of these machine learning problems renders current higher order accelerated gradient descent…

Low-Rank Adaptation (LoRA) is a widely adopted parameter-efficient method for fine-tuning Large Langauge Models. It updates the weight matrix as $W=W_0+sBA$, where $W_0$ is the original frozen weight, $s$ is a scaling factor and $A$,$B$ are…