MLINFO COLLECTION
On-policy distillation has been widely adopted for alleviating the distribution mismatch of off-policy distillation. Self-distillation further removes the need for an external teacher by using the…
Vision-Language-Action (VLA) models can perform diverse manipulation tasks directly from visual observations and natural language instructions, but they remain prone to mistakes and unpredictable…
We study learning a discrete distribution under person-level differential privacy in the batched setting. Given $n$ users, each contributing $m$ i.i.d.
Purpose: To describe an evidence-aware retrieval evaluation protocol for a clinical retrieval-augmented generation (RAG) system over breast lesion management literature, addressing the dependence of…
The attention mechanism underpins modern large language models, yet their dynamics remain only partially understood. Recent perspectives interpret attention blocks as interacting particle systems,…
Control evaluations measure whether safeguards can prevent an AI model from causing undesired outcomes even when it is intentionally trying to do so. These evaluations typically use purpose-built…
Sequence compression is a fundamental operation and a critical information bottleneck in efficient language and multimodal models, and yet prevailing approaches based on pooling or learned…
Recent methods for injecting graph structure into LLM prompts include graph soft prompting, in which a graph neural network (GNN) learns graph-specific tokens that capture relational information…
Objective: Iontophoretic drug delivery has primarily relied on current modulation to regulate drug transport. Here, we investigate hydrogel geometry, microstructure, and local electric fields as…
Generating 360-degree panoramas requires both local perspective fidelity and global spherical continuity. Existing representations face a trade-off: equirectangular projection (ERP) enables seamless…
Online Policy Distillation (OPD) often outperforms offline methods such as Supervised Fine-Tuning (SFT) by training on trajectories sampled directly from the student. However, standard OPD trains the…
The rapid growth of the space economy, alongside increasing orbital congestion and debris, is driving demand for reliable on-orbit transportation of large and non-cooperative objects. Performing such…
Understanding catastrophic forgetting, in which learning new tasks degrades performance on previously learned tasks, remains a fundamental challenge in continual learning (CL). Existing theoretical…
Multi-robot coordination of nonlinear systems is naturally formulated as joint-space optimal control subject to constraints over groups of robots. Existing methods that approach joint optimality…
Machine learning has permeated material optimization, providing high value. Nevertheless, its re- liance on a high number of samples limits its applicability to relatively explored material families.
Local anomaly detection is the task of identifying spatially confined anomalous or out-of-distribution (OOD) regions within an otherwise in-distribution (ID) image. Most existing methods are designed…
Nonparametric estimation of joint probability distributions is a core problem in statistics, which is notoriously challenging with high-dimensional data. Such challenges also arise with conditional…
Users increasingly rely on AI systems for extended, multi-turn tasks, yet evidence indicates that LLM-based system performance degrades over prolonged interaction. To evaluate and improve AI…
Accurate hippocampal segmentation can be a useful tool for diagnosing and monitoring neurological conditions such as Alzheimer's disease and epilepsy. While numerous automated segmentation methods…
Multibeam imaging sonar produces intensity images degraded by coherent speckle and system-induced blur, while clean reflectivity targets are rarely available. Existing despeckling methods often rely…
Apple Silicon is among the most widely used platforms for local LLM inference, yet nearly all inference optimizations are designed and validated on server-class NVIDIA GPUs under batched serving…
Vision-Language Models (VLMs) have shown strong potential for video anomaly detection, but dense frame-level inference makes them impractical for real-time deployment. Existing acceleration commonly…
Robot world models simulate how environments evolve in response to robot actions. Latent action models enable learning dynamics from videos by encoding visual transitions as proxy actions.
Despite advances in numerical methods, non-Newtonian flow simulations remain computationally expensive because velocity and stress must be advanced together through rate- and history-dependent…