Related papers: Probing Routing-Conditional Calibration in Attenti…

Deep reinforcement learning (RL) algorithms are predominantly evaluated by comparing their relative performance on a large suite of tasks. Most published results on deep RL benchmarks compare point estimates of aggregate performance such as…

Clinical monitoring of functional decline in ALS relies on periodic assessments that may miss critical changes occurring between visits. To address this gap, semi-supervised regression models were developed to estimate rates of decline in a…

Robots operating in shared workspaces must maintain safe coordination with other agents whose behavior may change during task execution. When a collaborating agent switches strategy mid-episode, continuing under outdated assumptions can…

The fundamental design of wireless systems toward AI-native 6G and beyond is driven by the need for ever-increasing demand of mobile data traffic, extreme spectral efficiency, and adaptability across diverse service scenarios. To overcome…

Recent studies have shown that deep neural networks are not well-calibrated and often produce over-confident predictions. The miscalibration issue primarily stems from using cross-entropy in classifications, which aims to align predicted…

In this paper, we study the inference accuracy of the Resistive Random Access Memory (ReRAM) neuromorphic circuit due to stuck-at faults (stuck-on, stuck-off, and stuck at a certain resistive value). A simulation framework using Python is…

Agentic memory enables LLMs to persist information beyond a single context window and reuse it in later decisions, but it also introduces a new vulnerability: spurious correlations, where retrieved memory carries miscorrelated evidence and…

Post-training large language models (LLMs) often suffers from catastrophic forgetting, where improvements on a target objective degrade previously acquired capabilities. Recent evidence suggests that this phenomenon is primarily driven by…

Ensuring reliability in modern software systems requires rigorous pre-production testing across highly heterogeneous and evolving environments. Because exhaustive evaluation is infeasible, practitioners must decide how to allocate limited…

Virtual cell models aim to enable in silico experimentation by predicting how cells respond to genetic, chemical, or cytokine perturbations from single-cell measurements. In practice, however, large-scale perturbation prediction remains…

Do reasoning models have "Aha!" moments? Prior work suggests that models like DeepSeek-R1-Zero undergo sudden mid-trace realizations that lead to accurate outputs, implying an intrinsic capacity for self-correction. Yet, it remains unclear…

Emerging deployments of Generative AI increasingly execute inference across decentralized and heterogeneous edge devices rather than on a single trusted server. In such environments, a single device failure or misbehavior can disrupt the…

Post-training has become essential for adapting large language models (LLMs) to complex downstream behaviors, including instruction following, preference alignment, and multi-step reasoning. Reinforcement learning with verifiable rewards…

Clinical deployment of chest radiograph classifiers requires models that can be updated as new datasets become available without retraining on previously observed data or degrading validated performance. We study a task-incremental…

Analog-Based In-Memory Computing (AIMC) inference accelerators can be used to efficiently execute Deep Neural Network (DNN) inference workloads. However, to mitigate accuracy losses, due to circuit and device non-idealities, Hardware-Aware…

Even as we engineer LLMs for alignment and safety, they often uncover biases from pre-training data's statistical regularities (from disproportionate co-occurrences to stereotypical associations mirroring human cognitive biases). This leads…

Meta-reinforcement learning (meta-RL) aims to learn from multiple training tasks the ability to adapt efficiently to unseen test tasks. Despite the success, existing meta-RL algorithms are known to be sensitive to the task distribution…

Low-rank structure is a common implicit assumption in many modern reinforcement learning (RL) algorithms. For instance, reward-free and goal-conditioned RL methods often presume that the successor measure admits a low-rank representation.…

Learning-based approaches, particularly reinforcement learning (RL), have become widely used for developing control policies for autonomous agents, such as locomotion policies for legged robots. RL training typically maximizes a predefined…

Adversarial training (AT) and its variants have spearheaded progress in improving neural network robustness to adversarial perturbations and common corruptions in the last few years. Algorithm design of AT and its variants are focused on…