Related papers: Test-retest Reliability of Psychophysical Tasks Us…
Signal Temporal Logic (STL) is a widely recognized formal specification language to express rigorous temporal requirements on mixed analog signals produced by cyber-physical systems (CPS). A relevant problem in CPS design is how to…
Several methods have been proposed recently to learn neural network (NN) controllers for autonomous agents, with unknown and stochastic dynamics, tasked with complex missions captured by Linear Temporal Logic (LTL). Due to the…
Hallucinations are one of the major issues affecting LLMs, hindering their wide adoption in production systems. While current research solutions for detecting hallucinations are mainly based on heuristics, in this paper we introduce a…
Mechanism-targeted synthetic data is increasingly proposed as a way to steer pretraining toward desirable capabilities, but it remains unclear how such interventions should be evaluated. We study this question for in-context learning (ICL)…
In the coming years, strong gravitational lens discoveries are expected to increase in frequency by two orders of magnitude. Lens-modelling techniques are being developed to prepare for the coming massive influx of new lens data, and blind…
Two rods made from sol-gel silica have been doped with Ce ions or co-doped with Ce and Tb ions respectively. First, a thermoluminescence (TL) characterization of the trapping and luminescence parameters is carried out to understand the…
This paper presents a renewed overview of photosensor oculography (PSOG), an eye-tracking technique based on the principle of using simple photosensors to measure the amount of reflected (usually infrared) light when the eye rotates.…
Continuous monitoring of trained ML models to determine when their predictions should and should not be trusted is essential for their safe deployment. Such a framework ought to be high-performing, explainable, post-hoc and actionable. We…
Reinforcement learning (RL) is often credited with improving language model reasoning and generalization at the expense of degrading memorized knowledge. We challenge this narrative by observing that RL-enhanced models consistently…
This paper presents the approach and results of USC SAIL's submission to the Signal Processing Grand Challenge 2023 - e-Prevention (Task 2), on detecting relapses in psychotic patients. Relapse prediction has proven to be challenging,…
Post-training has greatly improved reasoning in frontier vision-language models, yet its gains for perception remain comparatively limited, creating a bottleneck for end-to-end visual reasoning. To investigate this gap, we introduce a…
In supervisory control settings, autonomous systems are not monitored continuously. Instead, monitoring often occurs at sporadic intervals within known bounds. We study the problem of deception, where an agent pursues a private objective…
We explore the possibility that an intrinsic correlation between galaxy ellipticities arising during the galaxy formation process may account for part of the shear signal recently reported by several groups engaged in weak lensing surveys.…
Despite recent successes, test-time scaling - i.e., dynamically expanding the token budget during inference as needed - remains brittle for vision-language models (VLMs): unstructured chains-of-thought about images entangle perception and…
The endeavor to understand the brain involves multiple collaborating research fields. Classically, synaptic plasticity rules derived by theoretical neuroscientists are evaluated in isolation on pattern classification tasks. This contrasts…
The application of rule-based reinforcement learning (RL) to multimodal large language models (MLLMs) introduces unique challenges and potential deviations from findings in text-only domains, particularly for perception-heavy tasks. This…
Multimodal Large Language Models (MLLMs) show reasoning promise, yet their visual perception is a critical bottleneck. Strikingly, MLLMs can produce correct answers even while misinterpreting crucial visual elements, masking these…
A proportional iterative learning control (P-ILC) for linear models of an existing hybrid stroke rehabilitation scheme is implemented for elbow extension/flexion during a rehabilitative task. Owing to transient error growth problem of…
Estimating brain age from structural MRI has emerged as a powerful tool for characterizing normative and pathological aging. In this work, we explore contrastive learning as a scalable and robust alternative to L1-supervised approaches for…
SLAC E-158 is an experiment designed to make the first measurement of parity violation in Moller scattering. E-158 will measure the right-left cross-section asymmetry, A_LR^Moller, in the elastic scattering of a 45-GeV polarized electron…