Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2608. 12821v1 Announce Type: new Abstract: Large language models (LLMs) remain vulnerable to harmful requests and jailbreak attacks.
arXiv:2412. 17228v4 Announce Type: replace Abstract: Background: Clinical trials are essential to advancing cancer treatments, but fewer than 10% of adults with cancer enroll in therapeutic trials.
arXiv:2608. 12645v1 Announce Type: new Abstract: LLM judges have become central infrastructure for model evaluations, online grading, and reward modeling.
arXiv:2608. 12791v1 Announce Type: cross Abstract: What a finite learning device has recorded and what will hold value for it on future tasks are not the same quantity.
arXiv:2608. 13482v1 Announce Type: cross Abstract: As language-model-based AI is increasingly deployed in autonomous settings, aligning its goals and values with those of humans becomes critical.
arXiv:2601. 21628v2 Announce Type: replace-cross Abstract: Diffusion models have achieved remarkable progress in image generation, but their increasing deployment raises serious concerns about privacy and copyright.
arXiv:2608. 13341v1 Announce Type: cross Abstract: Infrared (IR) spectroscopy is widely used for chemical sensing, but extracting reliable chemical information from spectra remains challenging.
arXiv:2608. 13513v1 Announce Type: cross Abstract: Tabular-to-image methods have emerged as novel approaches to leverage the high predictive performance of convolutional neural networks and vision transformers.
arXiv:2608. 12751v1 Announce Type: cross Abstract: Logic synthesis transforms RTL designs into gate-level netlists, where PPA results are highly sensitive to the choice of optimization commands, making synthesis tuning both high-dimensional and expensive.
arXiv:2608. 12912v1 Announce Type: new Abstract: This paper considers the overestimation bias problem of Q-learning in the setting of a large action space, for the purpose of relieving the bottleneck of existing methods.
arXiv:2608. 13190v1 Announce Type: new Abstract: Group-robust learning is crucial for maintaining accuracy on rare subpopulations when training-group labels are unavailable.
arXiv:2608. 13039v1 Announce Type: new Abstract: The paper introduces the ante-hoc Explainable AI methodology to assess the global feature importance of the Machine Learning models used for heat demand forecasting in intelligent control of District Heating Systems, with motivation to facilitate their interpretability and trustworthiness, hence addressing the challenges related to adherence to communal standards, customer satisfaction and liability risks.
arXiv:2602. 05379v2 Announce Type: replace-cross Abstract: Effective reinforcement learning (RL) for complex stochastic systems requires leveraging historical data to improve sample efficiency and accelerate policy optimization.
arXiv:2607. 27995v2 Announce Type: replace-cross Abstract: Adversarial training can improve the robustness of predictive models to bounded perturbations, often at the cost of statistical efficiency.
arXiv:2608. 12717v1 Announce Type: new Abstract: Mechanistic interpretability of large language models lacks spatially resolved, falsifiable tools for testing whether internal components are specialized for distinct cognitive operations.
arXiv:2506. 01568v4 Announce Type: replace Abstract: Being able to solve a task in diverse ways makes agents more robust to task variations and less prone to local optima.
arXiv:2608. 12535v1 Announce Type: new Abstract: Deep learning models are widely used for time series analysis in domains such as healthcare, finance, energy systems, and environmental monitoring.
arXiv:2605. 01928v2 Announce Type: replace Abstract: We optimize losses that jump: spiking thresholds, quantized layers, and discrete routing put jumps in the forward pass, where backpropagation does not apply.
arXiv:2608. 13453v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models have emerged as generalist robotic policies capable of following diverse language instructions and performing a wide range of manipulation tasks.
arXiv:2604. 05809v2 Announce Type: replace-cross Abstract: This paper presents Text-Guided Backdoor (TGB), an adjustable backdoor attack against multimodal pretrained models that uses natural-word triggers, namely words that can naturally occur in ordinary textual inputs.