Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2610.07029v1 Announce Type: cross Abstract: Resistive random-access memory (ReRAM)-based Processing-in-Memory (PIM) accelerator is a promising platform for processing massively memory intensive...
arXiv:2610.07518v1 Announce Type: cross Abstract: Safety auditing of post-trained large language models typically relies on model behavior, requiring model execution and depending on the coverage of...
arXiv:2610.07603v1 Announce Type: cross Abstract: This article proposes Selective Affective Layer Fine-Tuning (SALFT), an efficient adaptation framework for Video Vision Transformers in player arousa...
arXiv:2610.07706v1 Announce Type: cross Abstract: Autoregressive large language models (LLMs) have rapidly advanced in capability, but their increasing scale comes with substantial computational and...
arXiv:2610.07928v1 Announce Type: cross Abstract: Dynamic multimodal learning aims to learn robust representations by adaptively modeling information discrepancies across modalities. However, existin...
arXiv:2610.08123v1 Announce Type: cross Abstract: End-to-end planners based on waypoint regression achieve strong open-loop accuracy, but they primarily learn to mimic expert geometry and remain diff...
arXiv:2610.08502v1 Announce Type: cross Abstract: Proactive power management systems reduce processor dynamic power through runtime power prediction and power-aware scheduling. Accurate, stable and l...
arXiv:2610.08541v1 Announce Type: cross Abstract: In this paper, we investigate the synthesis of Micro Neural Policies (MNP) to enable safe and robust real-time robotic control on computationally con...
arXiv:2610.08678v1 Announce Type: cross Abstract: Speculative decoding accelerates inference for a large language model (LLM), referred to as the \emph{target model}, by first using a smaller model,...
arXiv:2610.08773v1 Announce Type: cross Abstract: Web agents complete user requests by reading and acting on pages that third parties write, so an instruction planted on a page can redirect the agent...
arXiv:2605.05736v3 Announce Type: replace Abstract: Vector quantization (VQ) with autoregressive (AR) token modeling is a widely adopted and highly competitive paradigm for time-series generation. Ho...
arXiv:2605.27593v2 Announce Type: replace Abstract: Even when a tool is explicitly described as unfair and harmful to others, ostensibly safety-aligned LLM agents still voluntarily engage in secret c...
arXiv:2505.17847v3 Announce Type: replace-cross Abstract: Training time-series forecasting models poses unique challenges in loss function design. Most existing approaches adopt temporal mean squared...
arXiv:2510.24574v3 Announce Type: replace-cross Abstract: Training time-series forecasting models requires aligning the conditional distribution of model forecasts with that of the label sequence. Th...
arXiv:2511.21075v4 Announce Type: replace-cross Abstract: Engineering LLMs to accelerate life sciences research requires a robust alignment with biomedical knowledge. We observe that biomedical text...
arXiv:2610.01936v2 Announce Type: replace Abstract: Large Language Models (LLMs) have demonstrated remarkable fluency and versatility across natural language tasks but remain fundamentally limited by...
arXiv:2603.04364v2 Announce Type: replace-cross Abstract: Multimodal web agents that process both screenshots and accessibility trees are increasingly deployed to interact with web interfaces, yet th...
arXiv:2603.21276v2 Announce Type: replace-cross Abstract: The growing demand for on-device large language model (LLM) services on mobile edge devices has driven the adoption of Mixture-of-Experts (Mo...
arXiv:2605.07079v2 Announce Type: replace-cross Abstract: World models predict future transitions from observations and actions. Existing works predominantly focus on image generation only. Visual fe...
arXiv:2605.18618v3 Announce Type: replace-cross Abstract: Constrained Machine Learning (CML) enables fairness-aware training, physics-informed neural networks, and integration of symbolic domain know...