Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2602. 18037v2 Announce Type: replace-cross Abstract: Reinforcement Learning from Human Feedback (RLHF) or Verifiable Rewards (RLVR) are two key steps in the post-training of modern Language Models (LMs).
arXiv:2604. 16926v2 Announce Type: replace-cross Abstract: Electroencephalography (EEG) foundation models have shown strong potential for learning generalizable representations from large-scale neural data, yet their clinical deployment is hindered by distribution shifts across clinical settings, devices, and populations.
arXiv:2603. 22770v2 Announce Type: replace-cross Abstract: The deployment of deep neural networks (DNNs) in safety-critical edge environments necessitates robustness against hardware-induced bit-flip errors.
arXiv:2508. 21010v3 Announce Type: replace-cross Abstract: Existing Causal-Why Video Question Answering (VideoQA) models often struggle with higher-order reasoning, relying on opaque, monolithic pipelines that entangle video understanding, causal inference, and answer generation.
arXiv:2607. 03248v1 Announce Type: cross Abstract: The alignment of large language models with human preferences is commonly achieved through Reinforcement Learning from Human Feedback or Direct Preference Optimization.
arXiv:2607. 03166v1 Announce Type: cross Abstract: Template-based contrastive synthesis is scalable, but its candidates often differ only in a few entity-slots while sequence-level optimization spreads supervision over mostly shared templates.
arXiv:2607. 02615v1 Announce Type: cross Abstract: Generating structured artifacts with Large Language Models - e.
arXiv:2607. 04241v1 Announce Type: cross Abstract: Plasma disruption is a critical threat to tokamak safety.
arXiv:2607. 02572v1 Announce Type: cross Abstract: In multi-source image fusion scenarios, heterogeneous inputs are typically driven by distinct generative mechanisms and can be viewed as a composition of multiple causal systems.
arXiv:2607. 04270v1 Announce Type: cross Abstract: Large language models (LLMs) have recently emerged as powerful backbones for recommender systems by reformulating recommendation as a token-level generation task.
arXiv:2607. 02561v1 Announce Type: cross Abstract: Consumer depth sensors such as the LiDAR scanner on recent iPhones provide metric range, but their useful range is short and their returns are sparse.
arXiv:2607. 05055v1 Announce Type: new Abstract: Healthcare appointment scheduling remains a persistent operational bottleneck, driven by manual coordination, fragmented legacy systems, and high administrative overhead.
arXiv:2607. 04750v1 Announce Type: new Abstract: We present FM-ChangeNet, a pathwise-supervised framework for change detection that reformulates bi-temporal reasoning as continuous transport in feature space rather than static endpoint comparison.
arXiv:2607. 04718v1 Announce Type: new Abstract: Deep research agents decompose open-ended queries into subtasks, retrieve web evidence over multiple rounds, and synthesize long-form reports.
arXiv:2607. 04265v1 Announce Type: cross Abstract: World-action (WA) models can generate long-horizon action chunks for general-purpose robotic manipulation, but they remain vulnerable to calibration, perception, and contact-dynamics errors in real-world precision tasks, often failing in the final few millimeters of alignment or insertion.
arXiv:2607. 03386v1 Announce Type: new Abstract: Agentic AI systems are increasingly used to edit, refine, and repair decision policies, but evaluating these edits is difficult when per-state expert action labels are unavailable.
arXiv:2607. 04277v1 Announce Type: cross Abstract: The pursuit of self-evolving AI raises a critical question: when is autonomous self-improvement sustainable rather than degenerative?
arXiv:2509. 14026v2 Announce Type: replace-cross Abstract: Variational quantum circuits (VQCs) are central to quantum machine learning, while recent progress in Kolmogorov-Arnold networks (KANs) highlights the power of learnable activation functions.
arXiv:2607. 04487v1 Announce Type: cross Abstract: Neural autoregressive solvers for the Multi-Attribute Vehicle Routing Problem (MAVRP) reach competitive cost but offer no per-step justification, a problem when dispatchers must validate, accept, or compare them.
arXiv:2607. 04607v1 Announce Type: cross Abstract: The rapid advancement of AI-generated videos poses increasing security risks and calls for robust detectors with strong cross-domain generalization.