Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv:2507. 06637v2 Announce Type: replace-cross Abstract: We propose Path Signatures Logistic Regression (PSLR), a semi-parametric framework for classifying vector-valued functional data with scalar covariates.
arXiv:2607. 03339v1 Announce Type: new Abstract: Learning dissipative dynamics from discrete observations is essential for reliable long-horizon prediction and physically meaningful parameter identification.
arXiv:2607. 03397v1 Announce Type: new Abstract: Text-to-Image diffusion models often propagate harmful bias inherited from the training data.
arXiv:2607. 03050v1 Announce Type: cross Abstract: Omni modal large language models (OmniLLMs) have attracted wide attention for their ability to jointly process audio and video, but they generate large token sequences under audio-visual inputs, leading to substantial inference cost.
arXiv:2607. 03613v1 Announce Type: new Abstract: We study the implicit bias of noisy stochastic gradient descent in training wide two-layer ReLU networks for multivariate regression.
arXiv:2607. 02599v1 Announce Type: cross Abstract: Tool-using LLM agents are usually evaluated by final-answer correctness or LLM judges.
arXiv:2607. 03624v1 Announce Type: cross Abstract: This paper challenges the assumption that vision-language models (VLMs) require fixed patch-based 2D vision features.
arXiv:2607. 03847v1 Announce Type: new Abstract: Understanding why discovered scenarios become critical in scenario-based testing is essential for effectively leveraging them in decision-making systems.
arXiv:2607. 05306v1 Announce Type: new Abstract: Integrating complex, multi-omics data presents significant challenges.
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. 04906v1 Announce Type: new Abstract: Under the Shipping 4.
arXiv:2607. 03213v1 Announce Type: cross Abstract: We present OpenGlass, an open-source, privacy-oriented, local-first system for low-latency multimodal visual assistance, with a primary focus on blind and low-vision users.
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:2602. 20629v3 Announce Type: replace Abstract: As Large Language Models (LLMs) saturate elementary benchmarks, the research frontier has shifted from generation to the reliability of automated evaluation.
arXiv:2512. 14991v2 Announce Type: replace Abstract: We study reinforcement learning for controlled diffusion processes with unbounded continuous state spaces, bounded continuous actions, and polynomially growing rewards: settings that arise naturally in finance, economics, and operations research.
arXiv:2607. 02615v1 Announce Type: cross Abstract: Generating structured artifacts with Large Language Models - e.
arXiv:2607. 02687v1 Announce Type: cross Abstract: Intrusion detection systems are often trained under static benchmark conditions, although deployed network environments are affected by traffic drift, sensor noise, changing workloads, and evolving attack behaviour.
arXiv:2607. 01983v1 Announce Type: cross Abstract: Robust 3D object detection under adverse weather remains a critical hurdle for autonomous driving.
arXiv:2511. 06148v4 Announce Type: replace-cross Abstract: As large language models (LLMs) are adopted into frameworks that grant them the capacity to make real decisions, it is increasingly important to ensure that they are unbiased.
arXiv:2604. 19139v3 Announce Type: replace-cross Abstract: As Large Language Models (LLMs) continue to evolve through alignment techniques such as Reinforcement Learning from Human Feedback (RLHF) and Constitutional AI, a growing and increasingly conspicuous phenomenon has emerged: the proliferation of verbal tics--repetitive, formulaic linguistic patterns that pervade model outputs.