Knowledge catalogue
arXiv:2605.12112v1 Announce Type: new Abstract: RLHF is widely used to align flow-matching text-to-image models with human preferences, but often leads to severe diversity collapse after fine-tuning.
arXiv:2605.11240v1 Announce Type: cross Abstract: Generative AI models differ from traditional machine learning tools in that they allow users to provide as much or as little information as they choos
arXiv:2605.12090v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models have achieved strong semantic generalization for embodied policy learning, yet they learn reactive observation-to-
arXiv:2605.11435v1 Announce Type: new Abstract: In this paper, we propose a zero-reference diffusion-based framework, named ZeroIDIR, for illumination degradation image restoration, which decouples th
arXiv:2605.09342v1 Announce Type: cross Abstract: Autonomous drone fleets have immense potential in medical supply delivery during disaster incident response. However, coordinating multiple drones in
arXiv:2601.12374v2 Announce Type: replace-cross Abstract: Existing approaches to bias evaluation in large language models (LLMs) trade ecological validity for statistical control, relying either on ar
arXiv:2605.08946v1 Announce Type: new Abstract: Preference-conditioned multi-objective reinforcement learning aims to learn a single policy that captures trade-offs across preferences, but under nonli
arXiv:2605.08513v1 Announce Type: cross Abstract: Safety alignment in language models operates through two mechanistically distinct systems: refusal neurons that gate whether harmful knowledge is expr
A true exponential! Oy. According to a new paper in The Lancet, the rate of made-up citations in biomedical papers has increased by more than 12x since 2023. https://www.thelancet.com/journals/lancet/
arXiv:2510.18184v3 Announce Type: replace-cross Abstract: Large language models (LLMs) excel at generating fluent text, but their internal reasoning remains opaque and difficult to control. Sparse aut
arXiv:2605.10315v1 Announce Type: cross Abstract: Generative tabular augmentation is appealing in data-scarce domains, yet the prevailing focus on distributional fidelity does not reliably translate i
arXiv:2605.10470v1 Announce Type: new Abstract: Super-resolution (SR) is a severely ill-posed problem with inherent ambiguity, as widely recognized in both empirical and theoretical studies. Although
arXiv:2605.09707v1 Announce Type: cross Abstract: Training neural networks to satisfy universal constraints over continuous domains poses unique challenges. Common examples include Lyapunov Neural Net
arXiv:2605.09902v1 Announce Type: new Abstract: Adversarial perturbations can mislead Multimodal Large Language Models (MLLMs) recognize a benign image as a specific target object, posing serious risk
arXiv:2602.04284v2 Announce Type: replace Abstract: Managing agent context (e.g., thought and observation) during multi-turn agent-environment interactions is an emerging strategy to improve agent eff
arXiv:2603.22868v2 Announce Type: replace-cross Abstract: Agentic computing systems, while immensely capable, raise serious security, privacy, and safety concerns. A key issue is that the full set of
arXiv:2406.12708v3 Announce Type: replace Abstract: Peer review is fundamental to the integrity and advancement of scientific publication. Traditional methods of peer review analyses often rely on exp
arXiv:2605.08480v1 Announce Type: new Abstract: Individuals with Alzheimer's disease (AD) and Alzheimer's disease-related dementia (ADRD) experience memory and thinking changes that impact their abili
arXiv:2605.08401v1 Announce Type: cross Abstract: Recent advances in large language models (LLMs) have demonstrated remarkable reasoning capabilities, largely stimulated by Reinforcement Learning with
arXiv:2605.10819v1 Announce Type: cross Abstract: Vision-language-action (VLA) models remain constrained by the scarcity of action-labeled robot data, whereas action-free videos provide abundant evide
arXiv:2605.09476v1 Announce Type: cross Abstract: Text simplification plays a crucial role in improving the accessibility and comprehensibility of written information for diverse audiences, including
arXiv:2605.10415v1 Announce Type: new Abstract: Large language models for subjectivity analysis are typically trained with aggregated labels, which compress variations in human judgment into a single
arXiv:2603.29981v2 Announce Type: replace Abstract: Reliable estimation of predictive performance is essential for spatial environmental modeling, where machine-learning models are used to generate ma
arXiv:2605.08416v1 Announce Type: new Abstract: Jurisprudence, the study of how judges should properly decide cases, and alignment, the science of getting AI models to conform to human values, share a
arXiv:2509.20294v4 Announce Type: replace Abstract: We study spectral algorithms in the setting where kernels are learned from data. We introduce the effective span dimension (ESD), an alignment-sensi
arXiv:2603.02719v2 Announce Type: replace Abstract: As artificial intelligence systems move toward clinical deployment, ensuring reliable prediction behavior is fundamental for safety-critical decisio
arXiv:2605.08269v1 Announce Type: new Abstract: Wireless capsule endoscopy (WCE) enables painless visualization of the gastrointestinal tract, but its diagnostic potential is limited by incomplete muc
arXiv:2605.09659v1 Announce Type: new Abstract: Koopman operator theory provides a powerful framework for representing nonlinear dynamics through a linear operator acting on lifted observables, enabli
arXiv:2510.13397v3 Announce Type: replace Abstract: Dropout is common in clinical studies, with up to half of patients leaving early due to side effects or other reasons. When dropout is informative (
arXiv:2508.13813v2 Announce Type: replace-cross Abstract: As AI systems increasingly rely on training data, assessing dataset trustworthiness has become critical, particularly for properties like fair
arXiv:2402.02286v4 Announce Type: replace-cross Abstract: U-shaped architectures have long dominated the field of medical image segmentation, while Transformers are widely employed for modeling long-r
arXiv:2605.09313v1 Announce Type: new Abstract: Attention sinks -- tokens that receive disproportionate attention mass -- are assumed to be functionally important in autoregressive language models, bu
arXiv:2604.02151v2 Announce Type: replace Abstract: We consider multi-objective reinforcement learning problems where objectives come from an identical family -- such as the class of reachability obje
arXiv:2511.14045v2 Announce Type: replace-cross Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has become a core training stage in recent large language models (LLMs). Its reliance on
arXiv:2605.08354v1 Announce Type: new Abstract: Aligning multimodal generative models with human preferences demands reward signals that respect the compositional, multi-dimensional structure of human
arXiv:2605.10370v1 Announce Type: new Abstract: Scientific knowledge on the Web is published as passive assertions and cannot decide when to validate evidence, reconcile contradictions, or update conf
arXiv:2605.10170v1 Announce Type: new Abstract: Urban traffic congestion presents a significant challenge for modern cities, which impacts mobility and sustainability. Traditional traffic light contro
arXiv:2605.10174v1 Announce Type: new Abstract: Through-water photogrammetry based on UAV imagery enables shallow-water bathymetry, but refraction at the air-water interface violates the straight-ray
arXiv:2605.08571v1 Announce Type: new Abstract: We introduce BEACON--Best-Effort Adaptation for Cross-Domain Co-Training--a theory-driven framework for training generative robot policies with abundant
arXiv:2605.08463v1 Announce Type: new Abstract: Autonomous AI agents are increasingly deployed in open social environments, yet the relationship between their configuration specifications and their em
arXiv:2605.10223v1 Announce Type: new Abstract: Current large language model agent frameworks prioritize autonomy but lack the governability mechanisms required for enterprise deployment. High-risk wr
arXiv:2605.09268v1 Announce Type: cross Abstract: Users interacting with Large Language Models (LLMs) in a multi-turn conversation routinely refine their requests or pivot to new topics. LLMs, however
arXiv:2605.09310v1 Announce Type: new Abstract: ESG-aware portfolio optimization is increasingly important for sustainable capital allocation, yet most learning-based methods still operationalize ESG
arXiv:2505.24859v3 Announce Type: replace-cross Abstract: Steering vectors are a lightweight method for controlling text properties by adding a learned bias to language model activations at inference
arXiv:2605.08202v1 Announce Type: cross Abstract: Offline reinforcement learning (RL) faces a critical challenge of overestimating the value of out-of-distribution (OOD) actions. Existing methods miti
arXiv:2605.09463v1 Announce Type: new Abstract: Large Language Models (LLMs) have demonstrated exceptional performance across diverse tasks. However, their deployment in long-context scenarios faces h
arXiv:2605.09153v1 Announce Type: cross Abstract: Closed-loop traffic simulation requires agents that are both scalable and behaviorally realistic. Recent self-play reinforcement learning approaches d
arXiv:2605.08558v1 Announce Type: new Abstract: As an extension of the classical multi-armed bandit problem, multi-fidelity multi-armed bandits (MF-MAB) enable individual arms to be evaluated using di
arXiv:2510.20477v2 Announce Type: replace Abstract: Exploiting unlabeled data through semi-supervised learning (SSL) or leveraging pre-trained models via fine-tuning are two prevailing paradigms for a
arXiv:2605.08716v1 Announce Type: new Abstract: Are certain cognitive biases mathematically inevitable consequences of sequential information processing? We prove that primacy effects, anchoring, and
arXiv:2512.24863v2 Announce Type: replace-cross Abstract: The world is in the grip of ecological, meaning, and language crises that are converging into a metacrisis. Big AI is accelerating them all. L
arXiv:2605.08564v1 Announce Type: new Abstract: The feedback alignment (FA) algorithm offers a biologically plausible alternative to backpropagation (BP) for training neural networks yet notably fails
arXiv:2605.08123v1 Announce Type: cross Abstract: We study long-context balanced entropic optimal transport (OT) attention on TPU hardware through a stopped-base, fixed-depth tail-refinement surrogate
arXiv:2602.07144v2 Announce Type: replace-cross Abstract: Bayesian optimization (BO) is a popular technique for sample-efficient optimization of black-box functions. In many applications, the paramete
arXiv:2605.10764v1 Announce Type: cross Abstract: Recent studies show that gradient-based universal image jailbreaks on vision-language models (VLMs) exhibit little or no cross-model transferability,
Breaking. Sam Altman himself finally confirms what I was the first to point out publicly: his indirect equity stake in OpenAI. … which he failed to acknowledge when asked about his financial interest
arXiv:2602.08616v2 Announce Type: replace-cross Abstract: Reinforcement Learning (RL) is increasingly applied to large-scale decision-making problems like logistics, scheduling, and recommender system
arXiv:2605.08721v1 Announce Type: new Abstract: While Reinforcement Learning with Verifiable Rewards (RLVR) has proven effective for closed-ended tasks, extending it to open-ended social language game
arXiv:2511.21104v3 Announce Type: replace Abstract: Large language models can generate plausible code, but remain brittle for formal verification in proof assistants such as Lean. A central scalabilit
arXiv:2605.10288v1 Announce Type: new Abstract: Stochastic bilevel optimization (SBO) has become a standard framework for hyperparameter learning, data reweighting, representation learning, and data-m