Knowledge catalogue
arXiv:2604.14498v1 Announce Type: cross Abstract: Synthetic augmentation is increasingly used to mitigate data scarcity in financial machine learning, yet its statistical role remains poorly understoo
in 1996 mitzenmacher showed that sampling two backends and picking the better one drops max load exponentially vs. random selection one extra comparison. that's the whole trick we built pinecone assis
arXiv:2601.11227v2 Announce Type: replace Abstract: Output diversity is crucial for Large Language Models as it underpins pluralism and creativity. In this work, we reveal that controlling the languag
arXiv:2604.14717v1 Announce Type: cross Abstract: Persistent language-model agents increasingly combine tool use, tiered memory, reflective prompting, and runtime adaptation. In such systems, behavior
arXiv:2604.15311v1 Announce Type: new Abstract: This paper focuses on the alignment of flow matching models with human preferences. A promising way is fine-tuning by directly backpropagating reward gr
arXiv:2604.14811v1 Announce Type: new Abstract: Ad hoc wireless networks exhibit complex, innate and coupled dynamics: node mobility, energy depletion and topology change that are difficult to model a
arXiv:2604.14568v1 Announce Type: cross Abstract: Visual reasoning models (VRMs) have recently shown strong cross-modal reasoning capabilities by integrating visual perception with language reasoning.
arXiv:2604.15210v1 Announce Type: cross Abstract: Humor is one of the few cognitive tasks where getting the reasoning right matters as much as getting the answer right. While recent work evaluates hum
arXiv:2604.14564v1 Announce Type: cross Abstract: Reinforcement learning (RL) paradigms have demonstrated strong performance on reasoning-intensive tasks such as code generation. However, limited traj
arXiv:2604.14698v1 Announce Type: new Abstract: Diffusion models have recently emerged as expressive policy representations for online reinforcement learning (RL). However, their iterative generative
arXiv:2604.15190v1 Announce Type: cross Abstract: Simulating group-level user behavior enables scalable counterfactual evaluation of merchant strategies without costly online experiments. However, bui
arXiv:2604.14249v1 Announce Type: new Abstract: We introduce Metric-Aware Principal Component Analysis (MAPCA), a unified framework for scale-invariant representation learning based on the generalised
arXiv:2512.05024v3 Announce Type: replace-cross Abstract: As generative AI models are increasingly used to simulate real-world systems, quantifying the ``sim-to-real'' gap is critical. For each input
arXiv:2604.14808v1 Announce Type: new Abstract: Machine unlearning for large language models (LLMs) aims to remove targeted knowledge while preserving general capability. In this paper, we recast LLM
arXiv:2509.23468v3 Announce Type: replace-cross Abstract: Effectively integrating diverse sensory modalities is crucial for robotic manipulation. However, the typical approach of feature concatenation
arXiv:2601.15488v2 Announce Type: replace Abstract: Large Language Models (LLMs) exhibit social biases, which can lead to harmful stereotypes and unfair outcomes. We propose extbf{Multi-Persona Thinki
arXiv:2604.14908v1 Announce Type: new Abstract: We study downlink beam and rate adaptation in a multi-user mmWave MISO system where multiple base stations (BSs), each using analog beamforming from fin
arXiv:2604.14706v1 Announce Type: new Abstract: Recent advances in 3D Gaussian Splatting (3DGS) have enabled highly efficient and photorealistic novel view synthesis. However, segmenting objects accur
arXiv:2604.14595v1 Announce Type: new Abstract: This position paper argues that recent progress with diversity in NLP is disproportionately concentrated on a small number of areas surrounding fairness
arXiv:2601.08310v2 Announce Type: replace Abstract: Recent Large Reasoning Models (LRMs) achieve strong performance by leveraging long-form Chain-of-Thought (CoT) reasoning, but uniformly applying ove
arXiv:2505.20761v3 Announce Type: replace Abstract: While the performance of machine learning systems has experienced significant improvement in recent years, relatively little attention has been paid
arXiv:2603.13683v2 Announce Type: replace Abstract: Although debiased large language models (LLMs) excel at handling known or low-bias prompts, they often fail on unfamiliar and high-bias prompts. We
arXiv:2604.14352v1 Announce Type: cross Abstract: Online A/B testing at scale relies on proxy metrics -- short-term, easily-measured signals used in place of slow-moving long-term outcomes. When the p
arXiv:2604.14634v1 Announce Type: new Abstract: Multiple choice evaluation is widely used for benchmarking large language models, yet near ceiling accuracy in low option settings can be sustained by s
arXiv:2604.14175v1 Announce Type: new Abstract: We present a unified system addressing both Subtask 3 (answer generation) and Subtask 4 (evidence sentence alignment) of the ArchEHR-QA Shared Task. For
arXiv:2604.15281v1 Announce Type: new Abstract: 3D policy learning promises superior generalization and cross-embodiment transfer, but progress has been hindered by training instabilities and severe o
arXiv:2604.14951v1 Announce Type: cross Abstract: Tool learning with foundation models aims to endow AI systems with the ability to invoke external resources -- such as APIs, computational utilities,
arXiv:2604.14265v1 Announce Type: new Abstract: We study behavior-regularized reinforcement learning (RL), where regularization toward a reference distribution (the dataset in offline RL or the base m
arXiv:2604.14910v1 Announce Type: new Abstract: Achieving high-fidelity generation in extremely few sampling steps has long been a central goal of generative modeling. Existing approaches largely rely
arXiv:2604.14353v1 Announce Type: new Abstract: Localization of autonomous mobile robots (AMRs) in enclosed or semi-enclosed environments such as offices, hotels, hospitals, indoor parking facilities,
arXiv:2604.14373v1 Announce Type: new Abstract: Rural environmental risks are shaped by place-based conditions (e.g., housing quality, road access, land-surface patterns), yet standard vulnerability i
arXiv:2604.14474v1 Announce Type: new Abstract: Traditional esports scouting workflows rely heavily on manual video review and aggregate performance metrics, which often fail to capture the nuanced de
arXiv:2604.14672v1 Announce Type: new Abstract: Large language models (LLMs) are being increasingly used in urban planning, but since gendered space theory highlights how gender hierarchies are embedd
arXiv:2604.14379v1 Announce Type: cross Abstract: Reinforcement learning (RL) has emerged as a powerful tool for aligning diffusion models with human preferences, typically by optimizing a single rewa
arXiv:2604.14631v1 Announce Type: new Abstract: Effective code generation requires both model capability and a problem representation that carefully structures how models reason and plan. Existing app
arXiv:2604.14176v1 Announce Type: new Abstract: Generalized Category Discovery (GCD) leverages labeled data to categorize unlabeled samples from known or unknown classes. Most previous methods jointly
arXiv:2604.14807v1 Announce Type: cross Abstract: The rapid integration of large language models (LLMs) into everyday workflows has transformed how individuals perform cognitive tasks such as writing,
arXiv:2604.14197v1 Announce Type: new Abstract: Large language model (LLM) performance depends heavily on prompt design, yet prompt construction is often described and applied inconsistently. Our purp
“The sharpest drop came from people who used the model for direct answers, not from those who used it more like a hint system, which suggests the real issue is not AI exposure itself but replacing eff
arXiv:2512.03048v4 Announce Type: replace-cross Abstract: Static content-based AI value alignment is insufficient for robust alignment under capability scaling, distributional shift, and increasing au
arXiv:2603.18373v2 Announce Type: replace Abstract: When VLMs answer correctly, do they genuinely rely on visual information or exploit language shortcuts? We introduce the Tri-Layer Diagnostic Framew
arXiv:2506.09457v3 Announce Type: replace Abstract: Direct Alignment Algorithms (DAAs), such as Direct Preference Optimization (DPO) and Simple Preference Optimization (SimPO), have emerged as efficie
arXiv:2511.14178v2 Announce Type: replace Abstract: Vision-Language-Action (VLA) models have demonstrated significant potential in real-world robotic manipulation. However, pre-trained VLA policies st
arXiv:2604.13715v1 Announce Type: cross Abstract: Large Audio-Language Models (LALMs) enable general audio understanding and demonstrate remarkable performance across various audio tasks. However, the
arXiv:2604.14787v1 Announce Type: cross Abstract: Network Digital Twins (NDTs) enable safe what-if analysis for 6G cloud-edge infrastructures, but adoption is often limited by fragmented workflows fro
arXiv:2604.14967v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) extends Large Vision-Language Models (LVLMs) with external visual knowledge. However, existing visual RAG systems t
arXiv:2604.15196v1 Announce Type: new Abstract: We propose a novel hierarchical spatiotemporal vector quantization framework for unsupervised skeleton-based temporal action segmentation. We first intr
arXiv:2604.14765v1 Announce Type: new Abstract: We present a geometric framework for Reinforcement Learning (RL) that views policies as maps into the Wasserstein space of action probabilities. First,
arXiv:2604.15038v1 Announce Type: cross Abstract: The evaluation of fairness in machine learning systems has become a central concern in high-stakes applications, including biometric recognition, heal
arXiv:2604.14333v1 Announce Type: new Abstract: Key Opinion Leader (KOL) discourse on social media is widely consumed as investment guidance, yet turning it into executable trading strategies without
arXiv:2604.15280v1 Announce Type: new Abstract: Understanding emotions is a fundamental ability for intelligent systems to be able to interact with humans. Vision-language models (VLMs) have made trem
arXiv:2510.23853v3 Announce Type: replace Abstract: Large language model (LLM) agents are increasingly used to interact with and execute tasks in dynamic environments. However, a critical yet overlook
arXiv:2604.13240v1 Announce Type: new Abstract: Mapping the spatial distribution of species is essential for conservation policy and invasive species management. Species distribution models (SDMs) are
arXiv:2604.13645v1 Announce Type: cross Abstract: Co-training, which combines limited in-domain real-world data with abundant surrogate data such as simulation or cross-embodiment robot data, is widel
arXiv:2604.13057v1 Announce Type: new Abstract: For millions of users in developing economies who depend on mobile banking as their primary gateway to financial services, app quality directly shapes f
A 'race' implies that it is something that is worth 'winning', which is not the case for superintelligence. Whoever finished first is just the first to trigger irrecoverable catastrophe. 'There is no
arXiv:2604.06168v2 Announce Type: replace Abstract: World action models (WAMs) have emerged as a promising direction for robot policy learning, as they can leverage powerful video backbones to model t
arXiv:2508.00555v2 Announce Type: replace-cross Abstract: Jailbreaking is an essential adversarial technique for red-teaming these models to uncover and patch security flaws. However, existing jailbre
Three major advertising companies—Dentsu, Publicis, and WPP—settled with the Federal Trade Commission over allegations they colluded on anti-misinformation policies that reduced ad revenue for conserv
arXiv:2604.13495v1 Announce Type: new Abstract: Alzheimer's disease (AD) progresses heterogeneously across individuals, motivating subject-specific synthesis of follow-up magnetic resonance imaging (M