Knowledge catalogue
arXiv:2605.17187v1 Announce Type: cross Abstract: Social media are shifting towards pluralism -- community-governed platforms where groups define their own norms. What violates rules in one community
arXiv:2605.18654v1 Announce Type: cross Abstract: A fraud scorer needs to answer in under 2 ms. The best tabular foundation models (TFMs) take 151-1,275 ms on GPU. We close this gap by distilling the
arXiv:2605.18598v1 Announce Type: new Abstract: We address the fundamental question of why deep neural networks generalize by establishing a pointwise generalization theory for fully connected network
arXiv:2605.16479v1 Announce Type: cross Abstract: Job seekers often initiate search with short, underspecified queries. At LinkedIn, over 80% of job-related queries contain three or fewer keywords, ma
arXiv:2605.16588v1 Announce Type: new Abstract: Safety-critical autonomy in unstructured environments poses significant challenges for online safety certification under evolving constraints. We propos
arXiv:2605.18697v1 Announce Type: cross Abstract: Compound AI applications, which compose calls to ML models using a general-purpose programming language like Python, are widely used for a variety of
arXiv:2605.16727v1 Announce Type: new Abstract: We introduce PopuLoRA, a population-based asymmetric self-play framework for reinforcement learning with verifiable rewards (RLVR) post-training of LLMs
arXiv:2605.18672v1 Announce Type: new Abstract: This position paper argues that enforcing LLM agent safety within a single abstraction layer is not merely suboptimal but categorically insufficient for
arXiv:2605.17347v1 Announce Type: cross Abstract: When a neural network estimates someone's age from a photograph, does it process biometric data? The answer depends on whether identity-discriminative
arXiv:2509.19590v2 Announce Type: replace Abstract: Evaluations of generative models are now ubiquitous, and their outcomes critically shape public and scientific expectations of AI's capabilities. Ye
arXiv:2602.05287v2 Announce Type: replace Abstract: This position paper argues that the pursuit of 'Universal Foundation Models for Time Series' rests on a fundamental category error, mistaking a stru
arXiv:2605.18632v1 Announce Type: cross Abstract: Neural network checkpoints have quietly become a large-scale data resource: millions of trained weight vectors now exist, each encoding task-, domain-
arXiv:2605.18128v1 Announce Type: new Abstract: Existing Multivariate Time Series Anomaly Detection (MTSAD) frameworks increasingly rely on integrating Graph Neural Networks (GNNs) with sequence model
arXiv:2605.18643v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) scales language models efficiently through sparse expert activation, and its dynamic variant further reduces computation by a
arXiv:2605.18067v1 Announce Type: new Abstract: Deploying large language model (LLM) on edge device enables personalized LLM agents for various users. The growing availability of diverse personalized
arXiv:2605.16551v1 Announce Type: new Abstract: Evaluating LLM-based agents remains challenging because identifying meaningful failure cases often requires substantial human effort to design realistic
arXiv:2510.10777v3 Announce Type: replace Abstract: Optimization lies at the core of modern deep learning, yet existing methods often face a fundamental trade-off between adapting to problem geometry
arXiv:2605.18732v1 Announce Type: cross Abstract: While scaling laws govern aggregate large language model performance, no scaling law has linked factual recall to both model size and training-data co
arXiv:2605.16828v1 Announce Type: cross Abstract: We consider the following two-player game: using observational data, the leader chooses a prediction function for a response variable Y from given cov
arXiv:2605.17618v1 Announce Type: new Abstract: Autism Spectrum Disorder (ASD) is characterized by challenges with social interaction and communication and by restricted or repetitive patterns of thou
arXiv:2605.17989v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) improves factual grounding in large language models but suffers from substantial latency due to synchronous retri
arXiv:2605.16339v1 Announce Type: new Abstract: Preference learning in large language models relies on reward models as proxies for human judgment. However, these models frequently exhibit preference
arXiv:2605.16861v1 Announce Type: cross Abstract: Block Diffusion Models (BDMs) support parallel generation, flexible-length output, and KV caching, making them promising for efficient document parsin
arXiv:2605.18352v1 Announce Type: new Abstract: Presupposition projection in conditionals is central to theories of meaning and pragmatics, yet it remains largely unevaluated in large language models.
arXiv:2604.14215v2 Announce Type: replace-cross Abstract: To address the unsustainable rise in public health expenditures, the Hong Kong SAR Government is shifting its strategic focus to primary healt
arXiv:2605.17681v1 Announce Type: new Abstract: Humanoid and legged robots interact with the environment through intermittent contacts, making accurate motion estimation fundamentally dependent on rea
arXiv:2605.17125v1 Announce Type: new Abstract: Optical navigation is a critical component for lunar orbiter and lander missions. Image-based crater identification has emerged as a promising technolog
arXiv:2406.14427v4 Announce Type: replace Abstract: A central challenge for intelligent agents in an uncertain world is striking the right balance between utility maximization and resource use, not on
arXiv:2510.16609v3 Announce Type: replace-cross Abstract: Test-time augmentation, such as Retrieval-Augmented Generation (RAG) or tool use, critically depends on an interplay between a model's paramet
arXiv:2605.16612v1 Announce Type: new Abstract: Rapid identification of candidate materials with target properties has become a key task in materials science. Machine learning has emerged as an altern
arXiv:2605.17034v1 Announce Type: cross Abstract: Standard PII filters often miss contextual data leakage in RAG systems, such as non-regulated attribute clusters that collectively identify individual
arXiv:2605.17039v1 Announce Type: new Abstract: The wide adoption of residential photovoltaic (PV) systems introduces new challenges for generation fraud detection (FD). Unlike traditional electricity
arXiv:2605.18246v1 Announce Type: cross Abstract: We study reinforcement learning (RL) in multi-dimensional continuous state and action spaces with one-sided feedback, where the agent receives partial
arXiv:2605.18537v1 Announce Type: cross Abstract: This paper introduces the Manifold Probe, a supervised method for discovering representation manifolds in superposition. The method generalizes linear
arXiv:2605.18382v1 Announce Type: cross Abstract: We present a phenomenological study of tar{t}tar{t} production in proton-proton collisions at sqrt{s} = 13~TeV, using a Hyper-Graph Neural Network (H-
arXiv:2510.18941v2 Announce Type: replace-cross Abstract: Evaluating progress in large language models (LLMs) is often constrained by the challenge of verifying responses, limiting assessments to task
arXiv:2605.17428v1 Announce Type: cross Abstract: Our preliminary experiments on gym-DSSAT maize irrigation tasks revealed that +/-2 degrees C temperature noise causes an 11.9% reduction in economic r
arXiv:2605.17932v1 Announce Type: cross Abstract: Prompt compression reduces inference cost and context length in large language models, but prior evaluations focus primarily on autoregressive archite
arXiv:2605.18474v1 Announce Type: cross Abstract: The widespread deployment and redistribution of large language models (LLMs) have made model provenance tracking a critical challenge. While existing
arXiv:2605.16605v1 Announce Type: cross Abstract: Chatbots have long been explored as tools to support learning, and recent advances in large language models have significantly expanded the availabili
arXiv:2605.18414v1 Announce Type: cross Abstract: Large language models increasingly operate as autonomous agents that select and invoke tools from large registries. We identify a critical gap: when u
arXiv:2605.16407v1 Announce Type: cross Abstract: We present a framework for verifying the deterministic structured computations surrounding a large language model rather than the model itself, extend
arXiv:2605.16747v1 Announce Type: new Abstract: We develop a quantitative statistical theory of transformers in the large-context regime by adopting the abstraction of contextual flow maps (CFMs): dyn
arXiv:2605.16346v1 Announce Type: cross Abstract: LLM-based multi-agent systems (LLM-MAS) have become a promising paradigm for solving complex tasks through role specialization, tool use, memory, and
arXiv:2605.18032v1 Announce Type: cross Abstract: Multi-agent LLM workflows -- systems composed of multiple role-specific LLM calls -- often outperform single-prompt baselines, but they remain difficu
arXiv:2605.18053v1 Announce Type: cross Abstract: We study KV cache eviction under a shared globally capped decode-time harness. Seven policies (LRU, H2O, SnapKV, StreamingLLM, Ada-KV, QUEST, Random)
arXiv:2605.18552v1 Announce Type: new Abstract: Classifying protein topology is essential for deciphering biological function, but progress is held back by the lack of large-scale benchmarks that avoi
arXiv:2604.03212v2 Announce Type: replace Abstract: Remote sensing segmentation in real deployment is inherently continual: new semantic categories emerge, and acquisition conditions shift across seas
arXiv:2510.12534v4 Announce Type: replace Abstract: The rapid growth of user-generated text across digital platforms has intensified the need for interpretable models capable of fine-grained text clas
arXiv:2508.00901v4 Announce Type: replace-cross Abstract: Large language models may encounter factual knowledge during pre-training yet fail to reliably use that knowledge after fine-tuning. Despite g
arXiv:2605.16640v1 Announce Type: new Abstract: We investigate the expressive power of hybrid recurrent-attention decoders, a class of architectures used in recent open-source language models such as
arXiv:2605.18364v1 Announce Type: new Abstract: Global optimization is a challenging problem, with plenty of algorithms displaying empirical success, but scarce theoretical backing. In this work, we p
arXiv:2602.21426v2 Announce Type: replace Abstract: We consider the problem of sampling from a posterior distribution arising in Bayesian inverse problems in science, engineering, and imaging. Our met
arXiv:2605.16360v1 Announce Type: cross Abstract: Efficient long-context inference in Large Language Models (LLMs) is severely constrained by the Key-Value (KV) cache memory wall, yet existing pruning
arXiv:2605.18331v1 Announce Type: new Abstract: Large Language Models (LLMs) have experienced significant growth and development in recent years. However, performing inference on LLMs remains costly,
arXiv:2605.16647v1 Announce Type: cross Abstract: Fully homomorphic encryption (FHE) changes sequence-model design because rotations, encrypted products, ciphertext materialization, multiplicative dep
arXiv:2605.17679v1 Announce Type: cross Abstract: Cancer survivors face elevated rates of depression, anxiety, and general emotional distress, yet the precise moments they most need support are often
arXiv:2605.16793v1 Announce Type: new Abstract: Time series forecasting under non-stationarity faces a fundamental tension between capturing stable representations and adapting to distribution shifts.
arXiv:2605.18082v1 Announce Type: new Abstract: pyforce is a Python package implementing Data-Driven Reduced Order Modelling techniques for applications to multi-physics problems, mainly set in the Nu
arXiv:2601.16414v2 Announce Type: replace-cross Abstract: Difficulty replicating baselines, high computational costs, and required domain expertise create persistent barriers to clinical AI research.