Knowledge catalogue
arXiv:2605.25382v1 Announce Type: new Abstract: Evidence construction systems--chunk retrieval, agent memory, knowledge-graph traversal, and thematic indexing--are evaluated on separate benchmarks wit
arXiv:2605.26079v1 Announce Type: new Abstract: Modern AI benchmarks operate at a complexity that outpaces traditional verification methods. Tasks authored by domain experts often contain implicit ass
arXiv:2605.25413v1 Announce Type: cross Abstract: Neural operators learn mappings from function-dependent inputs to solutions, providing an effective framework for solving partial differential equatio
arXiv:2605.24183v1 Announce Type: cross Abstract: We introduce AvalancheBench, a benchmark for evaluating enterprise data agents through latent world recovery. AvalancheBench improves on existing benc
arXiv:2605.24652v1 Announce Type: new Abstract: Rapid advances in audio-video (AV) generation have enabled high-fidelity synthesis with synchronized sound, particularly for human-related scenarios inv
arXiv:2602.19878v3 Announce Type: replace Abstract: The Open Digital Rights Language (ODRL) represents policy constraints as triples of a left operand, an operator, and a value. Several spatial operan
arXiv:2510.00387v3 Announce Type: replace Abstract: This study uses controlled simulations with known ground-truth parameters to evaluate how Distributional Latent Variable Models (DLVM) and Bayesian
arXiv:2605.25549v1 Announce Type: cross Abstract: High-quality expert chain-of-thought (CoT) data is one of the core bottlenecks in large language model (LLM) post-training. Existing data production m
arXiv:2605.21602v2 Announce Type: replace Abstract: Many safety and alignment failures of large language models (LLMs) occur due to out-of-distribution (OOD) situations: unusual prompt or response pat
arXiv:2510.22143v3 Announce Type: replace Abstract: Existing benchmarks and training pipelines for industrial intelligent customer service (ICS) remain misaligned with real-world dialogue requirements
arXiv:2605.24297v1 Announce Type: cross Abstract: Which fine-tuning signals improve patent embedding models, and do gains transfer across patent landscapes? We benchmark 22 embedding models, from 22M-
arXiv:2605.25764v1 Announce Type: cross Abstract: Pathology foundation models (PFMs) have emerged as a core approach for learning transferable representations from whole slide images (WSIs), and they
arXiv:2605.24423v1 Announce Type: new Abstract: In-Context Reinforcement Learning (ICRL) has enabled foundation agents to adapt instantaneously to novel tasks, yet its efficacy in Ad-Hoc Teamwork (AHT
arXiv:2605.24219v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly deployed as autonomous agents that reason, use tools, and act over multiple steps. Yet most hallucination
arXiv:2605.24657v1 Announce Type: new Abstract: Major LLM platforms deploy models in an inference-only configuration: the model serves requests but never updates per-user weights. Users must repeatedl
arXiv:2605.25626v1 Announce Type: new Abstract: Social media platforms enable large-scale cross-lingual communication, but translating user-generated content (UGC) remains challenging due to its infor
arXiv:2605.25558v1 Announce Type: new Abstract: Optimizing the trade-off among predictive performance and computational cost is a central focus in the deployment of Large Language Models (LLMs). Curre
arXiv:2605.26100v1 Announce Type: cross Abstract: Code review is a critical practice in software engineering, yet the growing scale and frequency of code patches in modern projects, together with the
arXiv:2605.23931v1 Announce Type: new Abstract: The formal verification of operating system kernels requires precise specifications that capture the intended behavior of system calls. Writing these sp
arXiv:2509.24050v4 Announce Type: replace Abstract: Device-cloud collaboration holds promise for deploying large language models (LLMs), leveraging lightweight on-device models for efficiency while re
arXiv:2605.25937v1 Announce Type: cross Abstract: We present a dataset of adversarial malware samples derived from the public RawMal-TF collection of real-world malware binaries. Using a suite of adve
arXiv:2605.25920v1 Announce Type: cross Abstract: While large language models (LLMs) augmented with agentic search capabilities show promise for legal reasoning, they overlook a fundamental constraint
arXiv:2605.23913v1 Announce Type: cross Abstract: Cloud-hosted large language models (LLMs) commonly rely on LoRA for domain adaptation, yet domain data are distributed across multiple edge devices an
arXiv:2605.24055v1 Announce Type: cross Abstract: Real-world time-series data in industrial sensing, healthcare, and energy systems is often corrupted by a mixture of Gaussian noise and occasional lar
arXiv:2605.25891v1 Announce Type: cross Abstract: We find a mismatch between what large language models encode about a causal question and what they answer. On anti-commonsense CLadder items, a fixed
arXiv:2605.26029v1 Announce Type: new Abstract: We introduce CausaLab, a scalable environment for evaluating interactive causal discovery by LLM agents. Unlike prior evaluations, CausaLab evaluates bo
arXiv:2510.26418v4 Announce Type: replace Abstract: Large Reasoning Models (LRMs) improve task performance through extended inference-time reasoning. Although previous studies suggest that longer reas
arXiv:2605.24418v1 Announce Type: new Abstract: Federated learning is used in medical imaging where privacy prohibits centralizing data. Standard federated algorithms assume homogeneous hardware, iden
arXiv:2605.24305v1 Announce Type: cross Abstract: Standard accuracy on binary reasoning benchmarks hides critical failure modes: prior collapse, inconsistency under paraphrase, and inability to reason
arXiv:2510.02361v2 Announce Type: replace-cross Abstract: Transformer-based large models excel in natural language processing and computer vision, but face severe computational inefficiencies due to t
arXiv:2605.26036v1 Announce Type: new Abstract: Urban representation learning encodes complex urban environments into general-purpose embeddings for diverse downstream tasks and emerging urban foundat
arXiv:2605.25204v1 Announce Type: new Abstract: Pluralistic alignment requires systems to adapt to diverse user values, communication styles, and contextual assumptions. We believe that a foundational
arXiv:2605.26086v1 Announce Type: new Abstract: Large language model agents are increasingly envisioned as always-on personal assistants with access to anything relevant in the user's digital world. Y
arXiv:2605.25708v1 Announce Type: cross Abstract: Multi-domain task-incremental learning requires a model to sequentially acquire knowledge across visually diverse domains without forgetting prior tas
arXiv:2605.24453v1 Announce Type: cross Abstract: Large Language Model (LLM)-based code analysis tools are adopted to automate software documentation tasks. However, the scalability of these approache
arXiv:2605.25378v1 Announce Type: cross Abstract: Customized image editing aims to equip pre-trained diffusion models with specific visual effects using limited paired data, typically via Low-Rank Ada
arXiv:2604.18179v2 Announce Type: replace-cross Abstract: Hosted-LLM providers have a silent-substitution incentive: advertise a stronger model while serving cheaper replies. Probe-after-return scheme
arXiv:2605.24779v1 Announce Type: cross Abstract: Submodular optimization has become a fundamental paradigm for data selection, retrieval, summarization, and representation learning due to its ability
arXiv:2605.25765v1 Announce Type: cross Abstract: Concept unlearning aims to erase a target concept from a pretrained text-to-image diffusion model without retraining. Closed-form methods are attracti
arXiv:2605.25882v1 Announce Type: new Abstract: Recent advances in uncertainty quantification increasingly emphasise the distinction between aleatory and epistemic uncertainty in machine learning, mot
arXiv:2605.25835v1 Announce Type: cross Abstract: This paper examines the specialization of Small Language Models (SLMs) with up to 4 billion parameters for generating artifacts in domain-specific lan
arXiv:2605.24279v1 Announce Type: new Abstract: A frontier language model's acknowledged 'helpful programming assistant' persona does not survive long agentic-coding sessions in the deployment regime
arXiv:2605.25962v1 Announce Type: cross Abstract: Machine unlearning removes designated concepts or knowledge from pre-trained models. Recent work has extended this paradigm to speaker identity unlear
arXiv:2605.25006v1 Announce Type: cross Abstract: Sampling-based algorithms for robot path planning offer probabilistic completeness and strong empirical convergence properties across environments wit
arXiv:2602.04360v2 Announce Type: replace-cross Abstract: Hypergraph neural networks (HGNNs) effectively model higher-order interactions in many real-world systems but remain difficult to interpret, l
arXiv:2605.25616v1 Announce Type: new Abstract: Single-pass uncertainty quantification (UQ) methods for classification represent uncertainty by predicting a tractable distribution over the class proba
arXiv:2601.19070v2 Announce Type: replace Abstract: We rigorously study the thermodynamic limit of deep neural networks (DNNS) and recurrent neural networks (RNNs), assuming that the activation functi
arXiv:2605.24810v1 Announce Type: cross Abstract: Off-dynamics offline reinforcement learning seeks to learn a target-domain policy from a large source dataset and a limited target dataset under misma
arXiv:2605.24965v1 Announce Type: cross Abstract: The rapid evolution of generative models has enabled the creation of hyper-realistic facial deepfakes, exposing a critical vulnerability in modern dig
arXiv:2605.24603v1 Announce Type: new Abstract: A sparse 8-layer code transformer develops dedicated neural circuitry for every Python construct tested, and that circuitry is organised by a clean comp
arXiv:2605.25624v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) has driven breakthroughs in domains such as math, tool-use, and software engineering, yet its exte
arXiv:2605.24331v1 Announce Type: new Abstract: Context or prompt-level reweighting has emerged as a central algorithmic lever in Reinforcement Learning with Verified Rewards (RLVR) for improving the
arXiv:2605.24765v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly applied to cybersecurity question answering (QA) for critical tasks such as incident response and vulner
arXiv:2605.25893v1 Announce Type: new Abstract: Despite the emergence of diffusion large language models (D-LLMs) as an alternative to autoregressive large language models (AR-LLMs), safety monitoring
arXiv:2605.25188v1 Announce Type: new Abstract: Multi-agent LLM systems improve reasoning by combining outputs from multiple agents, but interaction-heavy methods can introduce error propagation and h
arXiv:2605.25221v1 Announce Type: cross Abstract: Reservoir computing typically relies on large, randomly generated reservoirs, enabling simple, often linear readouts. Over the past two decades, most
arXiv:2605.25393v1 Announce Type: new Abstract: Large Language Models (LLMs) and Multimodal LLMs (MLLMs) have demonstrated immense potential in autonomous driving (AD) by offering human-like reasoning
arXiv:2605.24454v1 Announce Type: new Abstract: Large language models (LLMs) have shown strong performance in the legal domain, demonstrating notable potential in Legal Question Answering (LQA). Howev
arXiv:2605.25997v1 Announce Type: new Abstract: Benchmarks increasingly guide deployment, procurement and scientific screening, yet a score supports only the response it records, not necessarily the d
arXiv:2605.25189v1 Announce Type: cross Abstract: Reward hacking arises when a model improves a proxy reward by exploiting shortcuts rather than solving the intended task. We study this failure mode t