Knowledge catalogue
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:2605.10901v1 Announce Type: new Abstract: Guardrail Classifiers defend production language models against harmful behavior, but although results seem promising in testing, they provide no formal
arXiv:2605.10034v1 Announce Type: new Abstract: Recent Autonomous Driving (AD) works such as GigaFlow and PufferDrive have unlocked Reinforcement Learning (RL) at scale as a training strategy for driv
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:2605.10438v1 Announce Type: cross Abstract: Current 3D tokenizers largely treat representation as spatial compression: compact codes reconstruct surface geometry, but leave component ownership a
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:2605.08761v1 Announce Type: cross Abstract: Large language model (LLM) agents are increasingly expected to operate in enterprise environments, where work is distributed across specialized roles,
arXiv:2605.08994v1 Announce Type: cross Abstract: The current catalyst discovery and development pipeline for energy-intensive applications like methane conversion remains bottlenecked by expensive tr
arXiv:2605.08280v1 Announce Type: cross Abstract: Preserving model fidelity is essential for stealthy text-to-image (T2I) backdoor attacks. Existing methods such as Learning without Forgetting (LwF) r
arXiv:2605.10780v1 Announce Type: cross Abstract: Representation autoencoders that reuse frozen pretrained vision encoders as visual tokenizers have achieved strong reconstruction and generation quali
arXiv:2502.08943v4 Announce Type: replace-cross Abstract: Large language models (LLMs) have demonstrated significant utility in real-world applications, exhibiting impressive capabilities in natural l
arXiv:2605.09146v1 Announce Type: new Abstract: Humanoid Visual Search (HVS) requires agents to actively explore immersive 360^irc environments. While prior methods treat this as a monolithic task rel
arXiv:2605.08618v1 Announce Type: new Abstract: Out-of-distribution (OOD) detection is essential for reliable deployment of deep learning systems, yet the majority of existing methods are evaluated on
arXiv:2605.08276v1 Announce Type: new Abstract: Cell-level dense prediction is central to computational pathology, but remains challenging due to fine-grained histological structures, strong domain sh
arXiv:2605.10345v1 Announce Type: new Abstract: Geometric differences between cross-view images, such as drone and satellite views, significantly increase the challenge of Cross-View Geo-Localization
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:2605.09041v1 Announce Type: new Abstract: Bias audits of large language models now operate within governance frameworks such as the EU AI Act, making benchmark reliability a security concern in
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:2605.08891v1 Announce Type: new Abstract: Sparse autoencoders have become a standard tool for uncovering interpretable latent representations in neural networks. Yet salient concepts often span
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:2605.09579v1 Announce Type: cross Abstract: Cardiovascular disease remains the leading cause of global mortality, yet scalable cardiac monitoring is hindered by the gap between diagnostic-rich E
arXiv:2510.07500v2 Announce Type: replace Abstract: We study black-box detection of machine-generated text under practical constraints: the scoring model (proxy LM) may mismatch the unknown source mod
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:2605.09134v1 Announce Type: new Abstract: Reinforcement learning for program repair is hindered by sparse execution feedback and coarse sequence-level rewards that obscure which edits actually f
arXiv:2605.06117v2 Announce Type: replace Abstract: Large language models (LLMs) have recently been adapted to tabular prediction by serializing structured features into natural language, but their pe
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,
arXiv:2603.04783v2 Announce Type: replace Abstract: While LLMs demonstrate strong reasoning capabilities when provided with full information in a single turn, they exhibit substantial vulnerability in
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:2605.10195v1 Announce Type: new Abstract: Tree-of-Thought (ToT) reasoning structures Large Language Model (LLM) inference as a tree-based search, demonstrating strong potential for solving compl
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:2605.08271v1 Announce Type: cross Abstract: Understanding ultra-long videos such as egocentric recordings, live streams, or surveillance footage spanning days to weeks, remains a challenge. For
arXiv:2605.10541v1 Announce Type: new Abstract: Epigenetic clocks based on DNA methylation have emerged as powerful tools for estimating biological age, with broad applications in aging research, age-
arXiv:2605.09096v1 Announce Type: new Abstract: Neural operators for time-dependent PDEs face a structural tension: spectral architectures (FNO and descendants) inherit exponential rollout-error growt
arXiv:2605.10036v1 Announce Type: cross Abstract: As 6G evolves, the radio access network must transcend traditional automation to embrace agentic AI capable of perception, reasoning, and evolution. A
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
arXiv:2605.08862v1 Announce Type: cross Abstract: Reinforcement Learning (RL) has become a cornerstone for improving the performance of Large Language Models (LLMs). However, its rollout phase constit
arXiv:2605.10598v1 Announce Type: new Abstract: Large language models (LLMs) have emerged as powerful tools for automatic algorithm design (AAD). However, existing pipelines remain inefficient. They o
arXiv:2605.10241v1 Announce Type: new Abstract: Natural language understanding (NLU) is integral to task-oriented dialog systems, but demands a considerable amount of annotated training data to increa
arXiv:2605.08404v1 Announce Type: cross Abstract: This work investigates the use of large language models (LLMs) for tasks in smart cities. The core idea is to leverage remote sensing imagery to chara
arXiv:2605.10661v1 Announce Type: cross Abstract: Vision Transformers (ViTs) are built by stacking independently parameterized blocks, but it remains unclear how much of this depth requires layer spec
arXiv:2605.09611v1 Announce Type: new Abstract: This preprint presents an empirical analysis of byte-exact chunk-level deduplication in Retrieval-Augmented Generation (RAG) pipelines. We measure conte
arXiv:2605.10744v1 Announce Type: new Abstract: Safety-critical planning in complex environments, particularly at urban intersections, remains a fundamental challenge for autonomous driving. Existing
arXiv:2605.08653v1 Announce Type: new Abstract: Accurate state-of-charge (SOC) estimation is critical for the safe and efficient operation of lithium-ion batteries in battery management systems (BMS).
arXiv:2504.21228v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are susceptible to indirect prompt injection attacks, where the model inadvertently responds to instructions inje
arXiv:2605.10873v1 Announce Type: cross Abstract: Recovering editable CAD programs from images or 3D observations is central to AI-assisted design, but progress is difficult to measure because existin
arXiv:2605.09279v1 Announce Type: cross Abstract: Volumetric video (VV) streaming enables real-time, immersive access to remote 3D environments, powering telepresence, ecological monitoring, and robot
arXiv:2605.09823v1 Announce Type: cross Abstract: We introduce CalBench, a controlled evaluation environment for studying multi-agent coordination through calendar scheduling. In CalBench, N agents ea
arXiv:2605.09245v1 Announce Type: new Abstract: Multi-camera multi-object tracking (MCMOT) faces significant challenges in maintaining consistent object identities across varying camera perspectives,
arXiv:2605.09702v1 Announce Type: cross Abstract: Multi-judge evaluation is increasingly used to assess LLMs and reward models, and the prevailing heuristic is to curate: keep the most accurate judges
arXiv:2605.09737v1 Announce Type: new Abstract: Modern large language models (LLMs) rely on system prompts to establish behavioral constraints and safety rules. Standard causal self-attention treats p
arXiv:2605.08325v1 Announce Type: cross Abstract: Many vision datasets now provide segmentation masks in addition to annotated images to support a wide range of tasks. In this work, we propose Class A
arXiv:2605.10448v1 Announce Type: new Abstract: Interactive agent benchmarks map an agent run to a binary outcome through outcome checks. When these checks rely on surface level signals or fail to cap
arXiv:2601.12369v3 Announce Type: replace Abstract: Deep Research Agents increasingly automate survey generation, yet whether they match human experts at retrieving essential papers and organizing the
arXiv:2605.10419v1 Announce Type: cross Abstract: This paper investigates the effectiveness of large language models (LLMs) in answering questions over datasets. We examine their performance in two sc
arXiv:2605.08439v1 Announce Type: new Abstract: Accurately communicating the side effects of cancer treatments to cancer survivors is critical, particularly in settings such as informed consent, where
arXiv:2512.18880v2 Announce Type: replace-cross Abstract: Accurate estimation of item (question or task) difficulty is critical for educational assessment but suffers from the cold start problem. Whil