Knowledge catalogue
arXiv:2608.07890v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) models decouple total parameters from per-token compute, but deployment still requires storing every expert. Recent theory sh
arXiv:2511.09373v2 Announce Type: replace-cross Abstract: LLMs now tackle a wide range of software-related tasks, yet we show that their performance varies markedly both across and within these tasks.
arXiv:2608.09853v1 Announce Type: cross Abstract: General-purpose reward models are increasingly the bottleneck for scaling robot learning, yet the recipe for learning value-related capabilities from
arXiv:2608.09303v1 Announce Type: cross Abstract: The deployment of autonomous robotic systems in chemistry laboratories is accelerating experimental workflows and providing the foundational data for
arXiv:2608.09260v1 Announce Type: cross Abstract: Large language models (LLMs) have advanced Text-to-SQL by enabling natural language interfaces to databases without task-specific fine-tuning. However
arXiv:2608.09230v1 Announce Type: new Abstract: Industrial-safety understanding requires more than detecting workers, equipment, and personal protective equipment. Models must also assess compliance,
arXiv:2608.08383v1 Announce Type: new Abstract: Steering vectors are a lightweight tool for controlling LLM behavior. However, emerging evidence shows that steering vectors can unintentionally comprom
arXiv:2608.08237v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) systems in production operate under strict service level objectives (SLOs) on tail latency and infrastructure cos
arXiv:2608.09196v1 Announce Type: new Abstract: Most existing vision-language navigation tasks assume that instructions are complete and unambiguous. However, real-world robots often encounter natural
arXiv:2505.15062v5 Announce Type: replace-cross Abstract: Knowledge extrapolation is the process of inferring novel information by combining and extending existing knowledge that is explicitly availab
arXiv:2608.08942v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly integrated into healthcare, education, public services, and everyday decision making. They should provide
arXiv:2608.09628v1 Announce Type: new Abstract: Collision avoidance systems are commonly used to avoid fragmentation events occurring in Low-Earth Orbit (LEO) and Geosynchronous Equatorial Orbit (GEO)
arXiv:2608.08555v1 Announce Type: new Abstract: Visible-to-infrared image translation provides a practical way to expand infrared training data using abundant visible images. Diffusion models are prom
arXiv:2608.07548v1 Announce Type: cross Abstract: Vision-and-Language Navigation in Continuous Environments (VLN-CE) requires agents to make fine-grained navigation decisions under partial observabili
arXiv:2509.09078v3 Announce Type: replace-cross Abstract: Given-data methods for variance-based sensitivity analysis have significantly advanced the feasibility of Sobol' index computation for computa
arXiv:2608.08293v1 Announce Type: new Abstract: This paper presents a scalable lateral control framework for robust path tracking of single-body and articulated autonomous vehicles at high speeds. A c
arXiv:2608.08746v1 Announce Type: new Abstract: Prospective daily symptom tracking is central to premenstrual health assessment, but repeated ordinal forms impose substantial response burden. We formu
arXiv:2608.07945v1 Announce Type: cross Abstract: Cloud-native serverless data warehouses achieve fine-grained elasticity by decoupling storage from compute, yet determining the optimal resource alloc
arXiv:2606.22790v2 Announce Type: replace-cross Abstract: In this paper, we investigate the tradeoffs between compute allocation and model performance for two speech processing tasks: Automatic Speech
arXiv:2608.07594v1 Announce Type: cross Abstract: Interpretability is often treated as a tax on capability: language models are trained as opaque systems, then explained after the fact, with methods w
arXiv:2608.09873v1 Announce Type: cross Abstract: We introduce Sci-VBench, a comprehensive benchmark for evaluating knowledge- and reasoning-intensive video generation across scientific domains. It co
arXiv:2603.08910v2 Announce Type: replace Abstract: We introduce SciTaRC, an expert-authored benchmark for question answering over scientific tables that targets composite, multi-step reasoning. To en
arXiv:2608.07923v1 Announce Type: new Abstract: Audio-visual event perception (AVEP) determines which events occur in a video, when they occur, and whether they are audible, visible, or both. Training
arXiv:2608.07959v1 Announce Type: new Abstract: Ultra-long egocentric video understanding requires reasoning over temporally sparse evidence distributed across hours or days, challenging current multi
arXiv:2608.08106v1 Announce Type: new Abstract: Synthetic Aperture Sonar (SAS) is core for wide-area detection of small underwater targets. However, large-scale, high-quality SAS datasets are scarce,
arXiv:2608.08594v1 Announce Type: new Abstract: Diffusion bridge models leverage Doob's (h)-transform to construct stochastic transports between arbitrary endpoint distributions, and have shown strong
arXiv:2608.09568v1 Announce Type: new Abstract: Direct Preference Optimization (DPO) aggregates token-level log-probability ratios via uniform summation, implicitly treating all tokens as contributing
arXiv:2608.07531v1 Announce Type: cross Abstract: Search-augmented language agents should retrieve external information only when necessary and ground their answers in retrieved evidence. Existing ext
arXiv:2608.08075v1 Announce Type: cross Abstract: Most video-retrieval systems assume a bounded corpus and return ranked files or timestamps. Agents operating over cameras, screens, streams, and archi
arXiv:2608.07924v1 Announce Type: cross Abstract: Drifting models are a recent class of one-step generative models that evolve the model distribution during training using a predefined sample-based dr
arXiv:2608.09763v1 Announce Type: new Abstract: Muon's polar update is exact for an unweighted spectral geometry. We introduce GO-MUON, which uses a matched data-dependent geometry and reuses it acros
arXiv:2608.09049v1 Announce Type: new Abstract: Mobile app reviews are a rich, continuously renewing source of how users experience privacy and security, yet existing taxonomies of these concerns are
arXiv:2410.01227v2 Announce Type: replace-cross Abstract: In the context of medical records, patients often experience testimonial injustice, where the textual account undermines the validity of their
arXiv:2608.07916v1 Announce Type: new Abstract: Image demosaicing reconstructs a full-color image from incomplete color measurements produced by a sensor covered with a color filter array (CFA). Most
arXiv:2608.09449v1 Announce Type: new Abstract: Video world models must capture how scenes evolve over time and across viewpoints. Training them for long-horizon generation and camera control therefor
arXiv:2510.15968v2 Announce Type: replace-cross Abstract: Thermal management in 3D ICs is increasingly challenging due to higher power densities. Traditional PDE-solving-based methods, while accurate,
arXiv:2608.07955v1 Announce Type: new Abstract: Large vision-language models have achieved strong performance in multimodal reasoning, but they remain unreliable on fine-grained spatial tasks that dem
arXiv:2608.07553v1 Announce Type: new Abstract: Robotic manipulation often requires object specific programming, manual data annotation, or calibrated perception pipelines, which limits rapid deployme
arXiv:2608.08685v1 Announce Type: new Abstract: Reliable semi-dense matching is essential for modern geometric vision systems. Designed under a coarse-to-fine paradigm, it achieves an optimal balance
arXiv:2607.28069v2 Announce Type: replace Abstract: Long-context retrieval and agentic workloads repeatedly reuse the same documents under changing instructions, histories, and document orders. Prefix
arXiv:2608.07835v1 Announce Type: new Abstract: Cross-View Geo-Localization (CVGL) with OpenStreetMap (OSM) performs well in structure-rich urban environments but collapses in feature-sparse scenes su
arXiv:2608.08839v1 Announce Type: cross Abstract: World-Action Models (WAMs) have emerged as a promising paradigm for robotic manipulation. However, most existing WAMs generate future videos and actio
arXiv:2608.07814v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) language models deliver high capacity at low per-token compute, but deploying them cheaply requires compressing their many ex
arXiv:2601.22510v2 Announce Type: replace-cross Abstract: Large language models (LLMs) often achieve strong benchmark accuracy yet remain brittle under small distribution shifts. While recent mechanis
arXiv:2608.09885v1 Announce Type: new Abstract: The safety of large language model (LLM) agents depends not only on model weights but also on the agent harness that manages context, memory, tools, per
arXiv:2608.08884v1 Announce Type: new Abstract: As collaborative robots have entered domains such as manufacturing, agriculture, and healthcare, programming or adapting robot behavior typically requir
arXiv:2608.09097v1 Announce Type: new Abstract: Despite rapid advances in generative models, achieving pixel-level precision in sketch-based image editing remains a persistent challenge, particularly
arXiv:2608.09400v1 Announce Type: cross Abstract: Research regarding the sign language recognition mostly relies on RGB images, whileas sign language datasets that provide depth images are limited. Po
arXiv:2608.09201v1 Announce Type: new Abstract: Dense expert merging combines domain-specialized language models into one single checkpoint, typically by admitting task-vector support in weight space.
arXiv:2608.09006v1 Announce Type: cross Abstract: Large Language Models (LLMs) have achieved remarkable success across a wide range of tasks. However, fine-tuning LLMs for Gloss-Free Sign Language Tra
arXiv:2606.14574v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly deployed as planners for autonomous agents in household environments. While existing benchmarks
arXiv:2512.09062v2 Announce Type: replace Abstract: Accurate 3D scene interpretation in active construction sites is essential for progress monitoring, safety assessment, and digital twin development.
arXiv:2608.09185v1 Announce Type: cross Abstract: Enterprise data warehouses (DWs) support business-critical analytics, but warehouse task delivery remains a complicated production process involving c
arXiv:2608.07639v1 Announce Type: cross Abstract: Agent Skills provide reusable capabilities to LLM agents. Agent Skill inconsistencies can expose undisclosed dangerous behavior or cause wrong Skill s
arXiv:2608.08640v1 Announce Type: new Abstract: Large language model agents increasingly rely on reusable skills to extend their capabilities beyond parametric knowl- edge. However, retrieving the app
arXiv:2608.09410v1 Announce Type: new Abstract: Modern vision-language-action (VLA) policies have acquired broad manipulation skills, but typically generate each action chunk from the current observat
arXiv:2608.09253v1 Announce Type: new Abstract: LLM agents are increasingly equipped with skills to perform complex tasks through multi-step reasoning and tool use. Although skills provide reusable pr
arXiv:2608.08468v1 Announce Type: cross Abstract: Agent Skills---structured packages of instructions and scripts that augment LLM-based agents---are rapidly proliferating, yet their security propertie
arXiv:2608.08037v1 Announce Type: new Abstract: LLM-based agent frameworks now act as personal assistants for multi-step tasks. Existing agent frameworks such as OpenClaw commonly follow the Cloud Age
arXiv:2608.08840v1 Announce Type: new Abstract: Individual fish re-identification (ReID) is a fine-grained recognition problem in which identity-discriminative cues are often localized to specific bod