Knowledge catalogue
arXiv:2605.09429v1 Announce Type: cross Abstract: Are low-attention visual tokens truly redundant in vision-language reasoning? Existing pruning methods often assume so, ranking visual tokens by shall
arXiv:2605.08143v1 Announce Type: cross Abstract: Large language models encode vast factual knowledge that inevitably becomes outdated or incorrect after deployment, yet retraining is costly prohibiti
arXiv:2605.09572v1 Announce Type: cross Abstract: Sign language production from symbolic notation offers a scalable route to accessible sign animation. We present KANMultiSign, a multi-scale sequence
arXiv:2605.09075v1 Announce Type: cross Abstract: Although the Laplace approximation offers a simple route to uncertainty quantification in deep neural networks, its reliance on inverting large Hessia
arXiv:2605.10218v1 Announce Type: new Abstract: Diffusion large language models (dLLMs) offer a promising route to parallel and efficient text generation, but improving their reasoning ability require
arXiv:2605.10257v1 Announce Type: new Abstract: Managing disruptions in railway traffic management is a major challenge. Rising traffic density and infrastructure limits increase complexity, making th
arXiv:2605.08842v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) language models organize knowledge into explicitly routed expert modules, making expert-level representations traceable and ana
arXiv:2605.07038v1 Announce Type: new Abstract: Risk-aware navigation should be selective: a policy should expose evasive degrees of freedom only when the local scene admits a lower-risk feasible mane
arXiv:2605.07116v1 Announce Type: cross Abstract: Physics-informed neural solvers offer a promising route to model-based reinforcement learning in continuous time, where optimal feedback synthesis is
arXiv:2605.04757v1 Announce Type: new Abstract: We introduce an elastic-driven self-folding approach that fabricates robots directly from flat 3D-printed conductive PLA nets. Elastic bands routed thro
arXiv:2605.04236v1 Announce Type: new Abstract: Large Language Model ensembles improve reasoning accuracy up to a performance boundary; beyond it, additional deliberation degrades accuracy. Static-bud
arXiv:2605.04754v1 Announce Type: new Abstract: Deep neural network (DNN) inference at the edge demands simultaneous improvements in accuracy, computational efficiency, and energy consumption. Approxi
arXiv:2605.04450v1 Announce Type: cross Abstract: Generative Recommender (GR) inference places embedding hot caches (EMB) and KV caches in direct competition for limited GPU HBM: allocating more memor
arXiv:2605.04893v1 Announce Type: cross Abstract: Large language models hallucinate in predictable ways: attention routing fails by over-concentrating on a narrow set of positions, or by spreading so
arXiv:2602.03204v2 Announce Type: replace Abstract: While Mixture-of-Experts (MoE) architectures define the state-of-the-art, their theoretical success is often attributed to heuristic efficiency rath
arXiv:2605.02187v1 Announce Type: cross Abstract: Bring-Your-Own-Key (BYOK) agent architectures let users route LLM traffic through third-party relays, creating a critical integrity gap: a malicious r
Why are four of the top 10 trending vendors AI inference platforms? Companies are getting selective about which model handles which task, and routing tokens accordingly. Read more from @arakharazian a
arXiv:2605.02960v1 Announce Type: new Abstract: Production LLM workloads increasingly serve discriminative tasks, such as classification, recommendation, and verification, whose answers are read from
arXiv:2605.00276v1 Announce Type: new Abstract: Trip planning for intelligent vehicles increasingly requires selecting optimal routes rather than merely producing feasible itineraries, as interacting
arXiv:2605.01330v1 Announce Type: new Abstract: Low-bit quantization is a practical route for efficiently deploying vision Transformers, yet activation outliers complicate fully quantized deployment.
arXiv:2605.01815v1 Announce Type: new Abstract: Generative Adversarial Networks (GANs) offer a pragmatic route to mitigate data scarcity in vision tasks. We study generative augmentation across two lo
arXiv:2605.02461v1 Announce Type: cross Abstract: Middle-mile logistics describes the problem of routing parcels through a network of hubs linked by trucks with finite capacity. We rephrase this as a
arXiv:2603.05228v3 Announce Type: replace Abstract: Mechanistic interpretability typically relies on post-hoc analysis of trained networks. We instead adopt an interventional approach: testing hypothe
arXiv:2603.26013v2 Announce Type: replace Abstract: Multilingual NLP is often treated as a route to global inclusion, but linguistic coverage and cultural competence frequently diverge. This paper syn
arXiv:2512.12744v3 Announce Type: replace Abstract: Activation sparsity offers a compelling route to accelerate large language model (LLM) inference by selectively suppressing hidden activations, yet
arXiv:2605.00419v1 Announce Type: cross Abstract: Model ensembling is a well-established technique for improving the performance of machine learning models. Conventionally, this involves averaging the
Use open models in Fleet! Not every step in an agent workflow needs the same model. Fleet now lets you customize which model each sub-agent uses, so you can route simple tasks to fast/cheap models and
arXiv:2604.27168v1 Announce Type: new Abstract: We present the Field of Safe Motion (FSM), a quantitative safety model for determining whether a driver maintains a collision-free escape route, or 'out
arXiv:2604.25421v1 Announce Type: new Abstract: Federated fine-tuning provides a practical route to adapt large language models (LLMs) on edge devices without centralizing private data, yet in mobile
Resource Orchestration & Redistribution Systems As production becomes more efficient (energy, goods, services), the constraint shifts to allocation. These systems dynamically route resources based on
arXiv:2603.26554v2 Announce Type: replace Abstract: Spectral optimizers such as Muon have recently shown strong empirical performance in large-scale language model training, but the source and extent
arXiv:2604.23519v1 Announce Type: cross Abstract: Multi-plane architectures have become increasingly prevalent in the Fat-Tree networks of AI data centers. By leveraging multiple ports on a single net
arXiv:2604.23036v1 Announce Type: cross Abstract: Despite MoE models leading many benchmarks, supervised fine-tuning (SFT) for the MoE architectures remains difficult because its router layers are fra
arXiv:2604.22464v1 Announce Type: new Abstract: Continual Model Merging (CMM) sequentially integrates task-specific models into a unified architecture without intensive retraining. However, existing C
arXiv:2604.21409v1 Announce Type: new Abstract: We present S1-VL, a multimodal reasoning model for scientific domains that natively supports two complementary reasoning paradigms: Scientific Reasoning
Networking technology giant Cisco Systems Inc. today introduced a new networking switch for quantum systems that routes quantum information between computers while preserving quantum state. The Cisco
Written by: JP Glab, Tufail Ahmed, Josh Kelley, Muhammad Umair Introduction Google Threat Intelligence Group (GTIG) identified a multistage intrusion campaign by a newly tracked threat group, UNC6692,
arXiv:2604.19323v1 Announce Type: cross Abstract: Concept Bottleneck Models (CBMs) route predictions exclusively through a clinically grounded concept layer, binding interpretability to concept-label
arXiv:2602.01219v4 Announce Type: replace-cross Abstract: The attention operator in Transformers can be viewed as a two-layer fast-weight MLP, whose weights are dynamically instantiated from input tok
arXiv:2604.18842v1 Announce Type: new Abstract: Human perception generalizes well across different domains, but most vision models struggle beyond their training data. This gap motivates multi-dataset
Today at Google Cloud Next, we’re announcing new capabilities in Google Distributed Cloud (GDC) that bring Gemini and our advanced AI stack to wherever your data is, so you don’t need to compromise be
arXiv:2403.09905v5 Announce Type: replace-cross Abstract: Embodied navigation methods commonly operate in static environments with stationary objects. In this work, we present approaches for tackling
While generative AI sparked a revolution, the true paradigm shift is the rapid evolution from standalone AI models to multi-agent autonomous systems. In this new era, the network transcends basic conn
arXiv:2604.18510v1 Announce Type: cross Abstract: Open-weight language models can be rendered unsafe through several distinct interventions, but the resulting models may differ substantially in capabi
arXiv:2604.17277v1 Announce Type: new Abstract: Physical neural networks offer a transformative route to edge intelligence, providing superior inference speed and energy efficiency compared to convent
arXiv:2604.16815v1 Announce Type: cross Abstract: Quantum error mitigation (QEM) provides a practical route for estimating reliable observables on noisy intermediate-scale quantum (NISQ) devices. Trad
arXiv:2604.17714v1 Announce Type: new Abstract: LLM confidence signals are used for abstention, routing, and safety-critical decisions. No standard practice exists for checking whether a confidence si
We built our internal AI engineering stack on the same products we ship. That means 20 million requests routed through AI Gateway, 241 billion tokens processed, and inference running on Workers AI, se
arXiv:2506.13408v2 Announce Type: replace-cross Abstract: Accurate channel estimation is critical for high-performance Orthogonal Frequency-Division Multiplexing systems such as 5G New Radio, particul
arXiv:2604.14828v1 Announce Type: new Abstract: Educational assistants should spend more computation only when the task needs it. This paper rewrites our earlier draft around the system that was actua
arXiv:2604.15009v1 Announce Type: cross Abstract: Flow matching retains the generation quality of diffusion models while enabling substantially faster inference, making it a compelling paradigm for ge
arXiv:2604.13060v1 Announce Type: new Abstract: Dental triage is a safety-critical clinical routing task that requires integrating multimodal clinical information (e.g., patient complaints and radiogr
arXiv:2604.12792v1 Announce Type: new Abstract: In tendon driven continuum manipulators (TDCMs), reconfiguring the tendon routing enables tailored spatial deformation of the backbone. This work presen
arXiv:2604.12411v1 Announce Type: new Abstract: Segmentation models based on deep neural networks demonstrate strong generalization for medical image segmentation. However, they often exhibit overconf
arXiv:2604.12301v1 Announce Type: cross Abstract: We present a systematic measurement study of seven tactics for reducing cloud LLM token usage when a small local model can act as a triage layer in fr
arXiv:2604.11817v1 Announce Type: cross Abstract: Hybrid quantum-classical models offer a promising route for learning from complex data; however, their application to multi-band remote sensing imager
arXiv:2602.18109v2 Announce Type: replace Abstract: Real-time schedulers must reason about tight deadlines under strict compute budgets. We present TempoNet, a reinforcement learning scheduler that pa
arXiv:2604.09572v1 Announce Type: cross Abstract: We introduce ACE-TA, the Agentic Coding and Explanations Teaching Assistant framework, that autonomously routes conceptual queries drawn from programm
arXiv:2604.10496v1 Announce Type: new Abstract: Outliers have emerged as a fundamental bottleneck in preserving accuracy for low-precision large models, particularly within Mixture-of-Experts (MoE) ar
arXiv:2511.11232v2 Announce Type: replace Abstract: Constructing a unified 3D scene understanding model has long been hindered by the significant topological discrepancies across different sensor moda