48 articles mentioning local-ai-toolkit
arXiv:2610.28223v1 Announce Type: cross Abstract: Large language models can solve complex problems across a variety of subjects, such as mathematics and coding. For such complex analytical tasks, models with a long context perform better. Serving models with long context is currently mostly done on
arXiv:2610.28286v1 Announce Type: cross Abstract: Teams of large language model (LLM) agents are increasingly applied to complex tasks, but their collaboration protocols are mostly designed empirically, without convergence guarantees. We formalize collaborative problem solving as block optimization:
arXiv:2610.27620v1 Announce Type: cross Abstract: Autonomous LLM agents act through tools under per-action authorization: a local guard screens each tool call in isolation. We show that local authorization does not compose into global authorization. A compositional authorization failure (CAF) is a l
arXiv:2610.27702v1 Announce Type: cross Abstract: Large language models are expected to estimate their own uncertainty, with confidence signals used to guide retrieval, adaptive compute allocation, routing, and selective abstention. We investigate whether confidence signals measured at different tem
arXiv:2610.23511v1 Announce Type: new Abstract: Locally deployed large language models (LLMs) can reduce reliance on remote cloud services for natural language smart building automation, but backend-facing processing requires correct outcome selection, alignment with local capabilities, and valid st
arXiv:2610.22439v1 Announce Type: cross Abstract: Catastrophic forgetting remains a challenge in supervised continual learning, as adapting to new tasks causes representation drift and loss of previously learned information. This raises the question of which representational changes should be constr
arXiv:2610.23434v1 Announce Type: new Abstract: Federated Learning (FL) enables collaborative training of complex models across large-scale networks of edge devices while keeping data localized. However, data heterogeneity and high communication overhead remain fundamental bottlenecks. Recently, the
arXiv:2610.23145v1 Announce Type: cross Abstract: Local learning algorithms can reshape resource requirements of artificial intelligence. The memory bottleneck of standard end-to-end backpropagation lies in the need to store all network activations until the loss gradient has been propagated back th
arXiv:2307.07030v4 Announce Type: replace-cross Abstract: This paper considers the problem of understanding the behavior of a general class of accelerated gradient methods on smooth nonconvex functions. Motivated by some recent works that have proposed effective algorithms, based on Polyak's heavy b
arXiv:2610.22996v1 Announce Type: new Abstract: Minimizing the wall-clock time required to reach a target accuracy is crucial in federated learning (FL), where many applications require frequent model updates as data distributions evolve over time. Nevertheless, in heterogeneous environments, slow c
arXiv:2610.21814v1 Announce Type: new Abstract: Understanding the learning-rate (LR) dependence of trained model performance is essential for better optimization of neural networks, but the appropriate size of the LR depends on learning dynamics, architecture, and their hidden biases, and thus our u
arXiv:2310.17882v3 Announce Type: replace Abstract: By aggregating distributed energy resources (DERs) into a single dispatchable resource, virtual power plants (VPPs) enable the grid to use the flexibility of numerous small-scale DERs. Delivering an aggregate VPP commitment requires multi-agent coo
arXiv:2610.22214v1 Announce Type: new Abstract: Multiple patterning lithography (MPL) has been widely used to improve lithography resolution in advanced nodes, but it faces cost limits as feature sizes shrink. Directed self-assembly (DSA) offers a cost-effective complement, extending the resolution
arXiv:2610.21151v1 Announce Type: cross Abstract: Cybersecurity interviews uncover critical security experiences, behaviors, and privacy concerns often not fully captured by conventional technical assessments. Consequently, identifying genuine self-disclosures is challenging because statements are c
arXiv:2610.20633v1 Announce Type: new Abstract: Long-horizon failures of language models are usually measured as end-task success or as a horizon length. We instead score, step by step, three components of a 400-step ledger task in which every step is easy in isolation and the model's own answers ar
arXiv:2610.21832v1 Announce Type: new Abstract: How long should each client train before communicating? Federated learning usually answers with a fixed, hand-tuned number of local epochs, yet an extra epoch helps only while the loss it removes outweighs the client drift it adds. We cast local traini
arXiv:2507.05291v2 Announce Type: replace-cross Abstract: We propose a physics-informed machine learning framework called P-DivGNN to reconstruct local stress fields at the micro-scale, in the context of multi-scale simulation given a periodic micro-structure mesh and mean, macro-scale, stress value
arXiv:2610.19686v1 Announce Type: new Abstract: Large language model agents increasingly undertake long-horizon tasks in complex environments characterized by fragmented evidence, partially completed states, and dependencies across resources and artifacts. Existing agents may satisfy individual requ
arXiv:2610.18883v1 Announce Type: new Abstract: Token-selection methods for on-policy distillation (OPD) prioritize student-visited positions using diverse signals, including uncertainty, teacher-student disagreement, and mismatch direction. We instead derive token importance from the distillation o
arXiv:2602.06219v3 Announce Type: replace-cross Abstract: World models offer a promising avenue for more faithfully capturing complex dynamics, including contacts and non-rigidity, as well as complex sensory information, such as visual perception, in situations where standard simulators struggle. Ho
arXiv:2610.14209v1 Announce Type: new Abstract: The most accurate agents executing user-provided tasks are driven by large, cloud-hosted models, which solve them by reading the private data of the user. Agents powered by models small enough to run on edge devices keep that data local, but yield far
arXiv:2610.18635v1 Announce Type: cross Abstract: The development of a digital twin brings together many stakeholders and technical components. We have previously investigated the reporting of the conceptual architecture for these digital twins as an artifact for discussion. However, we find that th
arXiv:2610.18945v1 Announce Type: cross Abstract: Amortized Bayesian inference uses simulations to perform Bayesian estimation when likelihoods are expensive or analytically unavailable. However, learning the full joint posterior is challenging in high-dimensional models with complex dependencies. W
arXiv:2608.14094v2 Announce Type: replace-cross Abstract: Cloud-local LLM inference can use the reasoning capability of large cloud models, but cloud-bound requests must exclude personally identifiable information (PII). Existing privacy-preserving methods modify the prompt or the model, which may d
arXiv:2610.20392v1 Announce Type: new Abstract: Speculative decoding accelerates LLM generation through lightweight drafting and parallel verification. It is particularly promising for long inputs, where KV-cache access costs can be amortized over multiple accepted tokens. Yet most drafters are trai
arXiv:2610.13437v1 Announce Type: new Abstract: Anomaly detection, the identification of collision events that deviate from Standard Model expectations, is one of the most promising model-agnostic strategies for new-physics searches at the Large Hadron Collider. Searching for rare events in learned
arXiv:2610.13479v1 Announce Type: new Abstract: Generating edge case scenarios is crucial for training, testing and safety assuring autonomous systems. This identifies hazardous failures to increase system reliability and robustness, ensures the system can still function safely on the boundaries of
arXiv:2508.02161v2 Announce Type: replace Abstract: Trajectory prediction is essential for formulating proactive strategies that anticipate user mobility and support advance preparation. Therefore, how to reduce the forecasting error in user trajectory prediction within an acceptable inference time
I'm embarking on a journey I've so far been hesitant to go on: actually using AI on the regular. Giving my most personal data to cloud services has been a major hold up for me, but it's increasingly possible to run powerful models locally to see what they're capable of. Is this tech so useful […]
arXiv:2610.12333v1 Announce Type: cross Abstract: Accurate simulation of rigid-body interactions is essential for predictive physical world models. Despite recent progress in modeling object dynamics, capturing how local contacts between surfaces shape object motion remains challenging. While end-to
arXiv:2610.05476v2 Announce Type: replace-cross Abstract: Scaling decentralized learning changes not only the number of clients $N$, but also the dynamics of information propagation and consensus. We argue that the effect of increasing $N$ cannot be understood in isolation, because data allocation,
arXiv:2510.12843v2 Announce Type: replace Abstract: Spiking neural networks (SNNs) promise energy-efficient artificial intelligence on neuromorphic hardware but struggle with tasks requiring both fast adaptation and long-term memory, especially in continual learning. We propose Local Timescale Gatin
arXiv:2610.11159v1 Announce Type: new Abstract: Speech-to-LLM systems often connect a frozen speech encoder to a frozen large language model (LLM) through a small trainable bridge. The bridge is usually treated as plumbing, but it in fact defines the geometry of the speech-to-LLM interface, and the
arXiv:2610.11482v1 Announce Type: cross Abstract: Context: Large language model (LLM) agents are increasingly used as software and data-engineering assistants, yet evidence about locally deployable open-weight agents remains limited. Existing evaluations often emphasize textual responses or isolated
arXiv:2610.11651v1 Announce Type: new Abstract: Automated interviewers and conversational agents are increasingly used in research, recruitment, customer service, and education. However, many existing systems rely on fixed question sequences and provide limited context-based personalization without
Google’s new AI Edge Foresight app takes on Granola with an offline meeting note-taker that can transcribe conversations, generate notes, and answer questions using on-device AI.
arXiv:2610.08176v1 Announce Type: new Abstract: Decentralized learning is highly sensitive to communication topology under non-IID data. Adaptive peer-selection methods can exploit local model information, but broader peer discovery may require increasingly large control state, whereas direct spectr
arXiv:2606.06539v2 Announce Type: replace-cross Abstract: Forward-Forward (FF) learning [Hinton, 2022] replaces backpropagation with strictly layer-local goodness updates. Recent FF-CNN work has narrowed the gap to BP on 32x32 benchmarks, raising the question of whether layer-local training is becom
arXiv:2610.10190v1 Announce Type: cross Abstract: We analyze the first-order deterministic diffusion sampler of Karras et al. (2022), termed EDM, in 2-Wasserstein distance by separating two sources of error: local discretization error and its amplification by subsequent learned steps. We prove that
arXiv:2610.08388v1 Announce Type: cross Abstract: Large language models (LLMs) have demonstrated strong capabilities in question answering, yet they still frequently suffer from hallucinations on knowledge-intensive tasks. Knowledge graphs (KGs) provide LLMs with structured, interpretable, and updat
arXiv:2610.08538v1 Announce Type: cross Abstract: Probabilistic load forecasting has been widely studied for power-system operation and planning, but customer- and transformer-level forecasting introduces a distinct scalability challenge. At these levels, load uncertainty is strongly affected by cus
arXiv:2609.20129v2 Announce Type: replace-cross Abstract: Deployment-time safety methods for large language models (LLMs) are predominantly supervised and assume access to unsafe training data. Nevertheless, new attacks and harm categories regularly arise, not captured by models trained in such a su
arXiv:2610.07514v1 Announce Type: new Abstract: A vision-language model may need to combine an image with a prompt to recognize a safety risk that neither reveals alone. Where does this joint safety judgment become accessible inside the model? We introduce SSU-Bench, a dataset of matched safe and un
arXiv:2602.01564v3 Announce Type: replace Abstract: We study the mean-field Langevin descent-ascent (MFL-DA), a coupled optimization dynamics on the space of probability measures for entropically regularized two-player zero-sum games, together with its associated interacting particle system. For gen
arXiv:2610.07327v1 Announce Type: cross Abstract: Agent tasks require sequences of interdependent decisions. Autoregressive models support more flexible decision interfaces than conventional classifiers but incur the latency of token-by-token generation. Recent shared-prefix methods reduce this cost
arXiv:2610.08292v1 Announce Type: cross Abstract: Many two-sample tests for populations of persistence diagrams assess global differences without identifying the regions of the birth-death plane that contribute to them. We study simultaneous inference for local mean contrasts when the number of avai
arXiv:2606.19617v2 Announce Type: replace-cross Abstract: We present GB-LSR (Global-Bandwidth Local Spectral Representation), a fixed-grid local spectral representation for continuous image decoding. The image domain is partitioned into non-overlapping square patches. Each patch carries coefficients