Search: “applications”

arXiv:2603.11600v2 Announce Type: replace Abstract: Deep reinforcement learning for continuous control often suffers from high variance, low energy efficiency, and poor generalization under distributi

arXiv:2603.26506v2 Announce Type: replace-cross Abstract: Connectivity structure shapes neural computation, but inferring this structure from population recordings is degenerate: multiple connectivity

arXiv:2605.31413v1 Announce Type: cross Abstract: We establish improved nonasymptotic bounds for Langevin Monte Carlo in the strongly log-concave setting, when the error is measured by the Wasserstein

arXiv:2605.31324v1 Announce Type: cross Abstract: Estimating the generalization gap and developing optimization methods that improve generalization are crucial for deep learning models, for both theor

Mellum2 is a 12-billion parameter Mixture-of-Experts language model developed by JetBrains, designed to efficiently process complex tasks by selectively activating different expert networks. The model

arXiv:2602.08267v2 Announce Type: replace-cross Abstract: We study the problem of transformation inversion on general Lie groups: a datum is transformed by an unknown group element, and the goal is to

arXiv:2412.18134v4 Announce Type: replace Abstract: Randomized self-reductions (RSRs) express f(x) using f evaluated at random correlated points, enabling self-correcting programs, instance-hiding pro

arXiv:2507.16362v3 Announce Type: replace Abstract: Chinese License Plate Recognition (CLPR) faces numerous challenges in unconstrained and complex environments, particularly due to perspective distor

arXiv:2605.31057v1 Announce Type: new Abstract: Dense self-attention is the compute and quality bottleneck of long-video diffusion inference: cost grows quadratically with the sequence length, and bey

The Perplexity Agent API documentation includes a 'Search as Code' feature accessible through the sandbox tools section, enabling developers to integrate search functionality programmatically within a

arXiv:2605.31296v1 Announce Type: cross Abstract: Therapeutic mRNA design requires coordinating multiple interacting sequence features across the full transcript, where codon usage, untranslated regio

Nemotron 3 Ultra is NVIDIA's latest language model featuring significant improvements in speed (5X faster) and cost efficiency (30% cheaper) compared to previous versions, positioning it as a frontier

arXiv:2509.00834v2 Announce Type: replace Abstract: This paper addresses the problem of suffix prediction in Business Process Management (BPM) by proposing a Neuro-Symbolic Predictive Process Monitori

arXiv:2602.15018v2 Announce Type: replace-cross Abstract: Neurosim is a fast, real-time, high-performance library for simulating sensors such as dynamic vision sensors, RGB cameras, depth sensors, and

arXiv:2605.31309v1 Announce Type: new Abstract: We survey Lyapunov-based techniques for the finite-time analysis of stochastic iterative algorithms, also known as stochastic approximation (SA) algorit

Personal agents are exploding in popularity, with open source projects like OpenClaw and Hermes seeing rapid adoption by AI developer communities on GitHub. Built to adapt to individual preferences an

Cosmos3-Super-Image2Video is a 64B model for temporally coherent image-to-video generation . NVIDIA's Cosmos platform is designed to accelerate Physical AI development by enabling machines to understa

Cosmos3-Super-Text2Image is a 64 billion parameter omnimodal world model capable of generating high-quality images from text inputs as part of NVIDIA's Cosmos 3 foundation model platform. The model is

arXiv:2605.31090v1 Announce Type: cross Abstract: Mislabeled samples in training datasets severely degrade the performance of deep networks, as overparameterized models tend to memorize erroneous labe

One of the new, buzzy jobs in Silicon Valley is the AI Forward Deployed Engineer (FDE), an engineer who is embedded within a client organization to help customize solutions, such as building and tunin

arXiv:2605.30792v1 Announce Type: cross Abstract: Speech translation systems increasingly span speech-to-text translation (S2TT), speech-to-speech translation (S2ST), offline translation, and streamin

arXiv:2506.12060v2 Announce Type: replace-cross Abstract: Cybersecurity organizations are adapting to GenAI integration through modified frameworks and hybrid operational processes, with success influ

arXiv:2602.06902v2 Announce Type: replace Abstract: In this paper, we study dynamic regret in unconstrained online convex optimization (OCO) with movement costs. Specifically, we generalize the standa

arXiv:2605.31513v1 Announce Type: new Abstract: Large vision-language models (LVLMs) have demonstrated strong general multimodal capability and are increasingly deployed in downstream systems. This tr

arXiv:2602.01553v2 Announce Type: replace-cross Abstract: Link prediction is a core challenge in graph machine learning, demanding models that capture rich and complex topological dependencies. While

arXiv:2605.30803v1 Announce Type: new Abstract: LLM judges are increasingly used to evaluate open-ended responses, but their scores depend strongly on the rubrics that condition them. A vague rubric a

Vercel has made Qwen 3.7 Plus, an AI model, available through its AI Gateway service, allowing developers to access this model via Vercel's platform. This addition expands the model options available

arXiv:2605.30966v1 Announce Type: cross Abstract: Knowledge graphs over corpora of inter-referencing documents - scholarly papers, legal opinions, policy briefs - encode the topology of reference but

arXiv:2508.11911v2 Announce Type: replace-cross Abstract: We introduce a novel data-driven symplectic induced-order modeling (ROM) framework for high-dimensional Hamiltonian systems that unifies laten

arXiv:2605.30960v1 Announce Type: new Abstract: Accurate Zeroth-Order (ZO) Hessian estimation is a cornerstone of derivative-free methods, essential for tasks such as bilevel optimization, Bayesian in

arXiv:2602.00942v3 Announce Type: replace Abstract: Modern large language models are increasingly deployed under compute and memory constraints, making flexible control of model capacity a central cha

arXiv:2511.03100v2 Announce Type: replace-cross Abstract: The agent-environment co-design paradigm jointly optimises agent policies and environment configurations in search of improved system performa

arXiv:2507.06161v2 Announce Type: replace Abstract: Smoothing a signal based on local neighborhoods is a core operation in machine learning and geometry processing. On well-structured domains such as

arXiv:2505.17607v3 Announce Type: replace Abstract: Large Language Models (LLMs) display reasoning capabilities over linguistic and symbolic objects but have limited capabilities to directly interpret

arXiv:2508.19830v2 Announce Type: replace-cross Abstract: Real-world model deployments inevitably encounter distribution shifts, rendering the confidence estimates of deep neural networks highly unrel

arXiv:2605.30600v1 Announce Type: new Abstract: Randomized sketching is a central tool for compressing large-scale optimization problems while preserving accuracy. In particular, sketches that are bas

arXiv:2603.00068v2 Announce Type: replace-cross Abstract: Artificial intelligence (AI) systems impose substantial and growing environmental costs, yet transparency about these impacts has declined eve

arXiv:2602.15293v2 Announce Type: replace-cross Abstract: This paper concerns the question of how AI systems encode semantic structure into the geometric structure of their representation spaces. The

arXiv:2605.31294v1 Announce Type: new Abstract: Recent advances in Audio-LLMs like GPT-4o have ushered in an era of conversational interaction with language models. Conversational avatars however, sti

arXiv:2506.22304v3 Announce Type: replace-cross Abstract: Continuous Normalizing Flows (CNFs) enable elegant generative modeling but remain bottlenecked by their iterative nature requiring costly samp

arXiv:2605.31521v1 Announce Type: new Abstract: Semantic speech tokenizers have become a widely used interface for Audio-LLMs, owing to their compact single-codebook design and strong linguistic align

arXiv:2605.31100v1 Announce Type: new Abstract: We study Vector Linking: given two embedding clouds produced by different black-box encoders over partially overlapping datasets, recover cross-model ob

arXiv:2605.31346v1 Announce Type: cross Abstract: Zeroth-order (black-box) optimization is applied when gradients are unavailable and objective evaluations rely on expensive simulations. In many such

NVIDIA Cosmos 3 is an open-source omni-model designed for physical AI reasoning and action tasks, representing an advancement in multimodal AI systems. The model integrates multiple modalities to enab

arXiv:2605.31226v1 Announce Type: cross Abstract: Machine learning models on microcontroller-class devices (TinyML) face a fundamental challenge: post-deployment distribution change undermines static

Video agent models represent the next frontier in AI by extending language model capabilities to process, understand, and act on video content in real-time, enabling autonomous agents to perceive and