Search: “inference”

arXiv:2512.02543v2 Announce Type: replace Abstract: Deploying LLM agents at scale typically requires choosing between quality and cost. Existing cost-reduction approaches fail to preserve agility: the

arXiv:2603.11331v2 Announce Type: replace-cross Abstract: Adversarial attacks can reliably steer safety-aligned large language models toward unsafe behavior. Empirically, we find that strong adversari

arXiv:2604.15729v1 Announce Type: cross Abstract: Whole Slide Image (WSI) analysis is pivotal in computational pathology, enabling cancer diagnosis by integrating morphological and architectural cues

arXiv:2604.15360v1 Announce Type: new Abstract: This study presents a triadic analysis of energy storage operation under multi-stage model predictive control, investigating the interplay between data

arXiv:2507.20058v3 Announce Type: replace-cross Abstract: Predicting Parkinson's Disease (PD) progression is crucial for personalized treatment, and voice biomarkers offer a promising non-invasive met

arXiv:2509.17292v3 Announce Type: replace-cross Abstract: Cognitive distortions have been closely linked to mental health disorders, yet their automatic detection remains challenging due to contextual

arXiv:2604.15694v1 Announce Type: new Abstract: Discrete diffusion models based on continuous-time Markov chains (CTMCs) have shown strong performance on language and discrete data generation, yet exi

arXiv:2604.16021v1 Announce Type: cross Abstract: Code localization is a cornerstone of autonomous software engineering. Recent advancements have achieved impressive performance on real-world issue be

arXiv:2604.16146v1 Announce Type: new Abstract: Recent works proposed test-time alignment methods that rely on a small aligned model as a proxy that guides the generation of a larger base (unaligned)

arXiv:2604.15364v1 Announce Type: cross Abstract: Edge intelligence is constrained by the energy and latency costs of shuttling data through electronic memory hierarchies. Optical systems offer a fund

arXiv:2604.15558v1 Announce Type: new Abstract: Deliberative multi-agent systems allow agents to exchange messages and revise beliefs over time. While this interaction is meant to improve performance,

arXiv:2602.13088v2 Announce Type: replace-cross Abstract: The distinction between genuine grassroots activism and automated influence operations is collapsing. While contemporary policy debates priori

arXiv:2604.16042v1 Announce Type: cross Abstract: While Large Language Models (LLMs) have achieved strong performance across many NLP tasks, their opaque internal mechanisms hinder trustworthiness and

arXiv:2604.15375v1 Announce Type: cross Abstract: Large Language Models (LLMs) have shown significant improvement in RTL code generation. Despite the advances, the generated code is often riddled with

arXiv:2604.15533v1 Announce Type: cross Abstract: We consider the problem of verification modulo tested library contracts as a step towards automating the verification of client programs that use comp

arXiv:2603.13966v2 Announce Type: replace Abstract: Vision-Language-Action (VLA) models are increasingly evaluated across multiple simulation benchmarks, yet adding each benchmark to an evaluation pip

We’re launching Kimi K2.6 on Fireworks as a Day-0 launch partner! K2.5 was the base for standout models like @Cursor’s Composer 2 and was the most popular model on our training platform. K2.6 on Firew

This post explains the technical details behind common terms and tools encountered on Hugging Face for running large language models locally, including quantization formats (GGUF, Q_4_M, IQ_4XL), opti

“my honest read is that a significant portion of this spending is driven by competitive fear rather than demonstrated returns. Nobody wants to be the company that didn't invest in AI when everyone els

Mooncake is the serving platform for Kimi developed by Moonshot AI, featuring a KVCache-centric disaggregated architecture that separates prefill and decoding clusters while leveraging underutilized C

Loop Payments Inc. today announced that it has raised 95 million in funding to upgrade its supply chain optimization platform. Valor Equity Partners and the Valor Atreides AI Fund led the Series C rou

arXiv:2604.14902v1 Announce Type: cross Abstract: Intelligent embodied agents should not simply follow instructions, as real-world environments often involve unexpected conditions and exceptions. Howe

Cerebras Systems Inc., the developer of the wafer-size WSE-3 artificial intelligence chip, today filed to go public. The move comes about 18 months after the company’s first attempt to list its shares

arXiv:2604.14661v1 Announce Type: cross Abstract: Edge AI model deployment is a multi-stage engineering process involving model conversion, operator compatibility handling, quantization calibration, r

arXiv:2404.00769v5 Announce Type: replace Abstract: Active perception approaches select future viewpoints by using some estimate of the information gain. An inaccurate estimate can be detrimental in c

arXiv:2604.14450v1 Announce Type: new Abstract: Quick and accurate emergency handling in Disaster Decision Support Systems (DDSS) is often hampered by network latency and suboptimal application accura

arXiv:2604.14246v1 Announce Type: new Abstract: Sparse Mixture-of-Experts (MoE) models have achieved remarkable scalability, yet they remain vulnerable to hallucinations, particularly when processing

arXiv:2512.22174v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) deployed in practical and safety-critical settings are increasingly susceptible to bit-flip faults caused by hard

arXiv:2604.15269v1 Announce Type: cross Abstract: The impossibility of simultaneously cloning non-orthogonal states lies at the foundations of quantum theory. Even when allowing for approximation erro

arXiv:2604.14556v1 Announce Type: new Abstract: Video object insertion is a critical task for dynamically inserting new objects into existing environments. Previous video generation methods focus prim

arXiv:2512.14098v3 Announce Type: replace Abstract: Any-to-Any models are an emerging class of multimodal models that accept combinations of text and multimodal data as input and generate them as outp

arXiv:2506.13763v2 Announce Type: replace-cross Abstract: Diffusion models have achieved remarkable success in generative modeling. Despite more stable training, the loss of diffusion models is not in

arXiv:2511.22521v2 Announce Type: replace Abstract: Document visual question answering requires models not only to answer questions correctly, but also to precisely localize answers within complex doc

arXiv:2410.01540v4 Announce Type: replace Abstract: Classical diffusion models typically rely on isotropic Gaussian noise, treating all regions uniformly and overlooking structural information importa

arXiv:2604.14626v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) models have become the dominant architecture for large-scale language models, yet on-premises serving remains fundamentally mem

arXiv:2503.21432v2 Announce Type: replace-cross Abstract: We propose a method to explore the flavor structure of leptons using diffusion models, which are known as one of generative artificial intelli

arXiv:2506.14121v2 Announce Type: replace Abstract: Face super-resolution (FSR) under limited computational budgets remains challenging. Existing methods often treat all facial pixels equally, leading

arXiv:2604.15306v1 Announce Type: cross Abstract: Whether language models can systematically generalize remains actively debated. Yet empirical performance is jointly shaped by multiple factors such a

arXiv:2604.15284v1 Announce Type: new Abstract: The efficient spatial allocation of primitives serves as the foundation of 3D Gaussian Splatting, as it directly dictates the synergy between representa

arXiv:2604.14507v1 Announce Type: new Abstract: As a classic vision task, anomaly detection has been widely applied in industrial inspection and medical imaging. In this task, data scarcity is often a

arXiv:2601.14724v3 Announce Type: replace-cross Abstract: Recent advancements in Multimodal Large Language Models (MLLMs) have demonstrated significant improvement in offline video understanding. Howe

arXiv:2501.09331v3 Announce Type: replace Abstract: A machine that learns a task from observations must encounter and process uncertainty and novelty, especially when it is to maintain performance whe

We are launching Flagship, a native feature flag service built on Cloudflare’s global network to eliminate the latency of third-party providers. By using KV and Durable Objects, Flagship allows for su

arXiv:2604.15107v1 Announce Type: cross Abstract: Feature selection is a classical problem in statistics and machine learning, and it continues to remain an extremely challenging problem especially in

arXiv:2512.05024v3 Announce Type: replace-cross Abstract: As generative AI models are increasingly used to simulate real-world systems, quantifying the ``sim-to-real'' gap is critical. For each input

arXiv:2509.06921v2 Announce Type: replace-cross Abstract: Cybersecurity demands both rapid pattern recognition and deliberative reasoning, yet purely neural or purely symbolic approaches each address