Search: “inference”

arXiv:2607.27990v1 Announce Type: cross Abstract: Spiking Neural Networks (SNNs) communicate through sparse binary spike events rather than dense activations, enabling energy-efficient inference on ne

arXiv:2607.27704v1 Announce Type: cross Abstract: As large language models (LLMs) continue to demonstrate exceptional capabilities across various domains, the challenge of achieving energy-efficient a

arXiv:2607.24692v1 Announce Type: cross Abstract: Inference systems increasingly combine a fast path that returns predictions within the application's latency deadline together with a higher-accuracy

arXiv:2607.23771v1 Announce Type: new Abstract: Large language model (LLM) performance increasingly depends not only on the base model, but also on the inference-time controller used to organize reaso

arXiv:2607.12829v1 Announce Type: cross Abstract: Diffusion large language models (dLLMs) offer a theoretical advantage in parallel generation over standard autoregressive models. However, parallel ge

arXiv:2607.12095v1 Announce Type: cross Abstract: Sensor-rich data-driven applications increasingly use Bayesian approaches to infer latent states of dynamic systems from noisy sensor measurements and

arXiv:2607.02781v1 Announce Type: cross Abstract: Inference-time alignment steers a frozen language model during decoding using auxiliary reward signals, avoiding the cost of repeated weight updates.

arXiv:2606.27802v1 Announce Type: new Abstract: Hierarchical predictive coding provides an interpretable framework for perception as error-driven inference in multi-layer generative models, while spar

arXiv:2606.28024v1 Announce Type: new Abstract: Lifted inference exploits indistinguishabilities in probabilistic graphical models by using a representative for indistinguishable objects, thereby spee

arXiv:2606.09635v1 Announce Type: cross Abstract: Ensuring the reliability of Large Language Models (LLMs) under distribution drift requires inference-time adaptation. While inference-time alignment m

arXiv:2512.16349v2 Announce Type: replace-cross Abstract: We propose a collaborative edge-to-server inference framework for vision-language models (VLMs) that reduces communication cost while maintain

arXiv:2605.30898v1 Announce Type: new Abstract: In real-world deployments of large language models (LLMs), balancing inference quality and computational cost has become a central challenge. Existing a

arXiv:2605.29467v1 Announce Type: cross Abstract: Stacking probabilistic building blocks into deeper architectures typically breaks closed-form inference. We show that closed-form inference can be pre

arXiv:2605.28224v1 Announce Type: new Abstract: Multi-trajectory inference for tool-use LLM agents - generating multiple reasoning attempts and selecting among them - benefits from transferring knowle

arXiv:2605.19317v1 Announce Type: cross Abstract: Inference-time scaling has emerged as a major approach for improving reasoning capabilities, and has been increasingly applied to diffusion models. Ho

arXiv:2605.19537v1 Announce Type: new Abstract: Progress in LLMs is increasingly measured through standardized benchmarks, where state-of-the-art improvements are often separated by fractions of a per

arXiv:2604.27368v1 Announce Type: new Abstract: Statistical inference in observational science typically relies on a fundamental assumption: as sample size increases and uncertainties decrease, the in

arXiv:2604.26334v1 Announce Type: cross Abstract: To usher in the next round of client AI innovation, there is an urgent need to enable efficient, lossless inference of high-accuracy large language mo

arXiv:2510.13763v2 Announce Type: replace-cross Abstract: Amortized simulator-based inference offers a powerful framework for tackling Bayesian inference in computational fields such as engineering or

arXiv:2604.16400v1 Announce Type: cross Abstract: As Large Language Models (LLMs) are increasingly adopted in edge intelligence to power domain-specific applications and personalized services, the qua

arXiv:2604.16714v1 Announce Type: new Abstract: Classical mixture models (MMs) are widely used tractable proposals for approximate inference settings such as variational inference (VI) and importance

arXiv:2602.11528v2 Announce Type: replace-cross Abstract: Recent studies have shown that large language models (LLMs) can infer private user attributes (e.g., age, location, gender) from user-generate

arXiv:2610.15281v1 Announce Type: new Abstract: Verifier-guided inference-time scaling uses additional computation to score intermediate states and steer generation toward better outputs. However, imp

arXiv:2610.14723v1 Announce Type: new Abstract: A method integrating policy gradient with fuzzy inference has been proposed. This method, hereafter referred to as the base model, has high flexibility

arXiv:2610.17591v1 Announce Type: new Abstract: Estimating simulation-ready material parameters from visual observations is crucial for deformable-object manipulation but challenging because material

arXiv:2610.13132v1 Announce Type: new Abstract: LLM-as-a-Service has become a dominant paradigm for accessing large language models without requiring local deployment. However, the process raises seve

arXiv:2508.19458v2 Announce Type: replace Abstract: A membership-inference attack gets the output of a learning algorithm, and a target individual, and tries to determine whether this individual is a

arXiv:2610.07391v1 Announce Type: cross Abstract: We present a new perspective on the problem of likelihood approximation within the framework of simulation-based inference that promotes scalable and

arXiv:2610.08444v1 Announce Type: new Abstract: Vision-language-action (VLA) policies repeatedly invoke inference to control robots, making graphics processing unit (GPU) energy a recurring cost of ta

arXiv:2610.08268v1 Announce Type: cross Abstract: Pervasive intelligent applications are increasingly deployed on mobile and Internet of Things (IoT) edge devices. Consequently, Large Language Models

arXiv:2610.08689v1 Announce Type: new Abstract: Counterfactual inference in Gaussian-process structural causal models (GP-SCMs) has been developed primarily for continuous endogenous variables, limiti

arXiv:2610.07311v1 Announce Type: new Abstract: Agentic memory allows LLM agents to reuse past experience, yet retrieved memories can also distort inference even when they are benign, correctly stored

arXiv:2609.40070v1 Announce Type: cross Abstract: When inference demand exceeds available compute capacity, model providers must decide which requests should be served first. Users have different tole

arXiv:2609.39525v1 Announce Type: cross Abstract: Casting Bayesian inference as a neural network optimization problem targeting an amortized posterior is attractive, as it extends to otherwise intract

arXiv:2609.38090v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) models are a compelling architecture for scaling model capacity, making them especially attractive for deployment on resource-c

arXiv:2609.30993v1 Announce Type: cross Abstract: We present FLIP, a final-layer inference-time probe for testing whether a logit-facing intervention site in an open-weight vision-language model (VLM)

arXiv:2609.30270v1 Announce Type: new Abstract: On-device inference with small language models keeps user data local, works offline, and incurs no per-query cost, so the on-device tier is preferred wh

arXiv:2609.21392v1 Announce Type: new Abstract: Natural audio-visual interaction is emerging as an important interface for AI assistants, allowing users to communicate through speech and vision rather

arXiv:2609.20614v1 Announce Type: cross Abstract: Frontier AI models are rapidly gaining the ability to exploit vulnerabilities in complex pieces of software. The risk is not theoretical, as evidenced

arXiv:2609.18045v1 Announce Type: new Abstract: Recovering latent interaction structures from multi-agent dynamics is important for understanding and predicting interacting systems. Trajectory-based s

arXiv:2609.16742v1 Announce Type: cross Abstract: Convolutional Neural Networks (CNNs) are increasingly deployed in safety-critical edge applications, where soft errors can silently corrupt inference

arXiv:2609.17193v1 Announce Type: new Abstract: Large language model (LLM)-powered agentic AI services increasingly demand low-latency inference, motivating the deployment of LLMs across distributed e

arXiv:2609.14213v1 Announce Type: cross Abstract: Modern mobile inference runs on heterogeneous platforms combining mobile GPUs with multiple CPU core clusters. Existing optimizations typically exploi

arXiv:2609.12421v1 Announce Type: cross Abstract: We study an online sketched Newton method that approximates the Newton direction at each step via a state-of-the-art sketching solver, called the gene

arXiv:2609.11334v1 Announce Type: new Abstract: Natural Language Inference processes pairs of sentences to extract their semantic relations. NLI has been a hot research topic, integrated as a main com

arXiv:2609.11799v1 Announce Type: cross Abstract: Large language models are often fine-tuned, shared, or downloaded from third parties, so a deployed model may carry a hidden backdoor that behaves nor