Search: “inference”

arXiv:2609.06674v1 Announce Type: cross Abstract: We present a new attack that reconstructs the text generated by locally hosted LLMs by observing CPU cache activity during detokenization. Unlike prio

arXiv:2609.05782v1 Announce Type: new Abstract: Vision-language models (VLMs) offer a promising alternative to conventional fire detection systems by reasoning about the semantic context of a scene an

arXiv:2504.18376v3 Announce Type: replace-cross Abstract: Natural Language Inference (NLI) is a central task in natural language understanding with applications in fact-checking, question answering, a

arXiv:2609.09476v1 Announce Type: cross Abstract: In-vehicle assistants must translate natural-language requests into accurate vehicle function calls under strict memory and latency constraints, makin

arXiv:2609.07987v1 Announce Type: new Abstract: LLM-based digital twins promise to reduce repeated human data collection by generating person- specific responses, yet existing evaluations provide litt

arXiv:2606.19376v2 Announce Type: replace Abstract: Inference costs for large language model (LLM) applications are rapidly growing, driven by surging demand and rising infrastructure cost. Users expe

arXiv:2602.17196v2 Announce Type: replace Abstract: Multimodal large language models (MLLMs) incur substantial inference cost due to the processing of hundreds of visual tokens per image. Although tok

arXiv:2609.07816v1 Announce Type: new Abstract: Linear attention is increasingly used in frontier language models for efficient long-context inference and constant-memory decoding. Its fixed-size recu

Automated lint: 12 errors, 53990 warnings, 3 info

arXiv:2508.11431v3 Announce Type: replace Abstract: An object can disappear from a 3D scene, yet still be detectable. Even after visual removal, modern vision models may infer what was originally pres

arXiv:2609.05519v1 Announce Type: new Abstract: We propose a unified strategy for fast goal inference in human-robot interaction. The core idea is to drive the human toward Critical Decision Points (C

arXiv:2609.07734v1 Announce Type: new Abstract: Gaussian Splatting has been effective in inferring scene representations that excel in novel view synthesis. Multiple splats cooperate seamlessly to syn

A few weeks ago, I saw this post where the author trained a SIREN MLP to implicitly memorize Bad Apple as a coordinate function: (t, y, x) to pixel. That got me curious about a slightly different form

I'm testing a new approach for reducing the cost of image-based LLM inference. I evaluated it on the MOMA Graph benchmark, using 1,315 questions. Compared with using GPT-4o to process the original ima

Pathway's Baby Dragon Hatchling (BDH) is a brain-inspired, post-transformer architecture that reasons in latent space instead of emitting chain-of-thought tokens. See how Pathway develops and scales B

arXiv:2609.05081v1 Announce Type: new Abstract: This paper introduces Deep Microcompression (DMC), a hardware-aware pipeline for deep learning inference on bare-metal microcontrollers. DMC integrates

arXiv:2609.04271v1 Announce Type: new Abstract: Wi-Fi-based human activity recognition (HAR) has become an important part of integrated sensing and communications, paving the way for a range of contex

arXiv:2509.25175v3 Announce Type: replace-cross Abstract: Large language model (LLM) steering has emerged as a promising paradigm for controlling model behavior at inference time through targeted mani

arXiv:2609.02984v1 Announce Type: new Abstract: The conventional approach to machine learning, that is, collecting data, training models, and performing inference in a single location, faces fundament

arXiv:2609.03229v1 Announce Type: new Abstract: Networks describe systems in biology and beyond, from protein interactions and social relationships to power grids and citation records. Reasoning about

arXiv:2609.03216v1 Announce Type: new Abstract: Vision Transformers (ViTs) typically process every image using a fixed input resolution and model width, even though many images can be classified with

arXiv:2609.02089v1 Announce Type: new Abstract: Steering aligns large language models (LLMs) by injecting a bias into selected activations at inference time, offering a far cheaper alternative to weig

arXiv:2609.02471v1 Announce Type: new Abstract: Target templates define what a visual tracker searches for, yet the templates available at inference trade off localization certainty with appearance fr

arXiv:2505.23713v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly deployed in socially grounded applications, where success requires interpreting context, inferring oth

arXiv:2609.02886v1 Announce Type: new Abstract: We introduce SolarWM, a fully open foundation for building interactive video world models from data preparation through long-horizon inference. Training

Frontier intelligence is going local. At IFA 2026, NVIDIA, Microsoft and its partners are teaming up to provide faster inference and new tools that make agents easier to set up and run locally on NVID

A noisy code reviewer gets ignored. Flag too many non-issues and engineers tune it out. @Macroscope got the control they needed with the Fireworks Training API to train a model using their own advanta

arXiv:2609.00577v1 Announce Type: cross Abstract: Multi-agent combinatorial optimization problems are notoriously challenging due to their NP-hard nature. Recent parallel autoregressive neural solvers

arXiv:2609.00896v1 Announce Type: new Abstract: Bayesian methodologies for handling count-valued time series have gained prominence due to their ability to infer interpretable latent structures and to

arXiv:2609.00224v1 Announce Type: cross Abstract: Weight-only post-training quantization (PTQ) can alleviate the computational burden of serving large language models (LLMs) at scale. However, existin

arXiv:2609.00834v1 Announce Type: cross Abstract: Modern Text-to-SQL systems often follow generate-execute-select pipelines, generating multiple candidate queries then selecting the best one. Listwise

I'm planning to upgrade my workstation (linux with 5700X/64GB DDR4) for local inference and pytorch training. I'm trying to decide between: 2× AMD Radeon AI PRO R9700 32GB 2× AMD Radeon PRO W7800 48GB

arXiv:2608.28673v1 Announce Type: new Abstract: Deploying vision perception models in autonomous vehicles requires that we prioritize inference speeds, resulting in a model with shallower architecture

arXiv:2608.29208v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models, built upon Vision-Language Models (VLMs), have significantly enhanced robotic capabilities by leveraging internet

arXiv:2608.29934v1 Announce Type: new Abstract: KV-cache compression reduces LLM inference memory by evicting context tokens, but when the evicted tokens contain answer-bearing evidence, the model may

arXiv:2510.22876v4 Announce Type: replace-cross Abstract: Inference optimizations are routinely evaluated by throughput alone, without verifying output correctness. We conduct a forensic analysis of b

arXiv:2505.16990v3 Announce Type: replace Abstract: In this work, we propose Dimple, the first Discrete Diffusion Multimodal Large Language Model (DMLLM). We observe that training with a purely discre

arXiv:2608.30439v1 Announce Type: cross Abstract: Inference with transformer-based large language models (LLMs) is often limited by the memory-bound KV cache and quadratic attention cost. State-space

arXiv:2608.31066v1 Announce Type: new Abstract: Chain-of-thought (CoT) reasoning improves multi-step problem solving, but long reasoning traces inflate inference cost. Token-level CoT compression redu

arXiv:2607.17486v2 Announce Type: replace-cross Abstract: As large language models (LLMs) process increasingly longer prompts, computation and KV-cache memory costs have emerged as major bottlenecks i

arXiv:2608.30399v1 Announce Type: cross Abstract: Large language models (LLMs) exhibit strong semantic reasoning and open-ended generation abilities, but aligning these abilities with structured seque

arXiv:2608.29432v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models reduce inference cost by executing multiple actions per call, but longer horizons often degrade accuracy because raw

arXiv:2608.30135v1 Announce Type: new Abstract: Speculative decoding accelerates large language model inference by using a draft model to generate candidate tokens, which are verified by the target mo

All week we’re spotlighting teams training past the frontier on Fireworks. @Figma’s AI team is shipping features that change how millions of people design, and with the Training API they can iterate f

arXiv:2608.27513v1 Announce Type: new Abstract: Softmax attention stores key and value vectors for every preceding token, causing inference memory to grow with sequence length. Recent language models

arXiv:2602.18154v3 Announce Type: replace Abstract: Jailbreaking poses a significant risk to the deployment of Large Language Models (LLMs) and Vision Language Models (VLMs). VLMs are particularly vul