Knowledge catalogue
arXiv:2605.28760v1 Announce Type: new Abstract: Zeroth-order (ZO) fine-tuning is attractive for large language models because it replaces backpropagation with forward objective evaluations. Existing i
arXiv:2605.27825v1 Announce Type: cross Abstract: Membership inference attacks (MIAs) test whether a target data record belongs to a system's private data, and have become a standard tool to measure p
OpenCode now integrates with DigitalOcean's Inference Router, enabling intelligent routing of AI model requests across distributed infrastructure. This integration allows developers to optimize model
arXiv:2605.27526v1 Announce Type: cross Abstract: We develop semiparametrically efficient inference for kernel measures of noise heterogeneity in additive noise models. In many applications, the regre
arXiv:2605.27474v1 Announce Type: cross Abstract: Estimating how an outcome responds to a continuous treatment (the Average Dose-Response Function, or ADRF) is a core causal-inference primitive. Howev
arXiv:2605.27740v1 Announce Type: new Abstract: Long-context inference in large language models (LLMs) is bottlenecked by the linear growth of the self-attention key-value (KV) cache. Top-k sparse att
arXiv:2605.28087v1 Announce Type: new Abstract: Service robots must infer object ownership to correctly interpret instructions such as 'bring me my cup.' However, ownership is a latent attribute that
arXiv:2605.26289v1 Announce Type: new Abstract: Multi-agent tool calling is becoming the dominant interaction pattern for LLM-based systems, yet existing inference frameworks treat each tool call as a
arXiv:2605.24657v1 Announce Type: new Abstract: Major LLM platforms deploy models in an inference-only configuration: the model serves requests but never updates per-user weights. Users must repeatedl
arXiv:2503.07482v2 Announce Type: replace-cross Abstract: Membership Inference Attacks (MIAs) aim to estimate whether a specific data point was used in the training of a given model. Existing state-of
arXiv:2605.24528v1 Announce Type: new Abstract: Real world decision-making requires constructing mental models under uncertainty over evidence, over the underlying causal rules, and over the state of
Artificial intelligence inference routing startup OpenRouter Inc. today announced it raised 113 million in new funding led by CapitalG, Alphabet Inc.’s independent growth fund, to push the envelope fo
This post describes implementing DCGAN (Deep Convolutional Generative Adversarial Network) inference on resource-constrained microcontroller hardware, achieving image generation with a 12.6 million pa
arXiv:2502.13731v5 Announce Type: replace Abstract: This paper addresses a key limitation in existing counterfactual inference methods for Markov Decision Processes (MDPs). Current approaches assume a
arXiv:2605.23158v1 Announce Type: cross Abstract: The deployment of large language models (LLMs) on resource-constrained devices remains challenging, spurring interest in split inference, where models
arXiv:2605.21617v1 Announce Type: new Abstract: Inference from interaction maps, such as centromere identification from genome-wide chromosome conformation capture techniques -- notably Hi-C -- can be
arXiv:2605.21516v1 Announce Type: new Abstract: Harness engineering has emerged as an important inference-time technique for large language model (LLM) agents, aiming to improve long-term performance
NEW paper worth reading. A full agentic workflow can be distilled into model weights and run at roughly 100x lower inference cost while preserving near-frontier task quality. The workflow includes mul
arXiv:2605.20295v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed on mobile devices, where Neural Processing Units (NPUs) necessitate fully static quantization for
arXiv:2605.18856v1 Announce Type: cross Abstract: Long-context inference is increasingly constrained by the KV cache: resident memory grows with context length, and decoding becomes limited by repeate
arXiv:2605.17164v1 Announce Type: cross Abstract: Deploying large-scale LLM training and inference with optimal performance is exceptionally challenging due to a complex design space of parallelism st
arXiv:2512.23752v5 Announce Type: replace-cross Abstract: Recent work has shown that small transformers trained in controlled 'wind-tunnel'' settings can implement exact Bayesian inference, and that t
arXiv:2512.09269v2 Announce Type: replace Abstract: Inferring the eventual goal of a mobile agent from noisy observations of its trajectory is a fundamental estimation problem. We initiate the study o
arXiv:2601.16172v2 Announce Type: replace Abstract: RL-trained Lean theorem provers mode-collapse at inference time: on miniF2F-test with DeepSeek-Prover-V1.5-RL, doubling the i.i.d. sampling budget f
arXiv:2605.17898v1 Announce Type: new Abstract: Gaussian process (GP) inference in Python is dominated by libraries such as GPyTorch and GPflow, which are built on deep-learning frameworks and inherit
'One thing that we've been seeing recently is that inference benchmarks don't really match production workloads that well.' - @realDanFu, VP of Kernels When you're running dozens of concurrent coding
arXiv:2605.18587v1 Announce Type: cross Abstract: Single-cell trajectory inference from destructive time-course snapshots is fundamentally ill-posed: neither cross-time cell correspondences nor contin
arXiv:2605.18031v1 Announce Type: cross Abstract: We propose a quantum sidecar architecture family for future hybrid AI training and inference. The central idea is not to store an entire Transformer i
arXiv:2605.18109v1 Announce Type: new Abstract: In real home deployments, household agents must often operate from a complete household scene and a situated household request, rather than from a clean
arXiv:2605.16397v1 Announce Type: cross Abstract: The increasing integration of sensors in autonomous maritime navigation has led to large-scale multimodal datasets, raising challenges in achieving ef
Clem Delangue argues for increased support and flexibility for local inference engine options rather than restrictions or consolidation. The post advocates for maintaining diverse, locally-deployed AI
arXiv:2605.15694v1 Announce Type: new Abstract: Transformer models are rapidly becoming a cornerstone of modern Internet of Things (IoT) applications, yet their computational and memory demands far ex
The post argues that 'return on inference' (ROI) has become the primary metric for evaluating AI investments and business value over the next 18 months, shifting focus from traditional return on inves
As inference workloads dominate, what if these matmuls could also perform useful work and generate beneficial byproducts!? Similar to all the byproducts we get from crude oil distillation that are not
arXiv:2506.08809v5 Announce Type: replace Abstract: High-resolution sinogram completion is critical for computed tomography reconstruction, as missing projections can introduce severe artifacts. While
arXiv:2605.13784v1 Announce Type: new Abstract: Conventional transformer inference engines are request-driven, paying an O(n) prefill cost on every query. In streaming workloads, where data arrives co
arXiv:2605.13537v1 Announce Type: cross Abstract: Inference-time alignment techniques offer a lightweight alternative or complement to costly reinforcement learning, while enabling continual adaptatio
arXiv:2506.02215v5 Announce Type: replace Abstract: Collision avoidance -- involving a rapid threat detection and quick execution of the appropriate evasive maneuver -- is a critical aspect of driving
arXiv:2605.11527v1 Announce Type: new Abstract: Diffusion models are the leading approach for tabular data synthesis and are increasingly used to share sensitive records. Whether they actually protect
arXiv:2605.11368v1 Announce Type: new Abstract: We study the application of recent Edit Flows for inference-time reward control for DNA sequence generation. Unlike most reward-guided DNA generation fr
probably correct, from @polynoamial: “with today’s AI models, intelligence is a function of inference compute.” but what about tomorrow’s models? never forget that humans are remarkably intelligent (t
arXiv:2605.12255v1 Announce Type: cross Abstract: When people share the same documents and observations yet reach different conclusions, the disagreement often shifts into a judgment that the other pa
arXiv:2605.08429v1 Announce Type: cross Abstract: Post-deployment monitoring of healthcare AI requires statistically valid, label-efficient methods, but gold-standard labels from clinician chart revie
arXiv:2503.05066v5 Announce Type: replace-cross Abstract: The Mixture of Experts (MoE) is an effective architecture for scaling large language models by leveraging sparse expert activation to balance
arXiv:2605.10351v1 Announce Type: new Abstract: Reliable inference requires that artificial intelligence (AI) models provide trustworthy uncertainty estimates, not merely accurate predictions. Recent
arXiv:2601.23252v2 Announce Type: replace-cross Abstract: Model comparison and calibrated uncertainty quantification often require integrating over parameters, but scalable inference can be challengin
arXiv:2605.09656v1 Announce Type: new Abstract: Recent advances in artificial intelligence (AI) have enabled effective perception and language models for robots, but their deployment remains computati
arXiv:2605.08142v1 Announce Type: cross Abstract: Reasoning in large language models is predominantly evaluated through labeled benchmarks, conflating task performance with the quality of internal inf
arXiv:2605.09834v1 Announce Type: cross Abstract: Modern predictive systems encode beliefs that can act as useful prior information for statistical inference in data-limited settings. Using them for p
arXiv:2603.29002v2 Announce Type: replace-cross Abstract: Modern large language models (LLMs) increasingly depends on efficient long-context processing and generation mechanisms, including sparse atte
arXiv:2605.07719v1 Announce Type: cross Abstract: Long-context inference increasingly operates over CPU-resident KV caches, either because decoding-time KV states exceed GPU memory capacity or because
arXiv:2605.07993v1 Announce Type: new Abstract: Causal inference, especially in observational studies, relies on untestable assumptions about the true data-generating process. Sensitivity analysis hel
arXiv:2605.07985v1 Announce Type: cross Abstract: Selecting the optimal LLM inference configuration requires evaluation across hardware, serving engines, attention backends, and model architectures, s
arXiv:2605.07531v1 Announce Type: new Abstract: Black-Box Variational Inference (BBVI) typically relies on Stochastic Gradient Descent (SGD) to optimize the Evidence Lower Bound (ELBO). However, the s
arXiv:2605.06763v1 Announce Type: new Abstract: Sparse attention improves LLM inference efficiency by selecting a subset of key-value entries, but at the cost of potential accuracy degradation. In par
Superhuman and Databricks collaborated to build a high-performance inference platform capable of handling 200,000 queries per second (QPS), leveraging Databricks' infrastructure and optimization capab
arXiv:2605.04376v1 Announce Type: new Abstract: The integration of deep learning approaches in biomedical research has been transformative, enabling breakthroughs in various applications. Despite thes
arXiv:2605.04069v1 Announce Type: new Abstract: We introduce LAWS (Learning from Actual Workloads Symbolically), a self-certifying inference caching architecture that builds a growing library of certi
arXiv:2605.04215v1 Announce Type: new Abstract: Diffusion-based Large Language Models (D-LLMs) represent a promising frontier in generative AI, offering fully parallel token generation that can lead t
arXiv:2505.24791v2 Announce Type: replace Abstract: Discrete normalizing flows are promising generative models with advantages such as analytical log-likelihood computation and end-to-end training. Ho