Knowledge catalogue
arXiv:2605.21765v1 Announce Type: new Abstract: The practical adoption of sampling-based inference (SAI) in Bayesian neural networks (BNNs) remains limited, partly due to persistent misconceptions abo
arXiv:2602.06500v2 Announce Type: replace Abstract: Scaling inference methods such as Markov chain Monte Carlo to high-dimensional models remains a central challenge in Bayesian deep learning. A promi
arXiv:2605.20473v1 Announce Type: cross Abstract: Test-time scaling has emerged as a promising approach for improving code generation by exploring large solution spaces at inference time. However, exi
arXiv:2603.10726v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) rely on optimizations like Automatic Prefix Caching (APC) to accelerate inference. APC works by reusing previousl
arXiv:2605.19294v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) policies are typically deployed with asynchronous inference: the robot executes a previously predicted action chunk while
arXiv:2603.14936v3 Announce Type: replace Abstract: Users often possess a clear visual intent but struggle to articulate it precisely in language. This intention-expression gap makes aligning generate
arXiv:2605.18226v1 Announce Type: cross Abstract: Modern large language model (LLM) applications increasingly rely on long conditioning prefixes to control model behavior at inference time. While pref
arXiv:2605.16732v1 Announce Type: new Abstract: Diffusion Transformers (DiTs) achieve state-of-the-art image generation quality but incur substantial memory and computational costs at inference. While
arXiv:2605.18702v1 Announce Type: cross Abstract: Tabular foundation models (TFMs) achieve strong performance on health datasets, but their inference cost and infrastructure requirements limit practic
arXiv:2605.18745v1 Announce Type: cross Abstract: Diffusion-based generative models increasingly rely on inference-time guidance, adding a drift term or reweighting mixture of experts, to improve samp
The modern software development landscape isn’t happening just on one surface — it’s happening across an entire ecosystem of agentic tools. Agents are being developed at an unprecedented scale, and th
arXiv:2605.16126v1 Announce Type: cross Abstract: For a fixed flow-based generative model under a small inference budget, sample quality can depend strongly on where the sampler spends its few functio
Every device, user, and microservice generates data. Ingesting this data, extracting meaning and insights, and driving business decisions in real time has the potential to deliver transformational bus
arXiv:2602.05319v3 Announce Type: replace Abstract: Sequential probabilistic inference from streaming observations requires modeling distributions over future trajectories as new observations arrive.
arXiv:2602.20571v2 Announce Type: replace Abstract: Many benchmarks for automated causal inference evaluate a system's performance based on a single numerical output, such as an Average Treatment Effe
arXiv:2605.13589v1 Announce Type: cross Abstract: Causal discovery, the problem of inferring the direction of causality, is generally ill-posed. We use the language of structural causal models (SCM) t
arXiv:2605.12924v1 Announce Type: new Abstract: The instrumental-variables (IV) setting is standard for partial identification of causal effects when unobserved confounding makes point identification
New course: Transformers in Practice. You'll get a practical view of how transformer-based LLMs work, so you can reason about their behavior, diagnose problems like slow inference, and make smarter de
B9134 is a recent build release of llama.cpp, an open-source C/C++ library for efficient large language model inference. The release was tagged on May 13, 2026, representing an ongoing development ite
arXiv:2605.11202v1 Announce Type: cross Abstract: LLM inference and serving systems have become security-critical infrastructure; however, many of their most concerning failures arise from the serving
arXiv:2605.11019v1 Announce Type: new Abstract: Although large language models rely on chain-of-thought for complex reasoning, the overthinking phenomenon severely degrades inference efficiency. Exist
arXiv:2605.12118v1 Announce Type: cross Abstract: For stochastic process models, parameter inference is often severely bottlenecked by computationally expensive likelihood functions. Simulation-based
arXiv:2605.11506v1 Announce Type: new Abstract: Score-based diffusion models achieve state-of-the-art performance for inverse problems, but their practical deployment is hindered by long inference tim
Databases have introduced new AI-powered SQL functions which take natural language instructions as input and are evaluated using LLMs. They leverage the power of LLMs to answer new kinds of queries: W
arXiv:2602.02281v2 Announce Type: replace-cross Abstract: Backpropagation is typically presented as a symbolic procedure: a backward pass topologically distinct from inference, with non-local error si
arXiv:2601.23087v3 Announce Type: replace Abstract: Learning long-horizon robotic manipulation requires jointly achieving expressive behavior modeling, real-time inference, and stable execution, which
arXiv:2605.09853v1 Announce Type: new Abstract: Post-training techniques combined with inference-time scaling significantly enhance the reasoning and alignment capabilities of large language models (L
arXiv:2603.14681v2 Announce Type: replace Abstract: Bayesian change-point and segmentation models provide uncertainty-aware piecewise-constant representations of ordered data, but exact inference is o
arXiv:2605.09649v1 Announce Type: new Abstract: The key-value (KV) cache is a major bottleneck in long-context inference, where memory and computation grow with sequence length. Existing KV eviction m
arXiv:2605.08696v1 Announce Type: new Abstract: Over the last two decades, language modeling has experienced a shift from predominantly recurrent architectures that process tokens sequentially during
arXiv:2603.22586v2 Announce Type: replace Abstract: In-context learning (ICL) enables task adaptation at inference time by conditioning on demonstrations rather than updating model parameters. Althoug
arXiv:2605.06875v1 Announce Type: cross Abstract: Advanced driver-assistance systems (ADAS) require neural compute engines that deliver low-latency inference under strict power and area constraints. P
arXiv:2602.01166v2 Announce Type: replace Abstract: Vision-Language-Action (VLA) models benefit from chain-of-thought (CoT) reasoning, but existing approaches incur high inference overhead and rely on
arXiv:2605.07180v1 Announce Type: new Abstract: LLM agents achieve strong performance on complex reasoning tasks but incur high latency and compute cost. In practice, many queries fall within the capa
arXiv:2605.04754v1 Announce Type: new Abstract: Deep neural network (DNN) inference at the edge demands simultaneous improvements in accuracy, computational efficiency, and energy consumption. Approxi
arXiv:2605.01566v1 Announce Type: new Abstract: Advances in inference methods have enabled language models to improve their predictions without additional training. These methods often prioritize raw
arXiv:2605.04039v1 Announce Type: new Abstract: Clinical LLMs are often scaled by increasing model size, context length, retrieval complexity, or inference-time compute, with the implicit expectation
arXiv:2512.12744v3 Announce Type: replace Abstract: Activation sparsity offers a compelling route to accelerate large language model (LLM) inference by selectively suppressing hidden activations, yet
arXiv:2604.26412v1 Announce Type: new Abstract: Speculative decoding accelerates LLM inference, but SOTA hidden-state-based drafters suffer from long-range decay: draft accuracy degrades as the specul
arXiv:2512.12087v3 Announce Type: replace Abstract: The growing demand for long-context inference capabilities in Large Language Models (LLMs) has intensified the computational and memory bottlenecks
arXiv:2604.22901v1 Announce Type: new Abstract: Diffusion models achieve remarkable success in time series generation. However, slow inference limits their practical deployment. We propose E^2-CRF (Er
arXiv:2604.23821v1 Announce Type: cross Abstract: Autonomous neutron spectroscopy must solve three distinct tasks: detection (where is the signal?), inference (which Hamiltonian governs it?), and refi
arXiv:2604.24637v1 Announce Type: cross Abstract: Block-sequential continual learning demands that a single model both protect prior solutions from catastrophic forgetting and efficiently infer at inf
arXiv:2603.17573v2 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) Models have become the mainstream solution for robot control, but suffer from slow inference speeds. Speculative
arXiv:2604.24586v1 Announce Type: new Abstract: Single-image point cloud reconstruction must infer complete 3D geometry, including occluded parts, from a single RGB image. While diffusion-based recons
arXiv:2604.23514v1 Announce Type: cross Abstract: The health condition of components in civil infrastructures can be described by various discrete states according to their performance degradation. In
arXiv:2510.19020v2 Announce Type: replace-cross Abstract: We propose a new method for statistical inference in generalized linear models. In the overparameterized regime, Principal Component Regressio
arXiv:2601.11194v2 Announce Type: replace Abstract: We suggest a new multi-modal algorithm for joint inference of paired structurally aligned samples with Rectified Flow models. While some existing me
arXiv:2604.21489v1 Announce Type: cross Abstract: Multi-modal trajectory generation is essential for safe autonomous driving, yet existing diffusion-based planners suffer from high inference latency d
arXiv:2604.21057v1 Announce Type: new Abstract: The field of Language Reasoning Models (LRMs) has been very active over the past few years with advances in training and inference techniques enabling L
arXiv:2603.09046v2 Announce Type: replace-cross Abstract: Device-side Large Language Models (LLMs) have witnessed explosive growth, offering higher privacy and availability compared to cloud-side LLMs
arXiv:2604.19431v1 Announce Type: cross Abstract: Generative AI systems are known to amplify biases present in their training data. While several inference-time mitigation strategies have been propose
Today at Google Cloud Next, we’re announcing new capabilities in Google Distributed Cloud (GDC) that bring Gemini and our advanced AI stack to wherever your data is, so you don’t need to compromise be
arXiv:2503.23439v2 Announce Type: replace-cross Abstract: Spoken dialogue systems powered by large language models have demonstrated remarkable abilities in understanding human speech and generating a
arXiv:2604.19635v1 Announce Type: cross Abstract: While generative models have set new benchmarks for Target Speaker Extraction (TSE), their inherent reliance on global context precludes deployment in
arXiv:2604.16581v1 Announce Type: new Abstract: Neural Combinatorial Optimization (NCO) has emerged as a powerful framework for solving combinatorial optimization problems by integrating deep learning
arXiv:2503.15845v2 Announce Type: replace Abstract: Network-wide Traffic State Estimation (TSE), which aims to infer a complete image of network traffic states with sparsely deployed sensors, plays a
arXiv:2601.02970v2 Announce Type: replace Abstract: Self-Consistency improves reasoning reliability through multi-sample aggregation, but incurs substantial inference cost. Adaptive self-consistency m
arXiv:2604.16535v1 Announce Type: new Abstract: Test-time scaling (TTS) improves large language models (LLMs) by allocating additional compute at inference time. In practice, TTS is often achieved thr
arXiv:2511.17408v4 Announce Type: replace-cross Abstract: Probing has emerged as a promising method for monitoring large language models (LLMs), enabling cheap inference-time detection of concerning b