Search: “inference”

arXiv:2605.30317v1 Announce Type: new Abstract: Autoregressive image and video generators are trained with teacher-forced histories but must sample from their own generated prefixes at inference time,

Based on the available information about llama.cpp, b9378 is likely an intermediate build release of the llama.cpp project. llama.cpp enables LLM inference in C/C++ , and the project releases multiple

arXiv:2605.28516v1 Announce Type: cross Abstract: Simulation-based inference with neural posterior estimation (NPE) often yields overconfident and unreliable posteriors under limited simulation budget

arXiv:2605.28302v1 Announce Type: cross Abstract: Modern large language model (LLM) inference has progressively disaggregated to keep pace with growing model sizes and tight TTFT and TPOT service-leve

arXiv:2511.20439v2 Announce Type: replace-cross Abstract: In Vision Language Models (VLMs), vision tokens are quantity-heavy yet information-dispersed compared with language tokens, thus consume too m

arXiv:2605.27993v1 Announce Type: new Abstract: Object hallucination remains a primary obstacle to the reliable deployment of Multimodal Large Language Models (MLLMs). Current inference-time mitigatio

arXiv:2605.28142v1 Announce Type: cross Abstract: Inference-time sampling can elicit strong reasoning abilities from language models without additional training. Existing power-sampling methods do so

arXiv:2605.26382v1 Announce Type: new Abstract: Deploying high-performing 3D medical image segmenters (e.g., nnU-Net) is often limited by memory footprint and inference latency. Compression is therefo

arXiv:2411.02355v4 Announce Type: replace-cross Abstract: Quantization is a powerful tool for accelerating large language model (LLM) inference, but the accuracy-performance trade-offs across differen

arXiv:2605.26908v1 Announce Type: new Abstract: Exploiting the indistinguishability of objects in a probabilistic graphical model such as a factor graph is key to lifted probabilistic inference algori

arXiv:2605.26582v1 Announce Type: cross Abstract: Discrete diffusion models achieve strong performance in text and image generation, but their inference remains slow and must inherently balance sampli

arXiv:2605.27128v1 Announce Type: new Abstract: Real-time semantic segmentation models offer an excellent balance between accuracy and inference speed. However, deploying these models in dynamic real

arXiv:2605.26632v1 Announce Type: new Abstract: Diffusion Transformers (DiT) achieve strong performance in image generation but incur substantial inference costs. While prior work has reduced this cos

arXiv:2605.27030v1 Announce Type: new Abstract: Test-Time Scaling (TTS) enhances the reasoning capabilities of large language models by allocating additional inference compute to explore the solution

arXiv:2605.27245v1 Announce Type: new Abstract: Symbolic regression (SR) seeks closed-form mathematical expressions that fit observed data. Neural SR methods amortize the search by training an encoder

arXiv:2505.11758v2 Announce Type: replace-cross Abstract: Few-shot adaptation of vision-language models remains fundamentally limited by how negative class signals are handled at inference. Existing m

arXiv:2502.15835v5 Announce Type: replace-cross Abstract: Pragmatic reasoning helps interlocutors infer intended meaning from ambiguous or underspecified messages by considering shared context and cou

arXiv:2603.06687v2 Announce Type: replace-cross Abstract: Geo-temporal understanding, the ability to infer location, time, and contextual properties from visual input alone, underpins applications suc

b9310 is a release build of llama.cpp, a C/C++ implementation for LLM inference . As an intermediate build number in the llama.cpp project's continuous release cycle, it represents incremental updates

Build b9315 is a release version of llama.cpp, a C/C++ implementation for LLM inference. As an intermediate build in the llama.cpp development sequence, b9315 likely includes bug fixes, performance im

llama.cpp is a C/C++ implementation for LLM inference . Build b9319 is a specific commit/version release from the llama.cpp project repository, representing a particular point in the software's develo

arXiv:2605.22883v1 Announce Type: new Abstract: Current AI energy benchmarks measure consumption at the granularity of a single model invocation or training run. For classical single-turn workloads th

arXiv:2605.23434v1 Announce Type: new Abstract: Approximate inference over inducing variables is the central computational bottleneck of Deep Gaussian Processes (DGPs). Existing methods either fit an

llama.cpp is an open-source C/C++ project for LLM inference , and build b9301 is a specific release version in the project's development history. This build number represents an incremental developmen

Clem Delangue reports consuming approximately 17 million tokens daily when running local language models, indicating substantial usage of on-device AI inference. He expresses satisfaction with the uti

arXiv:2605.22262v1 Announce Type: cross Abstract: Audio context determines which sound components and sources are relevant and which can be perceived as irrelevant (noise) by listeners. For example, t

arXiv:2505.22749v2 Announce Type: replace-cross Abstract: Attractor dynamics are a hallmark of many complex systems, including the brain. Understanding how such self-organizing dynamics emerge from fi

arXiv:2605.21553v1 Announce Type: new Abstract: Tokens are becoming the basic units through which foundation models represent and process information for understanding and inference. However, traditio

arXiv:2605.22322v1 Announce Type: new Abstract: Reasoning capability has significantly advanced complex logical inference and robotic decision-making in general domains. However, its potential in the

arXiv:2605.21427v1 Announce Type: new Abstract: Large language model (LLM) inference has become a dominant workload in modern data centers, driving significant GPU utilization and energy consumption.

arXiv:2605.22817v1 Announce Type: cross Abstract: Language models must now generalize out of the box to novel environments and work inside inference-scaling search procedures, such as AlphaEvolve, tha

arXiv:2509.26005v3 Announce Type: replace-cross Abstract: We introduce a formal active learning methodology for guiding the placement of Lagrangian observers to infer time-dependent vector fields -- a

arXiv:2605.21041v1 Announce Type: cross Abstract: Gaussian processes (GPs) offer a principled probabilistic model over functions, but exact inference is restricted to the linear-Gaussian regime. We es

arXiv:2605.20315v1 Announce Type: new Abstract: LLM agents have recently emerged as a powerful paradigm for solving complex tasks through planning, tool use, memory retrieval, and multi-step interacti

arXiv:2605.20894v1 Announce Type: new Abstract: Mobile imitation learning on portable demonstration interfaces faces two coupled bottlenecks: locomotion-contaminated action labels and inference-induce

arXiv:2605.20989v1 Announce Type: new Abstract: Single-cell RNA sequencing provides insights into gene expression at single-cell resolution, yet inferring temporal processes from these static snapshot

arXiv:2605.19950v1 Announce Type: new Abstract: Humans infer emotions by integrating observed multimodal cues with expectations about how affective states may unfold. Existing multimodal large languag

arXiv:2112.08507v5 Announce Type: replace Abstract: Traditional randomized A/B experiments assign arms with uniform random (UR) probability, such as 50/50 assignment to two versions of a website to di

B9251 is a build identifier for a release in the llama.cpp project, which enables LLM inference with minimal setup and state-of-the-art performance on a wide range of hardware - locally and in the clo

arXiv:2605.18810v1 Announce Type: cross Abstract: Speculative decoding accelerates LLM inference by having a small drafter propose tokens that a larger target model verifies in parallel. Recent diffus

arXiv:2605.19283v1 Announce Type: cross Abstract: Sequential prediction is challenging in regimes of delayed disambiguation, where early observations are ambiguous and multiple latent explanations rem

arXiv:2605.19945v1 Announce Type: cross Abstract: Mixture-of-Expert (MoE) models enable efficient inference by employing smaller experts and activating only a subset of them per token. MoE serving eng

arXiv:2411.10959v4 Announce Type: replace-cross Abstract: We study causal inference in experiments and quasi-experiments, where the economic outcome is imperfectly measured by a remotely sensed variab

arXiv:2605.19360v1 Announce Type: new Abstract: The rapid proliferation of AI-generated visual media has created an urgent need for efficient, trustworthy deepfake detection systems. However, existing

arXiv:2605.18796v1 Announce Type: cross Abstract: LLM cascades and model routing promise lower inference cost by sending easy queries to a small model and escalating hard ones to a large model, but mo

arXiv:2605.17000v1 Announce Type: cross Abstract: Optimization of LLM training and inference configurations, such as hyperparameters, data mixtures, and prompts, is critical to performance, but it is