Search: “inference”

arXiv:2604.16299v1 Announce Type: new Abstract: We introduce LaviGen, a framework that repurposes 3D generative models for 3D layout generation. Unlike previous methods that infer object layouts from

arXiv:2603.19339v2 Announce Type: replace-cross Abstract: Dimensionality reduction is critical for deploying dense retrieval systems at scale, yet mainstream post-hoc methods face a fundamental trade-

arXiv:2604.15727v1 Announce Type: new Abstract: Large language models exhibit systematic limitations in structured logical reasoning: they conflate hypothesis generation with verification, cannot dist

arXiv:2511.00739v3 Announce Type: replace Abstract: Agentic AI serving converts monolithic LLM-based inference to autonomous problem-solvers that can plan, call tools, perform reasoning, and adapt on

arXiv:2411.12502v4 Announce Type: replace-cross Abstract: Neural Processes (NPs) are a rapidly evolving class of models designed to directly model the posterior predictive distribution of stochastic p

arXiv:2604.15938v1 Announce Type: new Abstract: Diffusion policies are becoming mainstream in robotic manipulation but suffer from hard negative class imbalance due to uniform sampling and lack of sam

B8846 is a release version of llama.cpp, a C/C++ inference engine for running large language models locally. The release includes pre-built binaries and libraries for multiple platforms including macO

b8848 is a release from llama.cpp, an open-source C/C++ project for LLM inference . This release builds on the rapidly-developing codebase with regular updates that include bug fixes, feature improvem

The llama.cpp project is the main playground for developing new features for the ggml library , and the main goal of llama.cpp is to enable LLM inference with minimal setup and state-of-the-art perfor

Release b8838 is a version of llama.cpp, a C/C++ implementation for LLM inference. The release likely contains bug fixes, performance improvements, and updates to the codebase for running large langua

b8840 is a release version of llama.cpp, a C/C++ implementation for large language model inference. This release build includes compiled binaries and updates for various platforms and hardware acceler

b8832 is a recent build release of llama.cpp from April 17, 2026 . Llama.cpp is a C/C++ implementation for running large language model inference efficiently on consumer hardware with minimal setup. T

arXiv:2604.15153v1 Announce Type: new Abstract: Large Language Models (LLMs) incur significant computational and memory costs when processing long prompts, as full self-attention scales quadratically

arXiv:2602.22699v2 Announce Type: replace-cross Abstract: SQL is the de facto interface for exploratory data analysis; however, releasing exact query results can expose sensitive information through m

arXiv:2510.08055v2 Announce Type: replace Abstract: Large Language Model (LLM) inference in production must meet stringent service-level objectives for both time-to-first-token (TTFT) and time-between

arXiv:2604.14582v1 Announce Type: new Abstract: High-resolution (HR) land-cover mapping is often constrained by the high cost of dense HR annotations. We revisit this problem from the perspective of m

arXiv:2604.14698v1 Announce Type: new Abstract: Diffusion models have recently emerged as expressive policy representations for online reinforcement learning (RL). However, their iterative generative

arXiv:2602.07529v3 Announce Type: replace Abstract: Large language models (LLMs) have demonstrated strong performance and rapid progress in a wide range of medical reasoning tasks. However, their sequ

arXiv:2604.14158v1 Announce Type: new Abstract: Current evaluations of long-term memory in LLMs are fundamentally static. By fixating on simple retrieval and short-context inference, they neglect the

arXiv:2604.15063v1 Announce Type: new Abstract: Gradient inversion attacks threaten client privacy in federated learning by reconstructing training samples from clients' shared gradients. Gradients ag

arXiv:2510.17568v5 Announce Type: replace Abstract: Recent 3D feed-forward models, such as the Visual Geometry Grounded Transformer (VGGT), have shown strong capability in inferring 3D attributes of s

arXiv:2604.15022v1 Announce Type: cross Abstract: Cost-aware routing dynamically dispatches user queries to models of varying capability to balance performance and inference cost. However, the routing

arXiv:2604.15237v1 Announce Type: new Abstract: Reconstructing dense 3D geometry from continuous video streams requires stable inference under a constant memory budget. Existing O(1) frameworks primar

b8811 is a release build from llama.cpp, a C/C++ library for LLM inference . The project releases multiple versions frequently as part of its rapid development cycle , with b8811 representing one of t

arXiv:2604.13824v1 Announce Type: new Abstract: World models have been emerging as critical components for assessing the consequences of actions generated by interactive agents in online planning and

We built a custom technology stack to run fast large language models on Cloudflare’s infrastructure. This post explores the engineering trade-offs and technical optimizations required to make high-per

arXiv:2604.13327v1 Announce Type: cross Abstract: Modern GPU workloads, especially large language model (LLM) inference, suffer from kernel launch overheads and coarse synchronization that limit inter

arXiv:2604.14048v1 Announce Type: new Abstract: Feed-forward 3D reconstruction models are efficient but rigid: once trained, they perform inference in a zero-shot manner and cannot adapt to the test s

arXiv:2604.14053v1 Announce Type: new Abstract: Efficiency and safety of Large Language Models (LLMs), among other factors, rely on the quality of tokenization. A good tokenizer not only improves infe

arXiv:2512.02697v3 Announce Type: replace Abstract: Cross-view geo-localization infers a location by retrieving geo-tagged reference images that visually correspond to a query image. However, the trad

arXiv:2604.13993v1 Announce Type: cross Abstract: Physical reasoning over visual inputs demands tight integration of visual perception, domain knowledge, and multi-step symbolic inference. Yet even st

arXiv:2510.18165v2 Announce Type: replace-cross Abstract: Diffusion language models (DLMs) are emerging as a powerful and promising alternative to the dominant autoregressive paradigm, offering inhere

arXiv:2604.14069v1 Announce Type: new Abstract: Human-Object Interaction (HOI) detection is a longstanding computer vision problem concerned with predicting the interaction between humans and objects.

arXiv:2604.12129v1 Announce Type: new Abstract: The transition from stateless model inference to stateful agentic execution is reshaping the systems assumptions underlying modern AI infrastructure. Wh

Build **b8798** is an incremental release of [llama.cpp](https://github.com/ggml-org/llama.cpp), the open-source C/C++ framework for running large language model inference locally and in the cloud. Li

Build **b8799** is an incremental release of [llama.cpp](https://github.com/ggml-org/llama.cpp), the open-source C/C++ framework for running large language model inference locally and in the cloud. Li

**b8802** is a numbered incremental build release of [llama.cpp](https://github.com/ggml-org/llama.cpp), an open-source C/C++ framework for running large language model (LLM) inference locally and in

Build b8804 is an automated incremental release of [llama.cpp](https://github.com/ggml-org/llama.cpp), the open-source C/C++ framework for local LLM inference. Like all llama.cpp builds, it is trigger

**b8806** is a sequential build release of [llama.cpp](https://github.com/ggml-org/llama.cpp), an open-source C/C++ framework for running large language model (LLM) inference locally. Like other numbe

**b8807** is a sequentially numbered automated build release of [llama.cpp](https://github.com/ggml-org/llama.cpp), an open-source C/C++ framework for running large language model (LLM) inference loca

arXiv:2602.00181v3 Announce Type: replace-cross Abstract: Understanding camera dynamics is a fundamental pillar of video spatial intelligence. However, existing multimodal models predominantly treat t

arXiv:2604.12424v1 Announce Type: cross Abstract: Multimodal Large Language Models frequently suffer from inference hallucinations, partially stemming from language priors dominating visual evidence.

arXiv:2604.12035v1 Announce Type: new Abstract: Visual token pruning is a widely used strategy for efficient inference in multimodal large language models (MLLMs), but existing work mainly evaluates i

arXiv:2604.12518v1 Announce Type: new Abstract: Multimodal sentiment analysis (MSA) integrates heterogeneous text, audio, and visual signals to infer human emotions. While recent approaches leverage c

Have found the same things! Using glm-5 as a daily driver for a lot of things We've tested new OSS models the moment they're released for a while at Lindy. Inference is our #1 cost by a lot (more than

arXiv:2511.21356v2 Announce Type: replace-cross Abstract: Adversarial Inverse Reinforcement Learning (AIRL) has shown promise in addressing the sparse reward problem in reinforcement learning (RL) by