Knowledge catalogue
arXiv:2606.12243v1 Announce Type: cross Abstract: Speculative decoding (SD) addresses the high inference costs of LLMs by having lightweight drafters generate candidates for large verifiers to validat
The search results did not contain specific information about the b9592 release. Based on the available information, b9592 is a version release from the llama.cpp project, which is an LLM inference sy
arXiv:2603.21350v2 Announce Type: replace Abstract: Epistemic reasoning requires agents to infer the state of the world from partial observations and information about other agents' knowledge. Prior w
arXiv:2606.10820v1 Announce Type: cross Abstract: Autoregressive (AR) language modeling is the dominant paradigm for text generation, yet its sequential token-by-token decoding makes inference memory-
arXiv:2606.11180v1 Announce Type: new Abstract: Diffusion-based lip synchronization models achieve strong visual quality and audio-visual alignment, but full-sequence bidirectional attention and many
arXiv:2606.11187v1 Announce Type: new Abstract: Autoregressive video generation has emerged as a powerful paradigm for World Action Models (WAMs). However, existing approaches suffer from slow trainin
arXiv:2606.10908v1 Announce Type: cross Abstract: We introduce a spoofing countermeasure architecture conditioned on speaker-reference recordings, but observe that it converges to a solution that effe
arXiv:2606.11164v1 Announce Type: new Abstract: Long chain-of-thought (CoT) trajectories in large language model (LLM) reasoning cause severe inference bottlenecks due to rapid key-value (KV) cache gr
arXiv:2606.10520v1 Announce Type: new Abstract: Post-training quantization at the 2-bit level enables low-cost deployment and inference acceleration for large language models (LLMs). Scalar quantizati
arXiv:2508.07048v2 Announce Type: replace-cross Abstract: Autoregressive (AR) encoder-decoder models dominate high-quality multilingual ASR, but their left-to-right decoders make inference latency sca
arXiv:2606.08682v1 Announce Type: cross Abstract: Activation steering has emerged as a popular inference-time technique for modulating the behavior of large language models (LLMs). By constructing a s
Release b9585 of llama.cpp fixes granite speech model inference by applying embedding scale when deepstack is not used . The release was published on June 9, 2026, and represents a bug fix within the
arXiv:2606.08454v1 Announce Type: new Abstract: Activation steering provides a lightweight inference-time mechanism for controlling large language models (LLMs) by modifying their internal activation
arXiv:2606.08584v1 Announce Type: new Abstract: Sparse coding provides a principled framework for signal representation by expressing an input as a linear combination of only a small number of basis f
arXiv:2606.09659v1 Announce Type: cross Abstract: Long-context language model inference is bottlenecked by memory, as the KV cache grows with context length. Recent techniques to compress the KV cache
arXiv:2606.08375v1 Announce Type: new Abstract: All-atom generative modeling of 3D biomolecular complexes has emerged as the dominant paradigm for predicting the structure of proteins and protein-liga
arXiv:2606.08303v1 Announce Type: new Abstract: This paper investigates a novel concept of time series geolocalization, where the goal is to infer the geographic origin of each raw time series. Succes
arXiv:2606.08978v1 Announce Type: new Abstract: Hypergraph knowledge distillation aims to retain the predictive performance of a hypergraph neural network (HNN) teacher while reducing inference costs
arXiv:2606.07525v1 Announce Type: cross Abstract: Causal graphs in text are typically populated by observable, predefined events. In contrast, we study implicit causal graph construction from text by
arXiv:2606.09343v1 Announce Type: new Abstract: Neural combinatorial optimization has recently achieved strong results on the Euclidean Traveling Salesman Problem (TSP) using generative models such as
arXiv:2606.08511v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) face a significant inference bottleneck due to the quadratic computational cost of self-attention over long vis
NVIDIA GPUs with Confidential Computing are now used for confidential inference in Apple’s Private Cloud Compute (PCC), as it expands beyond Apple’s data centers to Google Cloud. Unveiled during Apple
arXiv:2602.05774v4 Announce Type: replace-cross Abstract: Speculative decoding accelerates inference for (M)LLMs, yet a training-decoding discrepancy persists: while existing methods optimize single g
arXiv:2606.07710v1 Announce Type: cross Abstract: The autoregressive nature of large language models (LLMs) remains a significant bottleneck for inference, particularly in complex agentic workloads. W
Based on available search results, I cannot find specific details about the b9568 release. B9568 is a build number from llama.cpp, an LLM inference implementation in C/C++ . This release likely contai
Gemma 4 MTP (Multi-Token Prediction) has been officially integrated into llama.cpp, enabling developers to build faster AI experiences by using the model with this inference framework. This merge allo
arXiv:2606.06842v1 Announce Type: new Abstract: Table reasoning remains challenging for large language models (LLMs), particularly in tasks that require multi-step inference over long and structured t
arXiv:2606.07400v1 Announce Type: new Abstract: Many scientific problems require inferring unobserved mechanistic latent states from indirect observations. While classical approaches, including expect
b9550 is a release of llama.cpp, a C/C++ implementation for LLM inference . The release represents an intermediate build in the llama.cpp development cycle, which releases frequently without tradition
llama.cpp is an open-source project that enables LLM inference with minimal setup and state-of-the-art performance on a wide range of hardware . Build b9541 is an intermediate release version of llama
B9544 is an intermediate build release of llama.cpp, an open-source C/C++ library for running large language model inference. Llama.cpp uses the GGUF model format and supports multiple hardware backen
b9519 is a release build identifier for llama.cpp, an open-source C/C++ project that enables LLM inference with minimal setup and state-of-the-art performance on a wide range of hardware . This specif
b9529 is a release tag for llama.cpp, a C/C++ implementation of LLM inference that enables running large language models locally on consumer hardware. This specific release represents a particular ver
B9530 is a release version of llama.cpp, a tool for LLM inference in C/C++ . It allows users to run large language models on everyday consumer hardware without expensive GPUs or cloud infrastructure .
arXiv:2606.06245v1 Announce Type: new Abstract: Vision-Language-Action (VLA) policies remain brittle in long-horizon and high-uncertainty control, where one-pass action decoding provides limited infer
arXiv:2601.02880v2 Announce Type: replace-cross Abstract: Every existing inference-time reasoning framework discards all failure context at problem boundaries, leaving a model solving problem 500 no w
arXiv:2606.06443v1 Announce Type: new Abstract: Large language models are increasingly used to simulate social media users and infer how individuals may respond to online discussions. However, it rema
arXiv:2606.06309v1 Announce Type: new Abstract: Video generation models based on Diffusion Transformers (DiTs) have achieved remarkable performance in video synthesis, yet they suffer from high infere
Release b9509 is a build version of llama.cpp, which provides LLM inference in C/C++ . As a specific build identifier in the llama.cpp project's release history, it likely contains bug fixes, performa
b9512 is a release build of llama.cpp, which provides LLM inference in C/C++ . The release uses a version numbering system with 'b' prefixes for intermediate builds, with newer releases building upon
llama.cpp is a C/C++ implementation designed to enable LLM inference with minimal setup and state-of-the-art performance on a wide range of hardware locally and in the cloud. Build b9515 is an interme
arXiv:2606.04432v1 Announce Type: new Abstract: Video diffusion transformers have achieved state-of-the-art visual quality, but their high inference cost remains a major bottleneck for real-time appli
arXiv:2606.04302v1 Announce Type: new Abstract: Key-value (KV) caching accelerates inference of large language models (LLMs) by reusing past computations for generated tokens. Its importance becomes e
arXiv:2601.10885v2 Announce Type: replace-cross Abstract: We propose a methodology to infer collision operators from phase space data of plasma dynamics. Our approach combines a differentiable kinetic
arXiv:2606.04730v1 Announce Type: new Abstract: With the advent of Large Language Models, single-task and token-based multi-task models have evolved into instruction-based systems that infer task and
arXiv:2606.04678v1 Announce Type: new Abstract: End-to-end ASR systems typically use fixed-depth acoustic encoders at inference, making it difficult to trade additional test-time computation for impro
arXiv:2606.02775v1 Announce Type: new Abstract: The KV-cache is the right memory for datacenters but the wrong memory for robots. Datacenter inference batches many short requests and resets them, amor
arXiv:2606.03304v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly evaluated in multilingual settings, yet their inference behavior in low-resource African languages remains
arXiv:2602.06960v3 Announce Type: replace-cross Abstract: Large reasoning models achieve strong performance by scaling inference-time chain-of-thought, but this paradigm suffers from quadratic cost, c
arXiv:2606.02963v1 Announce Type: new Abstract: Production inference increasingly targets a heterogeneous mix of accelerators. Agentic pipelines interleave reasoning, tool calls, and multi-agent coord
arXiv:2602.20217v2 Announce Type: replace-cross Abstract: Self-speculative decoding (SSD) accelerates LLM inference by skipping layers to create an efficient draft model, yet existing methods often re
arXiv:2606.02964v1 Announce Type: cross Abstract: Large Language Model (LLM) inference relies on key-value (KV) caches to avoid redundant attention computation. While approximate KV cache retention te
arXiv:2606.03305v1 Announce Type: new Abstract: Benchmark contamination, where evaluation examples appear in a model's training data, threatens the validity of LLM assessment. Statistical tools for de
arXiv:2606.03092v1 Announce Type: new Abstract: Inference-time scaling has emerged as a critical avenue for enhancing Large Language Models' performance, yet real-world deployment is constrained by st
arXiv:2606.03748v1 Announce Type: cross Abstract: Real-time vision demands models that are accurate, efficient, and simple to deploy across diverse hardware. The YOLO family has become widely deployed
arXiv:2606.02908v1 Announce Type: cross Abstract: Multi-turn user-facing agents must infer user intent from incomplete requests, collect missing information through dialogue and tools, and execute val
arXiv:2606.01104v1 Announce Type: new Abstract: VRR-QA evaluates whether video-language systems can infer spatial, temporal, viewpoint, depth, and visibility relations that are not always resolved by
arXiv:2601.21444v2 Announce Type: replace-cross Abstract: The efficiency of long-video inference remains a critical bottleneck, mainly due to the dense computation in the prefill stage of Large Multim
arXiv:2606.02256v1 Announce Type: new Abstract: Our work presents a method for ECG segmentation and arrhythmia detection using Tiny Machine Learning (TinyML) models for real-time, on-device inference
b9469 is an intermediate build release of llama.cpp, a C/C++ implementation that enables large language model inference on consumer hardware with minimal dependencies. Build releases like b9469 repres