b11155
server,common : fix the GCC 12 stringop-overread false positive (again) (#29325) Signed-off-by: Adrien Gallouët angt@huggingface.co Website: https://llama.app Attestations: https://github.com/ggml-org
Knowledge catalogue
server,common : fix the GCC 12 stringop-overread false positive (again) (#29325) Signed-off-by: Adrien Gallouët angt@huggingface.co Website: https://llama.app Attestations: https://github.com/ggml-org
model : add Ling 3.0 VL support (#29151) model : fold Ling 3.0 VL into the BailingMoeV3 architecture Assisted-by: Scout model : keep shared NORM rope list intact when gating bailingmoe3 on mrope secti
cuda : add conv3d with implicit GEMM (#29137) cuda : add conv3d with implicit GEMM cuda : refine conv3d implicit GEMM and handle empty kernels Website: https://llama.app Attestations: https://github.c
vulkan: tune KHR cooperative matrix support for Adreno GPUs (#29328) Enable coopmat support for Vulkan backend Fixed the mul_mat_s Removed the debug statement Website: https://llama.app Attestations:
vulkan: handle misalignment in conv_2d and conv_3d (#29365) vulkan: handle misalignment in conv_2d and conv_3d fix test-backend-ops print Website: https://llama.app Attestations: https://github.com/gg
vulkan: int8 coopmat1 matmul implementation for AMD RDNA3 and RDNA4 (#27952) vulkan: add int8 coopmat quantized matmul shader apply scales inline use scalar sums probe and directly access coopmat valu
llama: add llama_batch_ext (#24669) (wip) add llama_batch_ext wip updated design updated impl change signature unused var demo common_prompt_batch_decode fix pos tmp disable test-batch-alloc fix compa
test: flush status (#28352) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/49978694 macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, Klei
cuda : add F16 kernel support for CONV_2D_DW (#29064) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/49985945 macOS/iOS: macOS Apple Silicon (arm64) macOS
hexagon: support I32 CPY and CONT (#29379) Assisted-by: OpenCode Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/49994729 macOS/iOS: macOS Apple Silicon (ar
hexagon: dynamic quantizer improvements (#29395) hexagon: fix accuracy issue in Q8_0 N=1 MUL_MAT hex-quant: fix register spills hex-mm: use dma for all dyn.quant paths Co-authored-by: Aparna M P aparm
llama-grammar: fix numeric truncation for token_id parsing (#29382) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/50007794 macOS/iOS: macOS Apple Silicon
hexagon: handle multi-sequence in concat_2d (#29344) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/50014220 macOS/iOS: macOS Apple Silicon (arm64) macOS A
sync : ggml (#29396) ggml : bump version to 0.25.2 (ggml/1642) ggml : fix ubsan error in ggml_graph_nbytes (ggml/1644) ggml : bump version to 0.25.3 (ggml/1645) sync : ggml Website: https://llama.app
metal : optimize sparse FA + clean-up (#29377) metal : cache sparse FA indices in shared memory Assisted-by: pi:llama.cpp/DeepSeek-V4-Flash-Vision-Exp metal : simplify shared memory size calculation A
benched 5.5 is IN-SANE. It almost broke our benchmark. I thought it was a bug. Claude Opus 5.5 is the new #1 on our writing benchmark, and it is not close at all. 2631 Elo. Second one, Fable, is at 23
arXiv:2609.27208v1 Announce Type: new Abstract: Spatial transcriptomics (ST) measures gene expression in tissue context, but dense capture grids can be costly and may repeatedly sample morphologically
arXiv:2609.28283v1 Announce Type: new Abstract: Several foundation models dedicated to hyperspectral images have recently been made available. These models are trained on large unlabeled datasets and
arXiv:2607.22115v2 Announce Type: replace-cross Abstract: Given a database S and a natural language question Q, text-to-SQL systems aim to generate an SQL query that correctly answers Q when executed
arXiv:2609.27457v1 Announce Type: new Abstract: Vision-language models (VLMs) are often reported to outperform task-specific vision backbones for unmanned aerial vehicle (UAV) power-line defect assess
arXiv:2609.27176v1 Announce Type: new Abstract: Evidence that evaluation material entered training does not reveal how much it affected evaluation. This distinction leaves a contaminated benchmark sco
arXiv:2609.28245v1 Announce Type: cross Abstract: Large language models (LLMs) have shown strong performance in creative text generation, yet their ability to produce culturally grounded and stylistic
arXiv:2609.27299v1 Announce Type: cross Abstract: Information systems (IS) researchers increasingly use quasi-experimental methods such as difference-in-differences (DiD) and instrumental variables (I
arXiv:2609.27615v1 Announce Type: new Abstract: In multimodal emotion recognition (MER), human affective states are inferred by integrating complementary cues from multiple modalities. In audio-text M
arXiv:2609.27932v1 Announce Type: new Abstract: Ganian et al. (ICLR 2026) proved that quantized neural network training is fixed-parameter tractable when parameterized jointly by architecture treewidt
arXiv:2609.27275v1 Announce Type: new Abstract: Most autonomous-driving datasets record only the action executed by a behavior policy and the single future that followed, providing limited supervision
Mina Kimes posted that, despite facing backlash ('got cancelled'), she remains convinced that X (formerly Twitter) has returned to prominence. She characterizes the platform as the primary venue for i
arXiv:2609.27607v1 Announce Type: cross Abstract: An AI-generated radiology report can resemble a physician's report while omitting an abnormality, adding an unsupported finding, or reversing its pres
arXiv:2609.28090v1 Announce Type: cross Abstract: Backtest auditing is a calibration problem: high flaw recall is not useful when the model falsely flags matched clean strategies. We build a 96-item p
arXiv:2609.28449v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used in coding tasks, but their ability to reason about code execution remains unclear. Existing reposit
arXiv:2609.27262v1 Announce Type: new Abstract: Production customer-support systems often require LLMs to support multiple skills, such as intent classification, question answering, summarization, or
arXiv:2609.27327v1 Announce Type: new Abstract: Video provides a rich record of human behavior, interaction, and situated contexts, offering important evidence for understanding people and conducting
arXiv:2603.13768v2 Announce Type: replace-cross Abstract: Despite the strong performance of large audio language models (LALMs) in various tasks, exactly how and where they integrate acoustic features
arXiv:2609.27273v1 Announce Type: new Abstract: Computer-use agents (CUAs) increasingly act on behalf of users online. What happens when the environments they operate in have incentives that do not al
arXiv:2609.27067v1 Announce Type: cross Abstract: Large language model (LLM)-based agents use Electronic Design Automation (EDA) tools to generate and revise register-transfer-level (RTL) designs unde
arXiv:2609.27857v1 Announce Type: cross Abstract: Large language model (LLM) agents often process external tool responses as they arrive, making response timing part of the decision process. We introd
arXiv:2505.10083v2 Announce Type: replace Abstract: Conventional forecasting methods are trained end-to-end on unimodal time series, which limits their ability to exploit textual information and under
arXiv:2609.26945v1 Announce Type: new Abstract: Judicial reasoning remains challenging for large language models (LLMs) to analyze. This paper contributes a sentence-level benchmark for evaluating the
arXiv:2609.26913v1 Announce Type: cross Abstract: No single Large Language Model (LLM) is uniformly reliable across queries, motivating multi-model inference systems that either route among models or
arXiv:2609.26860v1 Announce Type: cross Abstract: Web applications are increasingly targeted by cyberattacks that exploit HTTP requests to evade security mechanisms. Traditional web application firewa
System-wide Dictation on Apple devices runs entirely on-device, and the speech it transcribes reaches the foundation model through a tokenizer: an encoder that maps short windows of waveform onto the
arXiv:2609.28290v1 Announce Type: new Abstract: Meaning identity (whether two sentences say the same thing after wording changes) is treated in retrieval and RAG as a geometric fact about independentl
arXiv:2609.27976v1 Announce Type: cross Abstract: Conformal Bayes combines Bayesian posterior predictive scores with conformal calibration, but under continuous label shift both the score and calibrat
A warped Manhattan is waiting in the cloud this week. Remedy Entertainment’s CONTROL Resonant brings Dylan Faden’s extraordinary abilities and a paranatural crisis to GeForce NOW at launch. With the r
arXiv:2412.02575v3 Announce Type: replace Abstract: Driven by practical demands in land resource monitoring and national defense security, this paper introduces the Remote Sensing Copy-Move Question A
arXiv:2609.26905v1 Announce Type: cross Abstract: Stacking heterogeneous vision backbones (CNNs, ViTs, and hybrids) is the de facto recipe for accuracy, calibration, and robustness, yet two coupled pa
arXiv:2609.27314v1 Announce Type: new Abstract: Comparing current and past observations helps robots understand scene changes and select subsequent actions during manipulation. However, comparing visu
arXiv:2609.27165v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used to measure public value orientations from long social media posts, yet such posts often mix backgro
arXiv:2609.27421v1 Announce Type: new Abstract: Multi-constraint instruction following requires a model to respond to a query under many simultaneously active constraints. Even strong instruction-tune
arXiv:2609.27034v1 Announce Type: cross Abstract: We study prediction in new environments when training data contain rare, large shifts. Anchor regression penalizes the average of the squared mean res
Decision models should do more than pick a label. To truly act, they need to extract evidence, understand relationships, produce structured records, and keep related decisions consistent. And they sho
arXiv:2609.27900v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed in multi-agent systems where a principal agent decomposes tasks and delegates them to subordinate
arXiv:2609.27470v1 Announce Type: cross Abstract: Recent video-language models increasingly adopt hybrid architectures that interleave linear and full attention layers for efficient long-context proce
The article introduces the Unity Gateway Command Line Interface (CLI) as a tool for deploying and managing coding agents at large scale. It outlines how users can automate agent deployment, monitor pe
arXiv:2609.27930v1 Announce Type: cross Abstract: We propose a Bayesian nonparametric mixture of regression trees with a Dirichlet process prior over tree-parameter pairs, enabling data-driven selecti
arXiv:2609.27234v1 Announce Type: new Abstract: AI virtual cells aim to predict cellular responses to specified interventions, yet held-out predictive performance alone does not establish use of the s
arXiv:2609.28087v1 Announce Type: new Abstract: The integration of model-based and data-driven paradigms provides a powerful framework for fault diagnosis by combining the interpretability of analytic
arXiv:2609.28231v1 Announce Type: cross Abstract: Pathology foundation models (PFMs) have transformed computational pathology through powerful representation learning from histopathological images. PF
Just watched a video from three years ago where Matt Berman tested Bard (yes, remember Bard?) and most of the tests were like summarization or logic tests. If it ever came to coding, it was the snake
arXiv:2609.27069v1 Announce Type: cross Abstract: Graph neural networks dominate recent work on microservice root-cause analysis, yet recent results question whether the graph contributes. Those resul