All entries

context : do not re-reserve the scheduler when toggling causal_attn (#28751) context : do not re-reserve the scheduler when toggling causal_attn llama_context::set_causal_attn() marks the scheduler to

metal: support left and circular padding in GGML_OP_PAD (#29561) metal: support left and circular padding in GGML_OP_PAD Align Metal with CPU, CUDA and Vulkan: shift the source coordinates by the left

HIP: fix template skip for DKQ > 256 mfma kernels (#29559) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/50767985 macOS/iOS: macOS Apple Silicon (arm64) m

ggml-cpu: enable tiled flash attention for non-vector-multiple head dims on x86 (#29423) ggml-cpu: enable tiled flash attention for non-vector-multiple head dims on x86 add AVX2 support for masked loa

tests : refactor test-recurrent-state-rollback (#29426) tests : use llama_context_ptr in test-recurrent-state-rollback Replace raw llama_context pointers with llama_context_ptr and drop the manual lla

webgpu: Handle unaligned writes in ggml_backend_webgpu_buffer_set_tensor (#29471) Fix: Handle unaligned writes in ggml_backend_webgpu_buffer_set_tensor Clang formatting Website: https://llama.app Atte

common : fix HF cache paths on Windows (#29475) Supersedes #29158 Signed-off-by: Adrien Gallouët angt@huggingface.co Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/atte

batch: migrate speculative, mtmd and server to batch_ext (#29385) adapt common add common_batch wip wip: spec cont common_speculative_process server_batch to use common_batch rm some stale calls Assis

ggml-openvino: mark unaligned batch-stride views unsupported (#29603) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/50908876 macOS/iOS: macOS Apple Silico

models: pad on the left with ggml_pad_ext (#29567) models: pad on the left with ggml_pad_ext The Parakeet, LFM2-Audio, Granite Speech and Gemma 4 audio encoders build a left padding as a right pad fol

vulkan: include functional header (#29597) Fixes the compile error: no template named 'function' in namespace 'std' Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attes

server : support typed content (vision/audio/video) input for /v1/embeddings endpoint (#29556) server : support multimodal input for /v1/embeddings (Qwen3-VL-Embedding) Accept the OpenAI-style wrapped

mtmd: fix GCC 15 stringop-overflow in decode_embd_batch (#29607) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/50949667 macOS/iOS: macOS Apple Silicon (ar

arXiv:2512.06902v2 Announce Type: replace-cross Abstract: As software systems evolve, developers increasingly work across multiple programming languages and often face the need to migrate code from on

arXiv:2609.30751v1 Announce Type: new Abstract: Pairwise language-model judges can gather evidence through direct comparison, reasoning, or reference-based verification, but no single protocol is best

arXiv:2609.31074v1 Announce Type: new Abstract: Resource constraints make high-dimensional hyperspectral imaging challenging in autonomous perception, motivating the use of band selection methods. How

Banger paper from Microsoft Research. (bookmark it) They run 1K+ coding agents at once to test a scalable self-organized multi-agent harness. This is an interesting test because most multi-agent syste

arXiv:2609.31180v1 Announce Type: cross Abstract: Decoding and interpreting naturalistic speech from the brain increasingly relies on alignment to pretrained speech and language representation spaces.

arXiv:2609.31107v1 Announce Type: cross Abstract: We study Bayesian optimization (BO) through the lens of information geometry. Pulling back the Fisher information metric through the surrogate posteri

arXiv:2609.31157v1 Announce Type: new Abstract: Multi-dimensional time series, inherently tensorial, are common in practice. Despite great progress in time series anomaly detection, most existing meth

arXiv:2609.30445v1 Announce Type: cross Abstract: Optimizing fMRI scan duration and spatial resolution is critical for experimental design, yet traditional correlation-based approaches cannot quantify

arXiv:2609.31546v1 Announce Type: new Abstract: Electrocardiogram (ECG) foundation models typically tokenize the signal into fixed-length patches that ignore cardiac structure, so a patch may split a

arXiv:2609.31306v1 Announce Type: new Abstract: Tabular in-context learners such as TabPFN, Mitra, or ConTextTab rely on alternating row and column attention over 2D sequences of latent embeddings. Th

arXiv:2609.30508v1 Announce Type: new Abstract: The aim of this work is to examine the connectomes of Caenorhabditis elegans through a computational lens using the reservoir computing framework. Conne

arXiv:2609.30550v1 Announce Type: new Abstract: Benchy is a semantic language and execution engine for benchmarking AI programs. A benchmark is completely specified by a program, a scoring function, a

arXiv:2609.31301v1 Announce Type: cross Abstract: Large language model agents increasingly act on software systems, no longer merely generating text but also changing databases and online services. Ho

arXiv:2602.02043v2 Announce Type: replace-cross Abstract: Modern vision-language models struggle with basic compositional reasoning, failing to bind attributes to objects or relations to their referen

arXiv:2609.31470v1 Announce Type: cross Abstract: Outliers are essential for evaluating and improving the robustness of machine learning systems, especially when future distributions may differ signif

arXiv:2609.30738v1 Announce Type: new Abstract: KV cache eviction methods such as SnapKV and PyramidKV rank tokens solely by mean attention over a small observation window. We study a unified score, m

arXiv:2609.30747v1 Announce Type: cross Abstract: As artificial intelligence (AI) becomes embedded in everyday life, its environmental footprint, particularly water consumption remains largely invisib

arXiv:2609.30489v1 Announce Type: new Abstract: Large Language Models (LLMs) have demonstrated historic breakthroughs in general reasoning with early successes in biomedical science. However, existing

Hans Nichols / Axios: Blackstone, OpenAI, QTS, and SoftBank partner with key US unions to launch the American Infrastructure Alliance, aiming to create data center standards in 2027 — AI companies, pr

arXiv:2609.31093v1 Announce Type: new Abstract: Scaling language models to long contexts is limited by the quadratic cost of self-attention. Block sparse attention offers an efficient alternative, but

arXiv:2609.30297v1 Announce Type: cross Abstract: Conversational recommendation agents are a new paradigm for content discovery, enabling users to express complex intents through natural language (e.g

BREAKING: Florida becomes the first state to do what I have been recommending for weeks! NEWS: Florida is calling for a pause in the development of ChatGPT, citing my @axios scoop on top AI labs inves

arXiv:2609.30492v1 Announce Type: cross Abstract: Language models often produce homogeneous responses to open-ended tasks; such homogeneity can spawn groupthink-the convergence of ideas toward a singu

arXiv:2609.31165v1 Announce Type: cross Abstract: Speech-breath segmentation is a fundamental preprocessing step in respiratory audio analysis, enabling applications such as respiratory acoustic bioma

arXiv:2609.31363v1 Announce Type: new Abstract: Distributionally robust optimization (DRO) provides a principled framework for learning under distribution shift, but its practical use is hindered by t

arXiv:2609.31329v1 Announce Type: new Abstract: Morphology--control co-design jointly optimizes an agent's body structure and control policy as an integrated embodied system. However, existing methods

arXiv:2609.30341v1 Announce Type: new Abstract: Data Spaces enable sovereign and governed data sharing across organizational boundaries, but their integration with AI agents remains challenging due to

arXiv:2609.30291v1 Announce Type: new Abstract: The purpose of this article is to highlight the central role of autonomous systems as the ultimate stage in the development of AI, to explain the underl

Yesterday I shared our open-source Clash Royale simulator and its recurrent PPO agent here. A training loop is easier to understand when you can watch it, so we put a small interactive version online:

arXiv:2609.31222v1 Announce Type: new Abstract: Pocket-conditioned molecular diffusion updates ambient atom coordinates, but many lead-optimization objectives are expressed on quotient features such a

Deploy a text-to-speech model on Amazon SageMaker AI with the AWS vLLM-Omni Deep Learning Container and stream generated speech over a persistent bidirectional connection. This Part 1 tutorial deploys

Vultr is evaluating NVIDIA’s Agent Safety Platform as enterprise agents move from experimentation to production and receive real autonomy over internal systems. The platform addresses trust by securin

arXiv:2609.30951v1 Announce Type: new Abstract: Differentiable simulation provides analytic gradients of robot dynamics, enabling fast and sample-efficient first-order policy optimization. However, ob