b11491
sycl: remove duplicate block-size defines from op headers (#29507) All were duplicates of the values in ggml/src/ggml-sycl/presets.hpp Website: https://llama.app Attestations: https://github.com/ggml-
Knowledge catalogue
sycl: remove duplicate block-size defines from op headers (#29507) All were duplicates of the values in ggml/src/ggml-sycl/presets.hpp Website: https://llama.app Attestations: https://github.com/ggml-
sycl: add grouped MoE XMX GEMM (#29245) Co-authored-by: cwriter cwriter@localhost Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/53864714 macOS/iOS: macOS
sycl: fuse the delta-net alpha gate (add + unary + mul) (#29687) sycl: fuse the delta-net alpha gate (add + unary + mul) tests: cover the fused add + unary + mul chain sycl: give the fused alpha gate
CUDA: fix norm family kernels when ne[2]/ne[3] exceed grid dim limits (#28175) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/53919465 macOS/iOS: macOS App
cuda : Use byte strides for roll to allow non-contiguous ROLL operations (#29547) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/53926988 macOS/iOS: macOS
hex-mmadd: do not assume aligned read/write when bias-add is fused (#30133) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/53932639 macOS/iOS: macOS Apple
sycl: FWHT optimizations (#29605) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/53938516 macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64
vendor : update cpp-httplib to 0.60.1 (#30134) Signed-off-by: Adrien Gallouët angt@huggingface.co Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/53949333 m
vulkan : fix TOP_K for +inf/NaN inputs and k = 1 on negative values (#30107) The bucket search in topk_nary_search.comp started from the range [0, 0xFF800000), which ends just below the ordered-uint m
llama: support MoE cache over multiple GPUs (#30112) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/53988921 macOS/iOS: macOS Apple Silicon (arm64) macOS A
CUDA: fix CCCL version guard breaking on major version rollover (#29453) CUDA: fix CCCL version guard breaking on major version rollover The guard compared the major and minor components independently
CUDA : looped PAD kernel for more than 65535 rows or slices (#30147) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/54006924 macOS/iOS: macOS Apple Silicon
CUDA: fix MMQ out-of-bounds reads (#29953) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/54029251 macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silic
model : fix DFlash output head sharing (#30111) llama : fix DFlash output head sharing Assisted-by: Codex dflash : read tied output weights from GGUF metadata Assisted-by: Codex llama : share tied wor
CUDA: improve top-k algorithm selection (#28713) CUDA: radix top-k for large row counts Replaces CUB's per-row DeviceTopKKernel with a grid-over-rows radix select, gated on GGML_CUDA_TOPK_RADIX_MIN_RO
Musa FWHT fix (#30167) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/54083178 macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI
arXiv:2610.09819v1 Announce Type: cross Abstract: Acoustic foundation models (AFMs) have democratized acoustic applications, enabling powerful models for tasks ranging from speech recognition to speak
arXiv:2610.10160v1 Announce Type: new Abstract: Mishandled checked baggage remains a recurrent issue in airport operations, and current recovery workflows still largely rely on tag-based tracking, whi
arXiv:2610.09464v1 Announce Type: new Abstract: Political discourse often uses rhetorical and persuasive language to frame narratives, influence public opinion, and mobilize audiences. While Bangla na
arXiv:2505.06592v2 Announce Type: replace Abstract: In this paper, we propose batch augmentation with unimodal fine-tuning for multimodal learning. We start with pre-trained unimodal models. We fine-t
arXiv:2610.09026v1 Announce Type: cross Abstract: We present BEACON-SP, an ontology-grounded Graph Retrieval-Augmented Generation (GraphRAG) framework for clinician-facing decision support in behavior
arXiv:2610.09052v1 Announce Type: new Abstract: Continuous cardiac monitoring outside clinical settings requires signals that are both informative and practical to collect during daily life. Electroca
arXiv:2610.09207v1 Announce Type: new Abstract: Belief-space planners with separately designed or off-the-shelf estimators may have access to state-relevant information the estimator does not observe.
arXiv:2610.10198v1 Announce Type: new Abstract: Behavior Foundation Models (BFMs) are emerging as a paradigm for translating human intentions into executable humanoid behaviors. As these models evolve
arXiv:2610.09340v1 Announce Type: new Abstract: Benign overfitting is extensively studied when learning from a single high-dimensional input, but its behavior under heterogeneous input fusion remains
arXiv:2610.10488v1 Announce Type: cross Abstract: We study the best arm identification problem in a stochastic environment with a novel form of adversarial perturbations, which we coin Shifting Means.
There are way too many forks to keep track of, so I've gotten lost. As far as I can tell, Radiance VLLM is best for models that fit in GPUs while some form of llama.cpp is probably best for MOE RAM-sp
I'm developing a benchmark for a low resource language and I don't want it to be leaked and used for training when it is being used to get predictions. For locally run models it shouldn't be a problem
arXiv:2610.10163v1 Announce Type: new Abstract: Linking people's appearance and actions to character identities is essential for understanding video narratives. We present a framework for identity-awa
arXiv:2610.08809v1 Announce Type: new Abstract: Depression severity among patients with chronic or acute medical conditions is influenced by a complex interaction of baseline psychological state, demo
arXiv:2610.09031v1 Announce Type: new Abstract: Medical imaging models often operate as black boxes, limiting interpretability and systematic debugging. We introduce an easy-to-use, plug-and-play fram
arXiv:2610.09726v1 Announce Type: new Abstract: Estimating remaining shelf life (RSL) from images could provide affordable decision support for perishable produce, but evaluation protocols can substan
arXiv:2610.09800v1 Announce Type: new Abstract: Surgical video generation holds substantial potential for surgical education, simulation, and data augmentation, yet generating surgical videos with rea
arXiv:2610.09244v1 Announce Type: cross Abstract: Recent advances in mean-field games and its multi-population variants enable large-scale heterogeneous multi-agent systems to be modeled through repre
arXiv:2610.10179v1 Announce Type: new Abstract: Search agents enable Large Language Models (LLMs) to iteratively retrieve and use information for complex multi-hop questions. Reinforcement Learning wi
arXiv:2610.09763v1 Announce Type: new Abstract: Offline reinforcement learning enables reward-driven policy improvement from fixed datasets without requiring online exploration, making it particularly
arXiv:2610.09170v1 Announce Type: new Abstract: Autoregressive action-token policies such as vision-language-action models require action tokenizers to translate discrete token sequences into precise
arXiv:2610.10000v1 Announce Type: new Abstract: Adversarial attacks on bandits aim to mislead a learner toward a target arm while keeping the attack cost small. Existing attacks typically achieve this
arXiv:2610.08842v1 Announce Type: new Abstract: Identifying suicide risk from social networking services (SNS) posts is important for detecting suicide-related signals in online environments. However,
arXiv:2610.08840v1 Announce Type: new Abstract: Large language models (LLMs) often abandon a correct answer, or endorse a user's position, once the user pushes back. This behavior, called sycophancy,
arXiv:2603.13357v2 Announce Type: replace Abstract: Bi-CamoDiffusion is introduced, an evolution of the CamoDiffusion framework for camouflaged object detection. It integrates edge priors into early-s
Big new paper nobody is talking about ‼️ 🌎 Robot world models now have scaling laws. Meta trained an 8B-parameter JEPA on 15,000 hours of robot video to prove it. RoboJEPA (FAIR at Meta + Mila) imagin
arXiv:2412.00112v5 Announce Type: replace Abstract: Generating natural and expressive human motions from textual descriptions is challenging due to the complexity of coordinating full-body dynamics an
arXiv:2610.09193v1 Announce Type: cross Abstract: MemoryAgentBench's Conflict Resolution split is read as measuring 'selective forgetting'. We execute the benchmark's own rule - the newest statement a
arXiv:2610.10383v1 Announce Type: new Abstract: Boosting converts weak hypotheses with a small edge over random guessing into highly accurate predictors, but the expressive power of the resulting clas
arXiv:2610.09967v1 Announce Type: new Abstract: Nano unmanned aerial vehicles (nano-UAVs) can navigate confined spaces that larger robots cannot, but their payload capacity severely limits the sensors
arXiv:2610.09804v1 Announce Type: new Abstract: Reinforcement learning is now central to eliciting reasoning in large language models, while in the popular algorithm Group Relative Policy Optimization
arXiv:2610.09712v1 Announce Type: cross Abstract: We develop a continuous-time deterministic policy gradient framework for reinforcement learning with reflected state dynamics, where the state process
arXiv:2610.09467v1 Announce Type: cross Abstract: Contextual biasing supplies an ASR system with a list of expected words at inference time, but existing methods rely on word boundaries that Japanese
arXiv:2610.08815v1 Announce Type: new Abstract: Agentic AI-enabled automation cannot be safely deployed in high-stakes environments on probabilistic reasoning alone. A recurring risk is epistemic drif
arXiv:2610.09109v1 Announce Type: new Abstract: Many organizations fine-tune publicly available pretrained Automatic Speech Recognition (ASR) models and deploy them in black-box settings, assuming lim
BREAKING: President Trump on Elon Musk today: “First, we honor an industrial titan, a brilliant engineer, and one of the greatest technology founders to ever live. His name is Elon Musk. Quite honestl
arXiv:2610.09733v1 Announce Type: new Abstract: Multilingual LLMs answer the same multi-hop reasoning question across languages, but we lack a mechanistic account of whether they share an internal cir
arXiv:2610.09873v1 Announce Type: new Abstract: Binary Neural Networks (BNNs) enable efficient deep learning deployment on resource constrained devices with weights and activations compressed to one b
arXiv:2610.10194v1 Announce Type: cross Abstract: Switching stochastic differential equations (SSDEs) describe continuous-time dynamics whose parameters switch according to a latent regime process tha
Industrial AI is entering a new phase. After decades of predictive analytics and other specialized applications, advances in foundation models, physical AI, and agentic AI are making it possible to au
Vultr demonstrated its composable cloud platform at the Agent Arena Hackathon in San Francisco by partnering with Cerebral Valley to build production‑ready enterprise agentic AI systems using Serverle
The NVIDIA KGMON team secured second place in the KDD Cup 2026 Data Agents competition by building a constrained harness around a small fixed LLM, unifying heterogeneous data into an SQLite database w
Building tonight? Join us at Codex Build Night where our AI Creative Technologist Guy Bar Hava will be demoing alongside @comfyui and @OpenAI to show how to build with LTX-2.5 open weights. Sign up he
arXiv:2610.10058v1 Announce Type: new Abstract: Repeated queries over shared documents incur redundant encoding, while caching model states introduces persistent storage costs. Building on CoMem's int