b10186
ggml : Fix issue with kleidiai ci and stringop overflow warning (#26277) Signed-off-by: Jonathan Clohessy Jonathan.Clohessy@arm.com Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) ma
Knowledge catalogue
ggml : Fix issue with kleidiai ci and stringop overflow warning (#26277) Signed-off-by: Jonathan Clohessy Jonathan.Clohessy@arm.com Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) ma
metal: fix memory unwire if model is freed without any GPU operations (#26082) metal: fix memory leak if model is freed without any GPU operations metal: run dummy work only if residency sets are used
Remove custom cpu op from the M3 graph, express with stock ops (#26297) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS I
sync : ggml Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFramework Linux: Ubuntu x64 (CPU) Ubuntu ar
ggml-cuda: Allow transpose-free gemmv computation (#26171) When matrix's weights are shaped 1xK is leverage a transpose-free computation to use mat_mul_vec_f. Website: https://llama.app macOS/iOS: mac
tests : avoid building get-model.cpp many times (#26317) tests : remove get-model.cpp tests : fix quant type selection Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Sil
llama-context : sync pending async copies before clearing embd_seq (#25676) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED mac
Test support for alternative conv layout (#25617) add bool cwhn = true to conv_2d test cases add layout check at graph building time extend layout checks for conv2d.cu kernel in CPU back-end kernel ne
vulkan: Support quantized concat (#25684) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFramework Lin
server: support inp embd to generate next token (#26313) server: support embd for sampled token fix ~server_batch() Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silico
arXiv:2607.26829v1 Announce Type: new Abstract: Many high-performing volumetric segmentation models maintain dense multi-scale feature maps, leading to high activation memory and inference cost. We pr
Written by: Kelli Vanderlee, Stuart Carrera For years, the cybersecurity industry's understanding of software supply chain compromise has been anchored by a few watershed events, including Russian cyb
arXiv:2607.27023v1 Announce Type: new Abstract: Evaluating large generative models across benchmarks is time-consuming and computationally expensive. This drives the need for methods that can estimate
I recently shared the original MindControl PoC (and on github) - sampler-level guided reasoning budgets for llama.cpp, nudging the model with self-aware statements about its own thinking budget instea
arXiv:2607.26581v1 Announce Type: new Abstract: Convolutional long short-term memory networks (ConvLSTMs) are widely used for precipitation forecasting, but most evidence for their performance comes f
Back to school means balancing assignments, deadlines and downtime. GeForce NOW makes it easy to have it all. With cloud gaming, everyday laptops used for class can also become GeForce RTX-powered gam
arXiv:2607.26247v1 Announce Type: new Abstract: Low-rank adaptation (LoRA) fine-tunes large pretrained models at a fraction of the cost of full fine-tuning, but its performance depends strongly on how
arXiv:2607.26232v1 Announce Type: new Abstract: Background manipulation is a practical but under-specified image-forensics setting: the manipulated evidence can sit outside the salient foreground obje
Ethan Mollick highlights that large, currently under‑explored benchmarks (e.g., ARC‑AGI, GDPval, METR long horizons, ASI cyber tasks) are growing in complexity, yet they increasingly lack systematic h
arXiv:2607.26914v1 Announce Type: new Abstract: Biomedical laboratory robots must navigate to instruments before performing experimental procedures. Existing embodied navigation platforms are designed
arXiv:2606.19651v2 Announce Type: replace-cross Abstract: Three-dimensional (3D) brain MRI is central to clinical neurology and neuro-oncology, where generative models could augment under-represented
arXiv:2607.26955v1 Announce Type: cross Abstract: Minimax-optimal rates for multivariate distribution estimation are known to suffer from the curse of dimensionality. We propose a sparse Bayesian netw
arXiv:2511.07210v3 Announce Type: replace Abstract: Clean-image backdoor attacks, which use only label manipulation in training datasets to compromise deep neural networks, pose a significant threat t
arXiv:2607.26828v1 Announce Type: new Abstract: Large language models increasingly support scientific and algorithmic discovery through inference-time search over evaluated candidates. Existing adapti
arXiv:2603.24800v2 Announce Type: replace Abstract: In this paper, we uncover the hidden potential of Diffusion Transformers (DiTs) to significantly enhance generative tasks. Through an in-depth analy
arXiv:2607.26752v1 Announce Type: new Abstract: Medical world models aim to learn a latent state of patient or organ physiology and a transition function that forecasts how that state evolves under in
arXiv:2607.27191v1 Announce Type: cross Abstract: Forecasts of explosive AI progress hinge on AI agents automating AI research. But evidence on whether agents can carry out open-ended AI research is t
Can AI agents conduct open-ended AI research? Most evaluations of agents conducting AI research focus on narrow, verifiable tasks. But AI research is often open ended. Researchers pick hypotheses, dec
Osmosis_AI claims that an open‑source model can rival a foundation model by leveraging reinforcement learning techniques. To demonstrate this, they will use the Y Combinator‑dedicated GPU cluster on T
arXiv:2607.26729v1 Announce Type: new Abstract: Deep learning-based watermarking has shown strong robustness against non-geometric distortions, yet its performance under geometric transformations rema
AI-native services are shifting the value of artificial intelligence beyond individual productivity and into stronger project-team outcomes. Professional services firms face pressure to deliver more q
arXiv:2607.26452v1 Announce Type: cross Abstract: World models must learn the joint dynamics of states, actions, events, and observations, yet existing video, robotics, and simulation datasets usually
arXiv:2505.06945v5 Announce Type: replace Abstract: Multimodal data modeling has emerged as a powerful approach in clinical research, enabling the integration of diverse data types such as imaging, ge
arXiv:2607.26458v1 Announce Type: cross Abstract: Domain generalization (DG) aims to learn from multiple source domains and generalize to unseen target domains. Most DG methods pursue invariance: they
arXiv:2607.26221v1 Announce Type: new Abstract: With the advancement of AI technologies, Generative AI (GenAI) and human written text have become nearly indistinguishable. Additionally, the global sta
arXiv:2607.26789v1 Announce Type: new Abstract: Vision-language-action (VLA) policies commonly execute long-horizon mobile manipulation through open-loop action chunks, issuing multiple actions withou
arXiv:2106.16038v3 Announce Type: replace Abstract: Recent pretraining models in Chinese neglect two important aspects specific to the Chinese language: glyph and pinyin, which carry significant synta
arXiv:2607.26200v1 Announce Type: new Abstract: Content-moderation classifiers are usually evaluated in isolation, but deployment requires choosing where to intervene and what follows a flag. We evalu
arXiv:2607.26910v1 Announce Type: new Abstract: Automatically generating cinematically expressive camera trajectories through 3D scenes from natural language descriptions is a challenging task of high
arXiv:2607.26529v1 Announce Type: new Abstract: Cinematic video generation is challenging for text-to-video diffusion models due to concurrent requirements on multi-shot generation, fine-grained contr
arXiv:2607.26580v1 Announce Type: new Abstract: With the increase in the number of cases related to respiratory diseases, there is an urgent need to detect them early and diagnose them accurately. Con
arXiv:2603.21809v2 Announce Type: replace Abstract: Retinal fundus imaging enables low-cost and scalable hypertension (HTN) screening, but HTN-related retinal cues are subtle, yielding high-variance p
arXiv:2607.26369v1 Announce Type: new Abstract: Rotary Position Embedding (RoPE) has been widely adopted in transformer-based large language models. However, its log-linear frequency schedule, origina
arXiv:2607.26470v1 Announce Type: new Abstract: Multi-turn information-seeking conversations require both multi-hop reasoning and long-range dependency tracking across turns. However, existing RAG sys
arXiv:2607.27054v1 Announce Type: new Abstract: Knowledge distillation (KD) enables a compact student model to learn from a powerful teacher and has become an effective paradigm for model compression.
arXiv:2607.26179v1 Announce Type: cross Abstract: LLMs are widely regarded as alien intelligences, systems whose cognitive operations are fundamentally unlike our own. Apparent similarities to human c
Cohere has joined @NVIDIA alongside industry leaders in founding the Open Secure AI Alliance. Everybody should have the capability to keep their infrastructure secure. Everybody deserves access to mod
arXiv:2607.26509v1 Announce Type: new Abstract: Deep off-policy reinforcement learning algorithms for continuous control typically rely on neural value function approximation to guide policy improveme
ComfyUI Face Swap Tutorial: Fast, Clean Results VFX artist Doug Hogan walks through a fully automated face swap workflow built inside ComfyUI - combining Florence 2, SAM2, and WAN Video into a single
arXiv:2607.26276v1 Announce Type: new Abstract: Background: Early prediction of distant metastasis (DM) risk in head and neck cancer (HNC) can enable timely interventions that may improve treatment ou
arXiv:2607.26481v1 Announce Type: new Abstract: Detecting when the statistical behavior of an engineered system changes, and identifying which component is responsible, are core problems in the monito
arXiv:2607.26887v1 Announce Type: cross Abstract: Many high-resolution imaging systems face the same fundamental question: when have enough measurements been collected to reconstruct an image accurate
Consistent with what I found with Qwen3.6 a while back: Claude Code uses 2-3x as many tokens than (many) other harnesses at similar success rate. - Unoptimized? - Buggy? - Deliberate (coz that helps i
arXiv:2607.26654v1 Announce Type: new Abstract: Post-training alignment is often shallow, eroding under fine-tuning. Whether midtraining interventions, cleanly isolated from post-training, can produce
arXiv:2607.26579v1 Announce Type: cross Abstract: World models offer a promising route toward robot planning by enabling agents to imagine and verify the consequences of actions before execution. Howe
arXiv:2512.07076v4 Announce Type: replace Abstract: Camouflage relies heavily on context, but current metrics used in camouflaged object segmentation ignore contextual cues. We identify two major draw
arXiv:2607.26640v1 Announce Type: new Abstract: Current human evaluation of machine translation typically assesses single outputs in isolation, a paradigm that suffers from high annotator noise and co
arXiv:2607.27085v1 Announce Type: new Abstract: This paper presents the North Carolina Transitional Autonomous Vehicle Lane-Changing (NC-tALC) dataset and uses it to characterize mandatory lane-changi
arXiv:2607.26901v1 Announce Type: cross Abstract: Convex Collision-Free Regions (CCFR) is a collision handling method that explicitly represents local convex feasible regions to enforce non-penetratio
arXiv:2607.27143v1 Announce Type: new Abstract: High-stakes decision systems in credit scoring, fraud detection, healthcare, and industrial safety require reliable uncertainty quantification under sev