b10307
sycl: fix UE4M3 parsing (#25608) The NVFP4 quantization format stores a scaling factor for every group of 16 weights, packed into a single UE4M3 byte. The SYCL GPU code was converting these scale valu
Knowledge catalogue
sycl: fix UE4M3 parsing (#25608) The NVFP4 quantization format stores a scaling factor for every group of 16 weights, packed into a single UE4M3 byte. The SYCL GPU code was converting these scale valu
Mitigate crashing issue on Windows MSYS2 UCRT64 environment (GCC 16.1.0) (#26555) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABL
ggml : add aarch64 HWCAP fallbacks and fix fp16 variant detection (#25554) ggml : add fallback definitions for missing aarch64 HWCAP bits ggml : require HWCAP_ASIMDHP for the aarch64 fp16 cpu variants
mtmd: stop feeding the text stream again during Qwen3-TTS generation (#26706) The reference implementation has two mutually exclusive prompt layouts. In non streaming mode the prefill carries the whol
server: (router) do not evict busy models (#26567) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFram
server: (router) add LRU scheduler (#26572) add lru_sched handle coalescing (req leaves waiting queue) add tests fix stream case address review comments Website: https://llama.app macOS/iOS: macOS App
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
mtmd: fix longest_edge ignoring min/max pixels (#26638) mtmd: fix longest_edge ignoring min/max pixels nits Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64
metal : fix NORM/RMS_NORM for row lengths that leave a partial simdgroup (#26708) ggml_metal_op_norm sized the threadgroup with nth = std::min(nth, args.ne00_t), which can leave nth not a multiple of
sycl: coalesce the ssm_conv window loads (#26612) test-backend-ops perf -o SSM_CONV on an Arc Pro B70, interleaved A/B against master, 6 reps, us/run: ne_a=[515,3328,1,1] ne_b=[4,3328,1,1] n_t=512 97.
tts: account for the vocoder pass in the timings line (#26733) get_output runs the waveform work the pipeline defers to it, from a single trailing window to a full pass depending on the model. Measuri
arXiv:2608.06291v1 Announce Type: cross Abstract: We accelerate a family of algorithms for neural network quantization whose geometry is informed by any Kronecker-factored approximation of the Hessian
arXiv:2608.05926v1 Announce Type: cross Abstract: Edge inference is a promising paradigm to provide large language model (LLM) inference services in next-generation mobile networks. LLM inference main
arXiv:2608.06062v1 Announce Type: new Abstract: Bar charts are commonly used in data visualization, and while they are easily understood by humans, it is non-trivial to extract the underlying data com
On August 7, 2026 Ethan Mollick tweeted that “every remaining good AI benchmark score has an implied asterisk next to it which reads: * could be significantly higher with a better harness.” The commen
arXiv:2608.05815v1 Announce Type: new Abstract: Few-shot learning has emerged as a promising approach for anatomical segmentation when labelled data are scarce. However, different few-shot learning al
arXiv:2608.05642v1 Announce Type: new Abstract: This paper proposes the Bayesian Expected Uncertainty Reduction (B-EUR) model, which formalizes the value of trying a candidate design action as its exp
arXiv:2608.05548v1 Announce Type: cross Abstract: Modern vehicles rely on the Controller Area Network (CAN) bus, whose design prioritizes low cost and real-time performance but provides no message aut
arXiv:2608.06312v1 Announce Type: new Abstract: Large language models (LLMs) increasingly support complex professional tasks, yet their capabilities in rule-intensive document review remain insufficie
arXiv:2608.06329v1 Announce Type: cross Abstract: Task-oriented conversational agents are evaluated using curated or automatically generated benchmarks, yet benchmark quality is rarely assessed. Poor
arXiv:2608.06164v1 Announce Type: new Abstract: Reconstructing objects with mechanical properties from video observations enables physically consistent dynamic prediction, benefiting robotics planning
arXiv:2607.16465v2 Announce Type: replace Abstract: Edmund C. Berkeley is usually remembered as a mediator between symbolic logic and early computing, yet that standard description understates the sco
arXiv:2608.05880v1 Announce Type: cross Abstract: Interpreting clustering outcomes remains a fundamental challenge in data analysis, particularly in domains such as healthcare where meaningful pattern
arXiv:2608.05999v1 Announce Type: new Abstract: Vision-language-action (VLA) models have demonstrated remarkable capabilities in robotic manipulation by leveraging pretrained vision-language models. H
arXiv:2608.05592v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have achieved strong progress in video understanding, yet it remains challenging because the token limitation m
arXiv:2608.05250v1 Announce Type: new Abstract: Multi-task supervised fine-tuning (SFT) often casts a heterogeneous data mixture as a single optimization problem, even though different tasks may reach
arXiv:2608.05171v1 Announce Type: cross Abstract: Generative AI (GAI) creates new opportunities for collaborative problem-solving (CPS), yet its role in shaping student interaction remains unclear. To
arXiv:2608.06206v1 Announce Type: cross Abstract: Conformal prediction endows arbitrary black-box predictors with finite-sample, distribution-free marginal coverage, yet marginal validity can hide sev
Large Language Models (LLMs) have achieved state-of-the-art performance on a broad range of Natural Language Processing (NLP) tasks, including document processing and code generation. Autoregressive L
arXiv:2608.05757v1 Announce Type: new Abstract: Whole-slide image (WSI) reasoning requires an agent to sequentially acquire visual evidence before answering a diagnostic question. Existing training-fr
arXiv:2608.05253v1 Announce Type: new Abstract: Quantized orthogonal fine-tuning (qoft) enables parameter-efficient adaptation of low-bit language models by learning structured activation rotations be
arXiv:2608.05155v1 Announce Type: cross Abstract: Traditional sentiment analysis (SA) models, while effective for polarity classification, provide limited insight into the rhetorical, ideological, and
arXiv:2608.06111v1 Announce Type: cross Abstract: Positional embeddings (PE) in Transformers encode token distance and order but are largely agnostic to extit{syntactic structure}. We introduce extbf{
arXiv:2608.06305v1 Announce Type: new Abstract: Retrieval-augmented generation over long documents is dominated by one design: chunk the text, embed the chunks, and surface the top-k nearest neighbour
arXiv:2606.16891v2 Announce Type: replace-cross Abstract: Federated Learning is rapidly evolving beyond the exchange of traditional model weights and gradients, yet existing definitions fail to captur
arXiv:2608.06300v1 Announce Type: new Abstract: Automatic speaking assessment systems are increasingly deployed in high-stakes settings to mark second language (L2) learners' speaking tests, making it
arXiv:2608.05960v1 Announce Type: cross Abstract: Routine CT interpretation is inherently comprehensive, capturing incidental findings across the entire scan volume. 3D CT foundation models could assi
arXiv:2601.21800v4 Announce Type: replace Abstract: We introduce BioAgent Bench, an evaluation suite designed for measuring the performance and robustness of AI agents in common bioinformatics tasks.
arXiv:2608.06023v1 Announce Type: new Abstract: To address the limitations of video-based emotion recognition under ambiguous or socially masked behavioral cues, as well as the poor deployability of p
arXiv:2608.05928v1 Announce Type: new Abstract: Single-cell transcriptomes are sparse observations of coordinated biological programmes, yet most self-supervised models learn by reconstructing individ
arXiv:2608.05716v1 Announce Type: new Abstract: The transition from block-based to text-based programming requires learners to convert visible program structures into abstract textual expressions, whi
🚨 BREAKING — Anthropic investors worry Dario Amodei’s AI doom marketing could hurt its upcoming IPO. “He’s more of a religious leader than he is a CEO.” > used to write sensitive OpenAI memos on an of
arXiv:2507.04884v2 Announce Type: replace Abstract: We consider open-retrieval conversational question answering (OR-CONVQA), an extension of question answering where system responses need to be (i) a
arXiv:2608.05381v1 Announce Type: new Abstract: Current Multimodal Large Language Models (MLLMs) can process diverse sensory inputs, yet their reasoning remains heavily biased toward a dominant modali
arXiv:2510.14768v2 Announce Type: replace Abstract: Real-world dexterous manipulation often encounters unexpected errors and disturbances, which can lead to catastrophic failures, such as dropping the
arXiv:2608.06352v1 Announce Type: cross Abstract: Training terminal agents requires executable and verifiable tasks that are not merely solvable, but appropriately challenging for learning. Executable
arXiv:2608.05420v1 Announce Type: cross Abstract: Large language models (LLMs) can generate text that resembles a mathematical proof, but resemblance does not establish correctness. A formal proof che
today was the last day of my subscription on ollama cloud, to be honest it was a great price value for me and with GLM 5.2 and Deepseek V4 Pro i was able to Vibe code my custom woocomerce shop with mu
arXiv:2608.05359v1 Announce Type: new Abstract: CASCADE is an agentic framework that predicts downstream transcriptional effects of gene perturbation from precomputed ARACNe regulatory networks, expos
arXiv:2608.05906v1 Announce Type: new Abstract: LLM agents that repair failures often discard successful corrections, forcing later episodes to rediscover similar solutions. We study whether finalized
arXiv:2608.05813v1 Announce Type: new Abstract: Personalizing language models (LMs) to individual user preferences is essential for aligning responses with diverse goals and backgrounds. Existing meth
arXiv:2608.05482v1 Announce Type: new Abstract: Modern image models provide strong cues about what should be segmented in each view, but their masks do not by themselves determine where those labels s
arXiv:2608.06205v1 Announce Type: new Abstract: RGB--T object detection exploits the complementary strengths of visible and infrared imagery, supporting robust perception in low-light, adverse-weather
arXiv:2608.05790v1 Announce Type: new Abstract: General-purpose large language model agents have achieved strong performance on tool-augmented tasks, yet they rely on assumptions break down in blockch
arXiv:2608.05176v1 Announce Type: cross Abstract: Music education has never been a static discipline. Each major technological shift has forced educators and institutions to reconsider what they teach
arXiv:2608.06351v1 Announce Type: new Abstract: This paper addresses the limitations of Explainable Artificial Intelligence (XAI) with respect to insufficient evaluation. They are illustrated through
arXiv:2608.05631v1 Announce Type: new Abstract: Multimodal large language models excel at passive perception but struggle with complex visual cognitive tasks requiring multi-step temporal reasoning. T
arXiv:2608.05732v1 Announce Type: new Abstract: Controlling the behavior of large language models (LLMs) remains a critical challenge for AI alignment. Existing steering methods, such as Contrastive A
arXiv:2608.05195v1 Announce Type: cross Abstract: A natural language interface can be used to make cancer genomics databases easier to use, but even if a question is perfectly fluent, its scientific m
arXiv:2608.05993v1 Announce Type: new Abstract: Much clinical value is conveyed not through structured records but through communication: exchanges in which patients describe symptoms, clinicians reas