b10752
metal : add metallib build support for xcframework (#28163) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/44563342 macOS/iOS: macOS Apple Silicon (arm64)
Knowledge catalogue
metal : add metallib build support for xcframework (#28163) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/44563342 macOS/iOS: macOS Apple Silicon (arm64)
hexagon: add missing FARF logs for cpy/get_rows/set_rows/gdn ops (#28217) hexagon: fix bug ne[2] printed in proc_op_req prep-src log hexagon: add shape/VTCM farf logs to cpy, get/set rows, gdn Website
opencl: fix out‐of‐bound reads in the Adreno image kernels (#27632) opencl: clamp the q4_K decode GEMV's fetch row on a padded x-grid opencl: enforce the tiling contract of the image KQ/KQV GEMMs open
vulkan : only request VK_KHR_shader_bfloat16 extension if supported (#28155) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/44637403 macOS/iOS: macOS Apple
vulkan: handle larger batch sizes (>4) efficiently for IQ3_S mat-vec (#27449) vulkan: handle larger batch sizes (>4) efficiently for IQ3_S mat-vec when NUM_COLS > 4. 5x perf at n=8 Assisted-by: Claude
hexagon: MUL_MAT and MUL_MAT_ID fusion and fixes (#28202) hex-mm: fuse QKV and FFN matmuls that land on HMX hex-mm: remove hardcoded ne[1] < 32K restriction hex-get-rows: explicitly reject repacked Q8
ggml: avoid KleidiAI buffer type init on dispatch (#27891) Co-authored-by: Acmmi acmmi@Acmmis-MacBook-Air.local Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestati
mtmd: Fix Qwen3-tts-0.6b (#28231) mtmd: load the qwen3-tts code predictor proj_in as optional The talker and the code predictor share the hidden size on the 0.6B checkpoints, so the reference builds n
mtmd: support DeepSeek-V4-Flash-Vision-Exp (#28133) mtmd: support DeepSeek-V4-Flash-Vision-Exp handle min/max token counts from CLI rm debugging use GGML_ROPE_TYPE_VISION nits apply review comments co
common, server : enable preserve_reasoning kwarg by default, log its effective state (#28174) common, server : enable preserve_reasoning kwarg by default, log its effective state If the preserve_reaso
ggml-cuda : remove unused vars (#28235) Signed-off-by: Adrien Gallouët angt@huggingface.co Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/44811308 macOS/iO
model: correctly support input vision for deepseek4 (#28154) model: correctly support input vision for deepseek4 nits Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/att
Update ROCm to 10.0.0 release (#27803) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/44848715 macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (
metal : fix memory query under low-memory conditions (#27701) metal: Fix memory query under low-memory conditions Simply variable name Co-authored-by: Georgi Gerganov ggerganov@gmail.com Write it even
arXiv:2609.01335v1 Announce Type: cross Abstract: Many production systems can assess a configuration only by using it on live requests and observing noisy feedback. Modern agentic systems are a promin
Banger paper from ByteDance Seed. If you are curious about self-evolving agent harnesses, this one is worth your time. (bookmark it) The proposes method, HarnessDev, stops scoring a model on the tasks
arXiv:2609.00615v1 Announce Type: cross Abstract: The evolution toward sixth-generation (6G) wireless networks is driving larger antenna arrays and highly directional multi-beam transmission, making a
arXiv:2609.00669v1 Announce Type: new Abstract: Physical human--robot interaction software often couples desired-behavior specification with constrained realization; we treat these as separate layers.
arXiv:2609.01374v1 Announce Type: new Abstract: Low-rank adaptation fixes the rank of the update, but it does not identify which parts of a trained write actually carry behavior. We study that questio
arXiv:2609.00014v1 Announce Type: cross Abstract: Persona-driven techniques increasingly adapt large language models (LLMs) to diverse contexts. However, existing methods predominantly rely on rigid,
arXiv:2609.01511v1 Announce Type: new Abstract: Face forgery detectors often achieve strong results on controlled benchmarks, but their reliability under realistic image degradations remains limited.
arXiv:2609.00866v1 Announce Type: cross Abstract: The rapid advancement of vision-language models (VLMs) has accelerated progress in computational pathology; however, whole-slide image (WSI)-based pat
arXiv:2609.00077v1 Announce Type: new Abstract: Code-level autonomous research loops (ARLs) have recently emerged as a concrete object of study in automated machine learning research. In such loops, a
arXiv:2606.18506v2 Announce Type: replace Abstract: Objective sleep assessment relies on polysomnography (PSG), yet clinical impact is often better reflected in patient-reported outcomes (PROs) such a
arXiv:2609.00232v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have achieved strong performance on OCR-centric document understanding and text-rich visual reasoning benchmark
arXiv:2609.00634v1 Announce Type: new Abstract: Much of the literature on structured image recognition has disproportionately focused on the comparison of classification algorithms. Rather than invest
arXiv:2609.00231v1 Announce Type: new Abstract: Existing research on object hallucination in multimodal large language models (MLLMs) predominantly attributes the problem to language priors such as ov
arXiv:2609.01100v1 Announce Type: new Abstract: In current Mixture-of-Experts architectures, routing is performed based on representations dominated by structure shared across all tokens, limiting exp
arXiv:2609.00478v1 Announce Type: new Abstract: Gaze-based assistive manipulation typically supports object selection, while arbitrary-position placement requires accurate spatial alignment between th
arXiv:2609.01604v1 Announce Type: new Abstract: LLM-based evaluators of natural language generation (NLG) quality are widely deployed as scoring tools and as automated training signals, yet the intern
arXiv:2601.04463v2 Announce Type: replace-cross Abstract: Memory management is vital for LLM agents in long-term and personalized interactions. Most previous work studies how to retrieve and use memor
arXiv:2609.00874v1 Announce Type: new Abstract: As agentic systems become compound systems, increasingly important decisions move above task execution itself: when should a higher-level controller pre
arXiv:2609.00924v1 Announce Type: cross Abstract: Monocular videos record 3D scenes as sequences of 2D image-plane projections, obscuring depth and spatial relationships. Multi-object trackers localiz
arXiv:2609.00495v1 Announce Type: cross Abstract: Diffusion large language models (dLLMs) generate text through iterative denoising rather than left-to-right decoding. This generation paradigm introdu
arXiv:2602.03708v3 Announce Type: replace Abstract: Large Language Models (LLMs) achieve strong performance across many tasks but suffer from high inference latency due to autoregressive decoding. The
arXiv:2508.08855v5 Announce Type: replace-cross Abstract: Understanding biases and stereotypes encoded in the weights of Large Language Models (LLMs) is crucial for developing effective mitigation str
arXiv:2603.10529v2 Announce Type: replace Abstract: Litter pollution represents a growing environmental problem affecting natural and urban ecosystems worldwide. Waste discarded in public spaces often
arXiv:2609.01194v1 Announce Type: new Abstract: Major life events have proven difficult to predict. Does this reflect limits of theory, data, and algorithms, or the large role of chance? We examine on
arXiv:2609.00593v1 Announce Type: new Abstract: Neuroradiologists rarely read a brain MRI in isolation, yet automated brain-MRI report generation has been built almost entirely for single studies. Tem
BREAKING: Insufferable sociopath largely responsible for AI Bubble says AI is a bubble. 🔥SAM ALTMAN WARNS OF AN AI BUBBLE: OpenAI CEO Sam Altman reveals: “I’m seeing the first signs of what feels to m
arXiv:2609.00632v1 Announce Type: cross Abstract: Large Language Models (LLMs) have achieved remarkable success across diverse domains, but their adaptation to privacy-sensitive, distributed datasets
arXiv:2609.00228v1 Announce Type: new Abstract: Scientific domain entity linking (EL) differs from general domain EL because mentions and entity names often lack lexical overlap. Another challenge is
AI factory deployment is becoming a workload-sizing exercise rather than a custom infrastructure project. Enterprises need infrastructure spanning edge inference and large-model training. Broadcom Inc
Custom chipmaker Broadcom Inc. beat expectations on earnings and revenue in its third-quarter financial report and hinted at the prospect of doing more business with leading artificial intelligence la
arXiv:2609.01554v1 Announce Type: cross Abstract: Automated lesion segmentation in whole-body PET/CT is complicated by the variety of physiological tracer uptake patterns and by the differing appearan
arXiv:2402.00759v4 Announce Type: replace-cross Abstract: We present a comprehensive survey of the advancements and techniques in the field of tractable probabilistic generative modeling, primarily fo
arXiv:2411.10788v4 Announce Type: replace Abstract: Synthetic Aperture Radar (SAR) imagery provides robust environmental and temporal coverage (e.g., during clouds, seasons, day-night cycles), yet its
arXiv:2609.00891v1 Announce Type: new Abstract: Sharing context between LLMs in a multi-model system requires the receiving model to prefill the shared prefix because KV caches are model-specific. Rec
arXiv:2512.11199v2 Announce Type: replace Abstract: Computer-aided design (CAD) defines 3D models as compact, precise, and editable representations, making it directly useful for several fields. Recen
arXiv:2609.00949v1 Announce Type: cross Abstract: Multi-turn tool calling is a core evaluation scenario for large language model (LLM) agents. On public tool-calling benchmarks, open-weight models now
arXiv:2609.01479v1 Announce Type: new Abstract: Beyond semantic content, camera parameters play a pivotal role in dictating the geometric perspective and appearance of any given image. While recent im
arXiv:2609.00747v1 Announce Type: new Abstract: Large language models increasingly generate research ideas, yet judging their novelty or feasibility at generation time does not establish whether they
arXiv:2609.01535v1 Announce Type: cross Abstract: This paper explores whether large language models (LLMs) can design video coding tools, a highly challenging task due to the intricate algorithmic cou
arXiv:2609.01552v1 Announce Type: new Abstract: Scientific equation discovery has long been central to scientific progress, proceeding through iterative cycles of hypothesis generation, observational
arXiv:2609.00457v1 Announce Type: new Abstract: Injecting frozen relational-encoder embeddings as soft tokens into a large language model (LLM) is a conceptually appealing fusion strategy: the encoder
arXiv:2510.26954v3 Announce Type: replace-cross Abstract: The Turing Test is no longer adequate for distinguishing human and machine intelligence. With advanced artificial intelligence systems already
arXiv:2609.00816v1 Announce Type: new Abstract: Scene text recognition is reported as 89--97% accurate on the six standard benchmarks, and the problem is widely treated as saturated. We present an alt
arXiv:2609.00959v1 Announce Type: new Abstract: Mixed-format medical visual question answering (VQA) requires stable option selection and machine-readable free-text output. The two formats fail differ
🚀🚀🚀 can't wait for the Muse Spark open weight releases. ❤️ Thank you @finkd Muse Spark 1.3 is rolling out today with frontier performance almost too cheap to meter. This is the biggest jump we've made
arXiv:2609.00445v1 Announce Type: cross Abstract: Deployed language model safeguards (safety fine-tuning, filtering, unlearning) vary by principal only outside the model weights: filters are reconfigu