Search: “model-releases”

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:2609.01374v1 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:2609.01511v1 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:2609.00232v1 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:2609.00478v1 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: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

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:2609.00816v1 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:2609.00892v1 Announce Type: new Abstract: Rubric-based reinforcement learning decomposes open-ended instructions into prompt-specific, flexible rubrics, making it better suited than reinforcemen

arXiv:2609.01425v1 Announce Type: new Abstract: Voucher abuse poses a major challenge in e-commerce, where malicious users exploit promotional vouchers for profit. Unfortunately, fraud patterns evolve

Celigo Inc., an intelligent enterprise automation platform built for artificial intelligence, today announced the general availability of Ora, the company’s interface for building and troubleshooting

arXiv:2609.01352v1 Announce Type: cross Abstract: Role-playing large language models (LLMs) are expected to adopt a character's style while also respecting that character's knowledge boundaries. Prior

Anthropic publish the system prompts for their Claude consumer applications (Claude.ai and the Claude mobile apps - sadly not for Claude Cowork or Claude Code). I love that they do this, and that they

arXiv:2609.01111v1 Announce Type: new Abstract: Clinical LLM assistants must reason over multi-visit patient trajectories, yet whether the compact history representations used to scale them---retrieva

arXiv:2609.01308v1 Announce Type: new Abstract: Cardiac magnetic resonance (CMR) imaging provides complementary information on cardiac anatomy, function, and tissue characterization across multiple se

arXiv:2609.00242v1 Announce Type: cross Abstract: Long-tail autonomous driving failures are often framed as rare-object recognition errors. We argue that this view is incomplete: the decision-critical

arXiv:2603.11915v2 Announce Type: replace Abstract: Theory of Mind (ToM)-the ability to reason about the mental states of oneself and others-is a cornerstone of human social intelligence. As Multimoda

arXiv:2609.00250v1 Announce Type: cross Abstract: Many people now see AI systems as not just productivity tools but as social companions. Researchers are eager to study the consequences of AI companio

arXiv:2510.14980v3 Announce Type: replace Abstract: Large language models (LLMs) have shown strong abilities in writing and revising programs, yet many program-synthesis benchmarks still evaluate prog

arXiv:2609.01200v1 Announce Type: new Abstract: When the visual encoder and the language decoder of a vision-language model (VLM) run on different compute nodes, the intermediate visual-token embeddin

arXiv:2607.19011v2 Announce Type: replace-cross Abstract: Multimodal humor in memes, cartoons, and comics remains difficult for AI systems because intended meaning depends on non-literal mechanisms, s

arXiv:2609.00960v1 Announce Type: new Abstract: Magnetic resonance images of the same subject look markedly different across field strengths, which complicates the comparison and pooling of data acros

This came from another thread or comment. I forgot exactly where, but the basic idea was to replace the 51B N-gram layer in Qwen 3.8 Next with a much higher precision version. Someone running a 5090 r

arXiv:2609.00460v1 Announce Type: new Abstract: Recent Relational Deep Learning architectures have been proposed as foundation models for multi-table relational data, yet they impose constrained neigh

arXiv:2609.00749v1 Announce Type: new Abstract: Long-horizon large language model (LLM) agents require context assembly: the runtime must decide what to include in each prompt, in what order, and when

arXiv:2609.00709v1 Announce Type: cross Abstract: Large Vision-Language Models produce fluent image descriptions but offer limited semantic control: users cannot reliably specify whether captions shou

arXiv:2609.01161v1 Announce Type: new Abstract: Large language models can reproduce memorized text verbatim, yet copyright defenses are usually evaluated under incompatible protocols. We introduce Cop

arXiv:2609.01600v1 Announce Type: cross Abstract: Dynamic agent harnesses let language models change the software that shapes their own execution. This flexibility brings a new reasoning burden: a loc

arXiv:2609.00370v1 Announce Type: cross Abstract: Surrogate safety measures allow road-safety assessment from trajectory data in which crashes are absent, yet the dominant proximity measures - time-to

arXiv:2609.00446v1 Announce Type: cross Abstract: Conventional federated learning (FL) relies on parameter averaging, which forces clients to be doubly homogeneous: it demands an identical architectur