b10720
ROCm: add radix TOP_K for long rows (#27466) ROCm: add radix TOP_K for long rows Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/44178618 macOS/iOS: macOS A
Knowledge catalogue
ROCm: add radix TOP_K for long rows (#27466) ROCm: add radix TOP_K for long rows Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/44178618 macOS/iOS: macOS A
webgpu : avoid crash when offset is not multiple of 4 in WebGPU ggml_backend_tensor_get() implementation (#28045) webgpu : avoid crash when offset is not multiple of 4 in WebGPU ggml_backend_tensor_ge
opencl: tune the quant paths for Intel Xe-LP GPUs to improve its TG and PP performance (#26438) opencl: Q4_K/Q5_K mul_mv N_DST 4->8 on Intel for 2x activation reuse opencl: Q4_K mul_mm 8x8 tile fot In
kv-cache : optimize restoring non-contiguous cells (#27991) kv cache : batch state restore scatter reads per contiguous run When restoring state into non-contiguous destination cells (e.g. a prompt-ca
AVX2: Speed up large batch size prompt processing of IQ models (#27402) Batched gemm for grid IQ quants Style updates and a bit more performance Clean up comments Move code around Vectorize IQ panel d
metal : add concat support for quantized types (#28116) Assisted-by: pi:llama.cpp/DeepSeek-V4-Flash-0731 Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/442
CUDA: XOR swizzle flash attn K,V smem fp16 tiles (#25635) CUDA: XOR swizzle flash attn K,V smem fp16 tiles Signed-off-by: ynankani ynankani@nvidia.com Fix use 64bit generic pointer instead of 32bit sh
metal : add fa-vec tunings for M1 Ultra (#28088) metal : add fa-vec tunings for M1 Ultra metal : move M1 Ultra tunings after M1 Max section metal : remove duplicate blank line Website: https://llama.a
arXiv:2608.28394v1 Announce Type: cross Abstract: Cyber threat intelligence (CTI) is foundational to modern cyber defense, yet much of it resides in unstructured reports whose volume and heterogeneity
arXiv:2608.27729v1 Announce Type: new Abstract: Function routing -- selecting the correct API call from a fixed catalog given a natural-language request -- is a deployment problem where small students
arXiv:2608.27477v1 Announce Type: cross Abstract: Graphical user interfaces have emerged as an important environment for evaluating autonomous AI agents on multimodal interactive tasks. Existing bench
arXiv:2608.28009v1 Announce Type: new Abstract: The rapid evolution of large language models necessitates robust machine-generated text detection. Existing paradigms typically follow two isolated trac
arXiv:2608.27757v1 Announce Type: new Abstract: Searchless chess networks reach human master strength from a single forward pass by imitating a stronger teacher: the strongest, Leela Chess Zero's (Lc0
Many of the questions that matter in enterprise data aren't just about individual rows — they're about how things connect: how two accounts are linked, what path a payment took, what context grounds a
arXiv:2608.28478v1 Announce Type: new Abstract: Factual question answering (QA) typically assumes a single canonical answer, obscuring whether large language models (LLMs) retain divergent accounts of
arXiv:2608.28557v1 Announce Type: new Abstract: Neural-network optimization in 2025-2026 is no longer well described as a succession of new Adam variants. The design space has expanded from coordinate
arXiv:2608.28389v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) augments LLMs with external documents, but public or user-editable sources expose RAG systems to data poisoning:
arXiv:2608.28070v1 Announce Type: new Abstract: Automated detection of surface micro-defects on industrial components, such as copper tubes, is critically important for quality assurance but remains c
arXiv:2608.28044v1 Announce Type: cross Abstract: Large language model (LLM) inference serving is priced by tokens, but GPU energy is consumed over inference windows. This accounting mismatch makes to
arXiv:2608.26907v1 Announce Type: cross Abstract: Deep generative models such as flow matching and diffusion models have shown potential for learning complex dynamical systems, but typically act as bl
arXiv:2608.28053v1 Announce Type: new Abstract: Chinese neologisms exploit diverse and unique linguistic mechanisms, such as phonetic substitution (e.g., 886 for ``bye-bye'') and visual character deco
arXiv:2608.28266v1 Announce Type: new Abstract: Agent systems powered by multimodal large language models (MLLMs) have advanced rapidly in recent years, yet existing embodied-agent benchmarks still la
arXiv:2608.27893v1 Announce Type: new Abstract: High-quality e-commerce creatives are essential for presenting products and conveying marketing messages. Recent diffusion models enable scalable creati
I've made a modification of llama.cpp MTP for people that want to run models like QWEN 27B on 16GB and similar setup, the focus is reducing the memory cost of MTP allowing more speed for less ctx cost
arXiv:2509.22737v3 Announce Type: replace Abstract: Visual comparison reasoning is a fundamental capability of vision-language models (VLMs), covering judgments of object quantity, geometric dimension
arXiv:2608.28084v1 Announce Type: new Abstract: The classification and regression of particle collision events constitute a persistent computational challenge in experimental high energy physics, wher
arXiv:2608.28341v1 Announce Type: new Abstract: Precise dense correspondence is a fundamental prerequisite for multimodal spectral imaging systems that fuse disparate wavelength ranges for subsequent
I haven't had a chance to test it yet, but it looks very promising. It seems to speed up MTP for MoE models across different draft widths (especially greater than 1). Check the benchmarks. submitted b
arXiv:2608.28405v1 Announce Type: new Abstract: Current cultural evaluations for large language models (LLMs) often reduce culture to single-turn factual recall via MCQs, failing to capture a common u
arXiv:2608.28442v1 Announce Type: new Abstract: Pretraining accounts for a large fraction of the total computational cost in LLM training. However, noise-dominant gradients and the highly ill-conditio
arXiv:2608.28080v1 Announce Type: new Abstract: Image-conditioned 3D generation has advanced rapidly, yet existing evaluation protocols largely judge rendered-view plausibility and semantic alignment,
arXiv:2608.28236v1 Announce Type: new Abstract: Predictive Process Monitoring (PPM) enables organizations to forecast future process behavior, such as the next activity and remaining time of ongoing c
arXiv:2608.27521v1 Announce Type: new Abstract: Many dynamical processes unfold on the sphere but the default scientific machine learning architectures are Euclidean. Applying these architectures on a
arXiv:2608.28547v1 Announce Type: new Abstract: Model merging combines multiple task-specific fine-tuned LLMs into a single multi-task model without additional training. However, merged models are kno
arXiv:2603.27936v3 Announce Type: replace-cross Abstract: Nonlinear Partial Differential Equations (PDEs) are ubiquitous in mathematical physics and engineering. Although Physics-Informed Neural Netwo
arXiv:2502.15438v5 Announce Type: replace Abstract: Vision-based occupancy networks (VONs) provide an end-to-end solution for reconstructing 3D environments in autonomous driving. However, existing me
arXiv:2608.28343v1 Announce Type: new Abstract: High-throughput phenotyping depends on accurate 3D reconstruction of plants across growth stages, yet the development and evaluation of temporal complet
I'm very happy with Qwen-3.8-27B, I run it on my work machine and switched for major part of real coding tasks from cloud subscriptions to it. I use one dedicated headless RTX 3090, and get maybe 1000
arXiv:2606.21359v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly used to communicate and explain scientific concepts, yet their tendency to hallucinate poses significa
arXiv:2608.27925v1 Announce Type: new Abstract: Entity-Memory graph retrieval keeps dialogue turns as verbatim Memory nodes, links repeated mentions through shared Entities, and connects adjacent Memo
arXiv:2305.12474v4 Announce Type: replace Abstract: Large Language Models(LLMs) have demonstrated remarkable performance across various natural language processing tasks; however, how to comprehensive
arXiv:2608.27844v1 Announce Type: new Abstract: Existing evaluations of harmful content detection rely predominantly on static benchmarks, which struggle to reflect the interactive adversarial ecosyst
arXiv:2608.28096v1 Announce Type: new Abstract: Learning-based image-to-point-cloud (I2P) registration has garnered increasing attention in recent years. Nevertheless, existing methods still struggle
arXiv:2608.28207v1 Announce Type: new Abstract: Diabetic retinopathy (DR) is a major cause of preventable blindness, creating a need for accurate and trustworthy automated screening. This study invest
arXiv:2608.27856v1 Announce Type: new Abstract: Recent advances in large language models are enabling autonomous clinical agents to perform increasingly complex electronic health record (EHR) modeling
arXiv:2608.28439v1 Announce Type: new Abstract: One model passed our fidelity check without ever opening the datasheet. We found it while qualifying models for an internal extraction service: a struct
arXiv:2608.28155v1 Announce Type: new Abstract: Professional financial examinations require models to combine domain knowledge, calculation, and judgment, yet no benchmark covers the full CFA and FRM
arXiv:2608.27672v1 Announce Type: new Abstract: We present Qwen-GuidePlay-2B, a 2B-parameter language model for dialogue-game interaction. We fine-tune Qwen3.5-2B using three steps: a) SFT on only suc
Data pipelines are the backbone of the modern enterprise, yet a barrier to entry exists for orchestrating them, making this critical capability unavailable to many data professionals. Following our an
arXiv:2608.27531v1 Announce Type: cross Abstract: The safety of large vision-language models is increasingly stress-tested by multimodal jailbreaks, yet existing attacks remain largely static at the m
arXiv:2608.28302v1 Announce Type: new Abstract: Diffusion-based inpainting models modify only a localized part of an image, while many AI-image detectors rely on global artifacts and do not localize.
arXiv:2608.28567v1 Announce Type: new Abstract: Conventionally, Building Damage Assessment (BDA) is tackled either with dedicated network architectures or by fine-tuning geospatial image foundation mo
arXiv:2608.28116v1 Announce Type: new Abstract: Forecast combination is a reliable way to improve predictive performance when several forecasting models are available. Simple aggregation rules such as
I keep seeing demos of AI agents building scenes in Blender through BlenderMCP, so I tried it myself. I ran both models locally for this and picked the GLM 5.3 family(Q4 quant) because videos of it do
glm-5.3 now beats gpt-5.6 sol and claude fable 5 on agentic benchmarks 5.3 flash is right behind it glm-5.3 didn’t even need a new base model to get there @zai_org kept the glm-5.2 base and scaled pos
arXiv:2608.28386v1 Announce Type: new Abstract: Existing monocular full-body 3D human-object interaction (HOI) methods do not combine explicit finger-level grasp optimization with category-agnostic ob
Grok @Bot only gets better from here Gavin Baker says Grok Bot feels like another ChatGPT moment because it turns hours of Claude Code work into seconds: 'You see these 23-year-old kids and just the w
arXiv:2608.28404v1 Announce Type: new Abstract: Video generation for autonomous driving cannot follow the web-scale route: driving data is expensive to collect, bound by privacy requirements, and cann
How fast is the Claude Code plugin ecosystem actually growing? Plugin-touching commit activity grew 8.8x in the six months after the initial launch. Researchers studied 1,926 repositories hosting plug
Hi all, I have recently been experimenting with different LLM set ups and after everyone was raving about how good Qwen 3.8 27b was, I was inspired to try and get it deploying. After some battling wit