Strata with Qwen3.8 Flash Next UD-Q4_K_XL
Been seeing quite a few posts about Strata lately, so I figured I'd give it a shot on my RTX PRO 6000 and I am very impressed. Most of the benchmarks I've seen are using IQ2 or IQ3 quants, so I wanted
Knowledge catalogue
Been seeing quite a few posts about Strata lately, so I figured I'd give it a shot on my RTX PRO 6000 and I am very impressed. Most of the benchmarks I've seen are using IQ2 or IQ3 quants, so I wanted
The ultimate LLM benchmark: Chilean Spanish. 80% of AI models fail to recognize Chilean Spanish and insist on speaking like an Argentine 80% de modelos de IA no logra reconocer el español chileno e in
We @Sequoia are thrilled to back @TypesafeAI @CompleteSkeptic. ChatGPT put AI front and center in the consumer mind. Claude Code transformed the day-to-day work of the developer/knowledge worker. Jev
arXiv:2603.01376v2 Announce Type: replace Abstract: Sparse plus Low-Rank (mathbf{S} + mathbf{LR}) decomposition of Large Language Models (LLMs) has emerged as a promising direction in model compressio
arXiv:2610.11716v1 Announce Type: cross Abstract: We describe a 4-tensor attention model that predicts the next semantic state of a scene, for video generation and robot planning. A window of states h
arXiv:2610.11696v1 Announce Type: new Abstract: Puzzles are widely used to evaluate the reasoning capabilities of artificial intelligence (AI) systems for sequential decision making, yet approaches or
arXiv:2610.10607v1 Announce Type: new Abstract: Immersive VR180 video is increasingly produced with professional stereo fisheye cameras, yet public VR180 research resources are mostly collected from o
arXiv:2610.12183v1 Announce Type: cross Abstract: Black-box optimization (BBO) arises in many scientific and engineering problems where objective evaluations are expensive and limited. Recent large la
arXiv:2607.17575v3 Announce Type: replace Abstract: We propose ARBITER, a novel LLM guardrail framework that introduces two key ideas: (i) dual-hypothesis reasoning, a reasoning method for LLM guardra
arXiv:2610.10862v1 Announce Type: cross Abstract: Modeling heterogeneous materials remains a challenge for physics-informed neural networks such as the deep energy method (DEM). The DEM and its varian
I shipped a new feature for my blog today: the Newsletters page, which offers an index of all of the newsletters I've sent out, both my free weekly Substack and my monthly sponsors-only updates. I bui
arXiv:2610.10580v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly being integrated into hardware verification to automate specification interpretation, verification-artif
arXiv:2610.11149v1 Announce Type: new Abstract: Video anomaly detection (VAD) is a fundamental and safety-critical task in computer vision. Recent generative approaches detect anomalies from a distrib
A week of free access to Qwen3.8-Max, Qwen3.8-Flash, and Wan3.0 on @gmi_cloudis live. Explore what you can build with us now. 🙌 We're extending FREE Qwen 3.8 Max + Flash for 7 more days! And we've inc
arXiv:2403.18791v4 Announce Type: replace Abstract: Estimating the pose of objects from images is a crucial task of 3D scene understanding, and recent approaches have shown promising results on very l
arXiv:2602.15397v2 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) models leveraging the native autoregressive paradigm of Vision-Language Models (VLMs) have demonstrated superior
arXiv:2610.12240v1 Announce Type: cross Abstract: Time-series foundation models (TSFMs) have achieved strong forecasting performance across domains. However, most adaptation methods remain static. Exi
arXiv:2610.11585v1 Announce Type: cross Abstract: Recent advances in large language model (LLM) pretraining highlight the role of high-quality training data in improving performance. While model-based
arXiv:2610.12265v1 Announce Type: new Abstract: Accurate workload forecasting is critical for elastic resource provisioning in web-scale cloud services, where distribution shifts driven by viral conte
arXiv:2610.10628v1 Announce Type: cross Abstract: Existing LLM-based approaches for software Requirements Engineering (RE) typically rely on basic prompting strategies or rudimentary agent collaborati
arXiv:2610.11050v1 Announce Type: new Abstract: Computer-use agents are capable of completing complex tasks, increasing the use of automatic judges to determine success, either for training or for eva
arXiv:2610.12002v1 Announce Type: cross Abstract: Test-time training (TTT) adapts an LLM's parameters using signals derived from test inputs, and can make striking improvements in pre-specified settin
arXiv:2610.09944v2 Announce Type: replace Abstract: An essential control of AI agents is their ability to manage runtime. This ability requires a sense of time-awareness, to predict and estimate wall-
arXiv:2610.10848v1 Announce Type: new Abstract: Accurate evaluation is central to selecting which LLM to deploy, yet testing a candidate on live traffic exposes real users to an unvetted model. Teams
arXiv:2610.10541v1 Announce Type: new Abstract: Knowledge Graph (KG) quality depends not only on downstream graph validation, but also on the quality of tabular metadata used before integration. In me
An Anthropic AI model provided false information about an unsolved homicide to a Philadelphia Police Department (PPD) tipline, according to a report from 6abc. In a statement released on Friday, the P
arXiv:2603.08993v2 Announce Type: replace-cross Abstract: System prompts for LLM-based coding agents are software artifacts that govern agent behavior, yet lack the testing infrastructure applied to c
arXiv:2610.10969v1 Announce Type: new Abstract: Predicting thermally activated diffusion and defect evolution with event-driven models requires identifying atomic rearrangement mechanisms and their ac
hexagon: fix IM2COL patch-embed DMA ring overflow (#30189) hexagon: fix IM2COL patch-embed DMA ring overflow The exact-tiling (stride == kernel, no pad/dilation) IM2COL DMA kernel issues ICKH DDR->VTC
CUDA: pass src1 precision to host MMQ config helpers (#30168) CUDA: pass src1 precision to host MMQ config helpers Signed-off-by: ynankani ynankani@nvidia.com make src1 prec explicit Signed-off-by: yn
metal: add the 128/96 flash attention kernels, accept every compiled pair (#30209) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/54260937 macOS/iOS: macOS
server: use port 9931 by default (#30159) server: use port 9931 by default revert unrelated changes Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/54269123
ci: fix Models Backend webgpu by supporting GGML_OP_DUP (#30216) The mixed batch path of PR-29622 writes the token rows with set_rows into a dup of the embeddings. WebGPU did not support DUP, so the d
musa: drop mp_21 from the default architectures (#30203) musa: drop mp_21 from the default architectures Signed-off-by: Xiaodong Ye xiaodong.ye@mthreads.com Address review comments Signed-off-by: Xiao
vulkan: fix rms_norm workgroup count overflow (#30145) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/54337638 macOS/iOS: macOS Apple Silicon (arm64) macOS
webgpu: use 2D workgroup dispatch for all the ops which use 1D dispatch (e.g., rms_norm) (#30219) remove 1D workgroups dispatching formatting Website: https://llama.app Attestations: https://github.co
meta : handle host views (#30217) meta : handle views of tensors allocated on the host A view shares the memory of its view_src, so ggml-alloc never allocates a view in the buffer of the split it land
ggml: fix OOB write in ggml_acc with negative offset (#30135) ggml_acc_impl narrowed a size_t offset to int32_t without checking that it fits, so a large offset could truncate to a negative int32_t. T
llama: keep the backend sampling graph static across ubatches (#30223) The reserve builds n_outputs_max_per_seq sampling chains per sampler, while a decode built one per output row, so the graph chang
chat : refactor API (#30210) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/54392536 macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, Kle
model : use exact GELU for ModernBERT encoders (#30108) model : use exact GELU for ModernBERT encoders Assisted-by: Codex model : keep tanh GELU aliases on ggml_geglu Assisted-by: Claude Opus 5.5 mode
opencl: fix kernel compilation for a6x GPUs (#30176) opencl: skip kernel_cpy_f32_f32_pack on A6X to avoid shader compiler crash The A6x compiler backend found in iot device with a623 (E031.50.31.01) c
CUDA: Remove redundant CUDA copies after SSM_SCAN (#29807) CUDA: fuse copy of updated state snapshots into recurrent cache with ssm_scan CUDA: remove redundant cuda copies with K==1 (non spec-dec) sce
llama-bench: respect -fitc if bigger than required benchmark size (#28331) Assisted-By: opencode,llama.cpp,Qwen3.6-35B-A3B,Qwen3.8-27B Website: https://llama.app Attestations: https://github.com/ggml-
graph : reorder get_rows for embeddings (#30160) graph : reorder get_rows for embeddings cont : fix gemma4 and improve input embedding construction logic cont : add TODO for lora cont : fix raw embedd
CUDA: fix round issue, under MSVC the CPU and GPU agree (#30229) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/54453988 macOS/iOS: macOS Apple Silicon (ar
vendor: apply deep nested json patch from upstream (#30253) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/54488539 macOS/iOS: macOS Apple Silicon (arm64)
Banger paper from Meta Superintelligence Labs on self-improving agents. (bookmark it) It's hard to know exactly what drives self-improvement, since so many variables are at play (notes, skills, tool c
Banger paper from Meta Superintelligence Labs on user simulators for agent training. Agent RL setups usually let an assistant LLM play the user, so the simulated user is too cooperative and too explic
arXiv:2610.10663v1 Announce Type: cross Abstract: Bioacoustics and ethology encompass a wide range of audio understanding tasks, many of which stand to benefit from recent advances in large audio-lang
arXiv:2501.19065v3 Announce Type: replace-cross Abstract: Long-term time-series forecasting supports a wide range of applications, including weather prediction and electricity demand planning. Frequen
before I joined Anthropic, I spent about 2 weeks hacking on this as a side project with Opus 4. It used the Agent SDK so it needed a constantly running process & didnt work that well but one prompt to
arXiv:2610.11305v1 Announce Type: new Abstract: A language model may revise the same proposition after receiving genuinely relevant evidence or after receiving directional user pressure that adds no r
arXiv:2511.04655v2 Announce Type: replace Abstract: Multimodal LLMs can answer many questions in vision-centric benchmarks without looking at the image, using linguistic priors and skewed answer distr
arXiv:2610.11407v1 Announce Type: cross Abstract: Synthetic tabular generators are commonly optimized for distributional fidelity, but statistical similarity alone does not guarantee preservation of c
arXiv:2610.11087v1 Announce Type: new Abstract: The rapid growth of scientific publishing has strained peer review, particularly in machine learning, raising concerns about declining review quality an
arXiv:2610.11610v1 Announce Type: cross Abstract: Generating ultrasound reports from multiple images requires aggregating clinical evidence across views, yet archived key frames capture only part of t
arXiv:2610.11489v1 Announce Type: new Abstract: Visual instance retrieval often fails when the same object appears at different apparent sizes in the query and gallery. We show that the dominant cause
I made BigMoeOnEdge+ (BigMoeOnEdge-plus), a fork of Helldez's BigMoeOnEdge, the engine that streams MoE experts from flash so models bigger than RAM can run on-device. It adds a full Android chat app
arXiv:2610.11430v1 Announce Type: new Abstract: While domain-specific Large Language Models (LLMs) have encoded vast biomedical knowledge, their limited context windows often hinder a deep understandi