Knowledge catalogue
With all the new models released recently one important upgrade went unnoticed: Llama.cpp bumped ROCm from 7.2 to 7.14. I was waiting for that because in 7.14 support for gfx1103 (Radeon 780m) was int
Honestly I am surprised at the speed and performance I am getting from the model, it does not allow for complete hands off like Claude 5.0 but that is not what I want, i want to be able to iterate and
I’m running Ollama on an M4 Pro Mac with 48 GB unified memory and testing local coding models for repository work. Direct Ollama inference is fine. Qwen3.8 27B-MLX runs well enough for me, and the loc
I did a short test of the different reasoning efforts, since on default xhigh the model thinks a lot. Not very scientific, just a quick 'generate an SVG of a pelican on a bicycle' prompt with 3 differ
My local inference build, with: ASUS WS C422 PRO/SE 10-core Xeon W-2255 64GB ECC RAM 64GB VRAM Pimped case with TurboLEDz indicating the frequencies of the 10 xeon cores. Running llama.cpp with SYCL b
totally agree! here's how we architected deepagents to enable this deepagents runs connected to a 'backend'. this backend needs to expose filesystem like operations, but it does not have to be a files
Hello; I'm a semi-beginner at local AI. I've been experimenting with this tech for a while, and I still haven't found a proper harness that fits my models, hardware, and needs. My use case is pretty s
@hwchase17 @LangChain I built an open-source CLI that scaffolds, runs, and deploys production LangChain agents — frontend and backend in one command. Every agent project starts the same way: wire up a
https://github.com/alekk89/llama-cpp-windows-manager It has been three months since I first shared my personal solution for running llama.cpp on Windows, and the project has evolved considerably since
You can literally run Opus 4.6 Max-level intelligence on a MacBook Pro. Locally. We promised open weights for Qwen3.8. Now, time to meet them! 🎉 ⚡ Qwen3.8-27B: - A native multimodal dense model. With
arXiv:2608.12745v1 Announce Type: new Abstract: Medical AI has demonstrated specialist-level diagnostic accuracy, yet these capabilities remain largely inaccessible in resource-constrained rural setti
arXiv:2608.12960v1 Announce Type: new Abstract: Fiber tractography's ability to reconstruct the brain's structural pathways, has made it a crucial component of modern neuroimaging, enabling detailed,
arXiv:2608.12398v1 Announce Type: cross Abstract: We propose IM-LEPP (Integrated Multimodal Latent Energy-based Predictive Processing), a hierarchical, energy-based model of multimodal cognition that
arXiv:2608.12665v1 Announce Type: cross Abstract: For solving nonconvex equality-constrained optimization problems, a recent Gradient-Eigenstep Algorithm by Goyens et al.~is an iteration-efficient app
arXiv:2603.04243v3 Announce Type: replace Abstract: Cerebral small vessel disease (CSVD) markers, specifically enlarged perivascular spaces (EPVS) and lacunae, present a unique challenge in medical im
@alibaba_qwen: Alibaba releases weights for Qwen3.8 models under Apache 2.0 license, including Qwen3.8-27B, which it says beats Qwen3.7-Plus and excels in real-world coding — We promised open weights
chat : pass reasoning_effort to template chat: add reasoning_effort to common_chat_templates_inputs Store OpenAI Chat Completions reasoning_effort and make it available to jinja templates (with model
arXiv:2608.12854v1 Announce Type: cross Abstract: Autonomous driving requires planning under both semantic constraints and predictive dynamics. Existing end-to-end driving approaches, however, typical
arXiv:2510.22282v2 Announce Type: replace-cross Abstract: Urban socio-economic sensing plays a vital role in advancing global sustainable development goals. With the advent of Large Vision-Language Mo
arXiv:2608.13438v1 Announce Type: cross Abstract: Contact-rich manipulation failures are often detected only after the robot has committed to contact. This is especially limiting in wrist-camera setup
arXiv:2608.12761v1 Announce Type: new Abstract: Agentic workflows are commonly evaluated by whether they reach the correct outcome. That is insufficient in institutional settings, where a correct acti
arXiv:2510.21805v2 Announce Type: replace-cross Abstract: Generative recommendation (GR) is an emerging paradigm that represents each item via a tokenizer as an n-digit semantic ID (SID) and predicts
arXiv:2608.12864v1 Announce Type: cross Abstract: Public blockchain data enables large-scale DeFi-related analysis, but many existing approaches are application-specific, difficult to scale, or hard t
arXiv:2608.12831v1 Announce Type: cross Abstract: Online platforms increasingly compare many adaptive decision policies---ranking systems, recommendation algorithms, pricing rules, and language-model
arXiv:2608.13458v1 Announce Type: new Abstract: Fine-grained human action recognition (FHAR) must distinguish visually similar actions that differ mainly in body configuration, timing, or local appear
arXiv:2608.12932v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models promise to bring end-to-end reasoning to autonomous driving, but their computational cost remains far too high for r
arXiv:2608.12365v1 Announce Type: cross Abstract: For fifty years, data systems have answered two questions. The relational model asked which records match a predicate; the vector model asked which ve
Ollama makes it easy to run a model locally, but the hard part for me starts after the model responds: what keeps an agent from having unclear tool permissions, unbounded loops, silent partial failure
arXiv:2608.12377v1 Announce Type: cross Abstract: Brains and large language models (LLMs) are fundamentally different memory systems, but they can be compared through shared functional questions: wher
arXiv:2608.13200v1 Announce Type: cross Abstract: Modern LLMs excel at reasoning and instruction following, enabling users to express complex and diverse information needs. However, conventional retri
arXiv:2608.12926v1 Announce Type: cross Abstract: Traditional player evaluation in professional handball relies on basic box-score metrics or heuristic indices, which fail to credit the multi-player b
Have been thinking about building a custom harness because nothing out there quite meets my needs for scaling a fully hybrid human + AI company, especially when it comes to compounding learning loops.
arXiv:2608.12502v1 Announce Type: new Abstract: Remote sensing image change captioning (RSICC) converts bitemporal imagery into a sentence describing semantic changes. Most RSICC methods condition cap
arXiv:2608.13267v1 Announce Type: cross Abstract: Existing vision-language model (VLM) benchmarks emphasize perception and reasoning accuracy (how well VLMs describe and reason about what they see in
arXiv:2608.12645v1 Announce Type: new Abstract: LLM judges have become central infrastructure for model evaluations, online grading, and reward modeling. Judges are typically validated by accuracy on
arXiv:2608.13545v1 Announce Type: cross Abstract: Modern language models are trained on heterogeneous web-scale text corpora. Consequently, studying knowledge and skill acquisition is difficult, as pr
arXiv:2608.13450v1 Announce Type: cross Abstract: Autonomous vehicles depend on large safety-critical software stacks, where weaknesses reachable from adversarial inputs may affect steering, braking,
arXiv:2608.13476v1 Announce Type: new Abstract: We present Multi-Agent Reasoning and Coordination (MARC), an open-source framework that replaces monolithic LLM prompting with deterministic multi-agent
Max-level intelligence, one API call away. Qwen3.8-2.4T-A95B is now live on DeepInfra, ready for your creative builds. 🥳 Take a deep dive on DeepInfra! @DeepInfra New on DeepInfra: Qwen3.8-2.4T-A95B 🚀
arXiv:2608.12361v1 Announce Type: new Abstract: Neologisms, emerging terms in meaning or form, can serve as new vehicles for toxic expression, like 'country girl' as a stigmatizing label targeting fem
Qwen3.8-27B is finally here, and NInfer already has Day-0 support! Weights: https://huggingface.co/neroued/Qwen3.8-27B-NInfer Just update to the latest source and give it a try. On a single RTX 5090,
arXiv:2608.13039v1 Announce Type: new Abstract: The paper introduces the ante-hoc Explainable AI methodology to assess the global feature importance of the Machine Learning models used for heat demand
arXiv:2608.12346v1 Announce Type: new Abstract: This position paper argues that modern AI alignment methods - originally designed to prevent harmful output - are dual-use technologies that may easily
arXiv:2608.12675v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) is widely used to improve the performance of Large Language Models (LLMs) in answering user queries. Existing priva
Qwen3.8-Max is live on DigitalOcean Serverless Inference. Launching side by side with DigitalOcean as our Day 0 launch partner. Big model. Smooth sailing. Now on DigitalOcean.🌊🏄♀️ @digitalocean Now a
arXiv:2608.13239v1 Announce Type: new Abstract: Training Multimodal Large Language Models for audio-visual social understanding is a crucial step toward embodied social intelligence. Chain-of-thought
arXiv:2608.13381v1 Announce Type: new Abstract: Digital restoration of historical manuscript images aims to improve readability while preserving the authenticity of cultural heritage documents. Howeve
arXiv:2608.13426v1 Announce Type: cross Abstract: Transformer-based language models achieve strong performance but incur substantial inference cost due to repeated high-dimensional matrix multiplicati
I've been an Ollama Cloud subscriber for ~6 months. I generally use the the latest GLM models available for coding as well as a personal instance of Open WebUI. I have tried to get answers directly vi
The demo video above was created with a single prompt using Qwen 3.8 27B Q8_K_XL. Prompt: create me a single page, html/js/css GeoCities, Laser Wave, 80's retro, minecraft clone named RetroCraft. Embe
arXiv:2608.12748v1 Announce Type: new Abstract: Referring Expression Comprehension (REC) is commonly studied under dataset-specific fine-tuning, resulting in specialist models with limited cross-datas
arXiv:2511.17007v2 Announce Type: replace-cross Abstract: Open and intelligent radio access networks (RANs) envisioned for 6G require accurate and reusable wireless channel knowledge for intelligent i
arXiv:2608.12829v1 Announce Type: new Abstract: Multimodal Diffusion Transformers (MM-DiTs) have demonstrated remarkable text-to-image generation performance, surpassing traditional U-Net-based diffus
arXiv:2506.15577v2 Announce Type: replace Abstract: Estimating above-ground biomass (AGB) from terrestrial laser scanning (TLS) via quantitative structural models (QSMs) is highly accurate under leaf-
arXiv:2608.13186v1 Announce Type: new Abstract: Sketch-guided image inpainting provides intuitive structural control, yet real sketches often mix reliable global intent with locally crowded, displaced
arXiv:2608.12336v1 Announce Type: cross Abstract: A story premise is the creative spark from which a full narrative can grow. Yet LLM-based story generation has mostly emphasized later-stage planning,
Hey Folks, Some of you saw my Muse-Glimmer-30B SOTA line this week. I recently went all in, got a few more techniques hooked up to my pipeline, and re-quantized the 3.5 9B. And oh boy, did it demolish
“This nightmare will only cost you eleventy trillion dollars…” Wild that to hear tech people speculate that the growing AI backlash is some kind of “Chinese op” when, like, “we’re taking your job and
arXiv:2608.13495v1 Announce Type: new Abstract: Efficiently retrieving relevant clips from large-scale driving logs is essential for data curation, model development, and safety analysis. Structured a
arXiv:2608.12333v1 Announce Type: cross Abstract: Vision-language models must associate visual entities with textual attributes. Whether these associations or concept bindings remain stable when the l