Knowledge catalogue
arXiv:2610.17986v1 Announce Type: new Abstract: A common practice in instance retrieval is to grow the gallery size to improve a benchmark's discrimination capability. One prominent example is ILIAS,
NVIDIA RTX Spark is a new beginning for the PC — a reinvention combining the capabilities of a gaming PC, a creative studio and a personal AI supercomputer into a single superchip. With up to 128GB of
I'm a first year ML PhD at a T5 ML program in the US. I managed to get a first author paper accepted to NeurIPS Main Track last month and thought I'd start applying for PhD research internships since
The reality for most organizations is that data lives everywhere. As engineering teams expand and adopt specialized platforms for their workloads, enterprise data naturally disperses across multiple c
Grok @Bot rocks I've been using Grok @Bot as my daily driver for a few weeks now and: - it has replaced 100% of my search-like queries on chatgpt / claude - it has replaced 100% of my Hermes usage & a
So I wanted to try the horsey challenge myself on the latest engine i been testing which is a strata fork by sergqwer. https://github.com/sergqwer/strata-nvfp4. I seen a post earlier and seen i believ
Release: llm-gemini 0.35 I added support to llm-gemini for the new Gemini 4 Argon model, made available today via the Gemini API and for customers of their 100/month subscription plan. Here are the lo
I came across this blog post from OrcaRouter: https://www.orcarouter.ai/blog/qwen-3-8-next-vs-qwen-3-8 Not only is the blog post nonsensical in some parts, it's also completely without any value. It b
arXiv:2610.13669v1 Announce Type: new Abstract: Curriculum learning typically organizes training samples from easy to hard. In GRPO, medium-difficulty samples are attractive for online selection becau
arXiv:2610.13504v1 Announce Type: cross Abstract: Generative Recommenders increasingly use Reinforcement Learning (RL) to optimize outcomes that may appear hundreds or thousands of interactions after
arXiv:2610.13277v1 Announce Type: cross Abstract: Memory-augmented assistants retrieve evidence from stored conversations and documents to answer queries. Most embedding-based retrievers compare singl
tl;dr: Are there other models I should try? Is there something better than Kimi K3 for a code review? Is GLM-5.3 better at finding/patching security vulnerabilities? Are skills like https://github.com
Introducing RSI-Anything: Unlocking Recursive Self-Improvement with World Models 🚀 Can AI learn to improve itself by predicting the consequences of its actions? Built on JEPA-Anything, RSI-Anything us
🇫🇷 Le Chonk joins the sudo L7 leaderboard 🇫🇷 We just added @MistralAI's Mistral Large 4 to sudo L7, our benchmark for staff-level software engineering. Mistral Large 4 scores 13.3%, ahead of Muse Spar
arXiv:2610.13437v1 Announce Type: new Abstract: Anomaly detection, the identification of collision events that deviate from Standard Model expectations, is one of the most promising model-agnostic str
Microsoft Corp. today pulled back the curtains on Maia 300, its newest internally developed artificial intelligence accelerator. The chip is optimized for inference. Microsoft estimates that it can pr
Nvidia Corp. today announced new partnerships and contributions to the open-source community at the Open Compute Project Global Summit in San Jose, aimed at laying the foundation for the future of age
arXiv:2610.12802v1 Announce Type: new Abstract: A conversational speech model has to decide, at every pause, whether to speak. Existing evaluations test boundary detection, policy adherence, or aggreg
arXiv:2610.13557v1 Announce Type: new Abstract: Anticipation of vessel trajectories is an essential task when navigating at sea. This applies to both human navigators and autonomous surface vessels. T
Recommended NVIDIA paper on memory-efficient post-training RL. A very interesting technique for scaling RL for LLMs. The main takeaway is that you can update all of a model's weights with RL and still
arXiv:2610.03994v2 Announce Type: replace-cross Abstract: VeriContest is a benchmark of 1007 competitive-programming problems in Rust, each with a Verus specification, a judge-accepted solution, and a
Inspired by DigUp for macOS, VectorDash aims to be a full Windows 11 search replacement, powered by EmbeddingGemma 2. Full indexing: search by meaning or exact words across photos, screenshots, audio,
We need a name for the kind of people that conflate 2022 pure LLMs that were in fact a tiny bit like stochastic parrots (not my phrase, and not one I ever endorsed) with 2026 systems that couple those
Financial institutions are adopting artificial intelligence faster than many compliance teams can establish the controls needed to oversee it. That gap is raising new questions about AI-powered compli
Summary of project status metrics Since StillDeadcode has released his new radiance inference engine, the writing is on the wall for the old vllm-radiance builds, people have moved on to newer and bet
I run local LLMs pretty much around the clock, but I also enjoy gaming on the same PC. Having models sitting in VRAM while gaming isn't exactly ideal, and constantly unloading and reloading them manua
There is a lot of discussion which quant to use. Especially a lot of post how much speed you gain with FP4, but not much about quality. So i tested some of the models that I use on my R9700. Models: Q
I stumbled across this as I was currently having glm5.3 flash run only around 10tok/s basically unusable. With Maya i am running 30 tok/s now. GLM5.3 feels even with this low quant like a much more en
webAI released TwIL LM3 Pro on September 30. I haven't seen it posted here yet, so I went through the model card, and their comparison chart is attached. It's a 3.66B model built on IBM's Granite 4.2
For what it's worth. I'm a mechanical engineer by education and software engineer in practice over the past ~20 years. Playing around with local models has been a recent hobby. Today I decided to do a
I wanted to compare gemma 4 31b qat q4 and qwen3.8 27b iq4_nl, so I run SWEBench verfied on them. The original gemma 4 chat template doesn't work with preserve reasoning, so google released an update
Hi All: I have an Asus ESC 4000 G3 with 128 GB DDR4 RAM - I tried putting in my V620s but couldn’t put more than 2. Sadly, pivoted to T4s, these are 72 watt passive cards and I thought I could use the
Strata vs Infernix on the same model, RTX 5090 — A/B at 262k and 512k context Hi folks, another inference engine post for your feed. I was blown away by Strata, but saw someone else post about Inferni
I am developing a Windows-based local AI virtual spouse application that supports adult roleplay. My goal is to run it without a server or external AI APIs. I am looking for existing open-source modul
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:2610.11140v1 Announce Type: cross Abstract: Clinical diagnosis is inherently sequential: clinicians escalate from cheap to costly tests only when additional evidence is expected to resolve diagn
arXiv:2610.10926v1 Announce Type: new Abstract: Managing machine learning workloads as a network service introduces a resource-orchestration problem distinct from conventional model training; which no
Claude Malhuret Was Right about Trump. On Friday, at Trump's direction, the US Treasury issued a license waving Russian diesel back onto the world market, days after Russia killed dozens of Ukrainians
arXiv:2610.12431v1 Announce Type: new Abstract: Diffusion models can represent complex, multimodal trajectory distributions, but extracting uncertainty from them typically requires costly Monte Carlo
arXiv:2506.06410v4 Announce Type: replace-cross Abstract: We introduce Delphos, a deep reinforcement learning framework for assisting discrete choice model specification process. Delphos aims to suppo
For those of you who have been wanting to utilize your dual Spark cluster for image/video gen with ComfyUI - today is your day. I started this personal project back in April of this year, and it’s at
arXiv:2610.11310v1 Announce Type: new Abstract: While 3D spatial reasoning in dynamic egocentric environments is crucial for embodied intelligence, audio-visual large language models (AV-LLMs) lack ex
arXiv:2610.12230v1 Announce Type: cross Abstract: Text prompting is an indirect interface for poster generation, requiring users to encode inherently two-dimensional composition intent into a one-dime
Disclosure: I work at H2O.ai. We released H2O-Lightning-4B, an open-weight (Apache-2.0) model for the 'decisions API' style of inference that Jev made popular: you send a state plus typed questions (p
arXiv:2610.10633v1 Announce Type: cross Abstract: Screening in systematic reviews (SRs) is manual and time-consuming. Prior work has explored large language models (LLMs) for automating this step, but
arXiv:2610.08966v2 Announce Type: replace Abstract: Humans perceive far more in a scene than what is explicitly depicted: a single glance captures past causes and future trajectories; a quick peek det
arXiv:2606.18810v2 Announce Type: replace-cross Abstract: Reinforcement learning with verifiable rewards (RLVR) has driven substantial progress in training LLMs for reasoning tasks, but representative
In the dawn of the LLM craze, when wild Llama2's roamed free and 4k tokens was considered a fairly long context for local models, I forked an interactive fiction and MUD library called Tale to experim
arXiv:2610.11264v1 Announce Type: new Abstract: Given the inherent unpredictability of packet loss in vehicular wireless communications, V2X collaborative perception can yield practical benefits only
arXiv:2610.11312v1 Announce Type: new Abstract: Large-scale construction of medical vision-language model (VLM) benchmarks is increasingly feasible with richly annotated imaging datasets and large lan
arXiv:2610.12081v1 Announce Type: new Abstract: Continuing the Perception Test challenge series, we organised the fourth edition as a workshop at the European Conference on Computer Vision (ECCV) 2026
Referring to specifically Unsloth's UD_Q4_K_XL quant because that's going to be a question, and is relevant regardless. It's old now. It's not great at coding medium sized or even small-ish projects.
Hello all! Thank you to everyone that contributed their feedback and notes for LlamAmpere the last time I posted. I've continued to chip away at improvements for the 3090 crowd -- this release is mode
arXiv:2610.11183v1 Announce Type: cross Abstract: Following retrieved evidence does not guarantee factual correctness: misleading evidence can induce a model to replace an answer it previously gave co
arXiv:2610.11146v1 Announce Type: new Abstract: Cold-start credit scoring -- deploying models with scarce labeled data, weak features, or minimal capacity -- is a recurring problem in financial machin
ik ik 'another harness D:'. so... i spent the last 6 months of my life building and ironing out every single detail and bug through almost every route with extensive testing across 3 machines, daily,
arXiv:2610.12185v1 Announce Type: new Abstract: Reliable robotic manipulation requires timely intervention to correct emerging deviations and restore progress after execution errors. However, recovery
arXiv:2610.12424v1 Announce Type: cross Abstract: A generalist robot should not only perform diverse tasks but also improve through experience, turning what it learns during execution into capabilitie
Rashi Shrivastava / Forbes: Sabi, which is building a baseball cap that uses 100K non-contact neuro-sensors to convert neural signals into text prompts for AI systems, raised a $50M seed — Palo Alto-b