Knowledge catalogue
arXiv:2604.08036v1 Announce Type: cross Abstract: This paper addresses the problem of training a reinforcement learning (RL) policy under partial observability by exploiting a privileged, anytime-feas
arXiv:2502.02514v5 Announce Type: replace Abstract: Image AutoRegressive generation has emerged as a new powerful paradigm with image autoregressive models (IARs) matching state-of-the-art diffusion m
arXiv:2604.06912v1 Announce Type: cross Abstract: MLLMs require high-resolution visual inputs for fine-grained tasks like document understanding and dense scene perception. However, current global res
A factual description for this entry would be: This model is a base version of Qwen 3.5 with a 4-billion parameter count, optimized using ZitGen techniques. It is likely used for supplementary or f...
arXiv:2604.07882v1 Announce Type: new Abstract: Reconstructing non-rigid objects with physical plausibility remains a significant challenge. Existing approaches leverage differentiable rendering for p
arXiv:2604.07298v1 Announce Type: cross Abstract: Multiple Instance Learning (MIL) is the dominant framework for gigapixel whole-slide image (WSI) classification in computational pathology. However, c
arXiv:2604.06247v1 Announce Type: cross Abstract: Large Language Models (LLMs) and Vision-Language Models (VLMs) remain highly vulnerable to textual and visual jailbreaks, as well as prompt injections
arXiv:2604.07098v1 Announce Type: new Abstract: Large language models often fail on tasks they seem to already understand. In our experiments, this appears to be less about missing knowledge and more
arXiv:2604.06389v1 Announce Type: new Abstract: Uncertainty estimation for reasoning language models remains difficult to deploy in practice: sampling-based methods are computationally expensive, whil
arXiv:2604.06265v1 Announce Type: new Abstract: Quantum-inspired tensor networks algorithms have shown to be effective and efficient models for machine learning tasks, including anomaly detection. Her
arXiv:2604.06482v1 Announce Type: cross Abstract: Time-resolved volumetric MR imaging that reconstructs a 3D MRI within sub-seconds to resolve deformable motion is essential for motion-adaptive radiot
arXiv:2511.11663v2 Announce Type: replace-cross Abstract: The emergence of accurate open large language models (LLMs) has sparked a push for advanced quantization techniques to enable efficient deploy
arXiv:2604.03647v2 Announce Type: replace-cross Abstract: In the unsupervised self-evolution of Multimodal Large Language Models, the quality of feedback signals during post-training is pivotal for st
arXiv:2604.06375v1 Announce Type: new Abstract: AI-driven symptom analysis systems face persistent challenges in reliability, interpretability, and hallucination. End-to-end generative approaches ofte
arXiv:2604.06377v1 Announce Type: cross Abstract: We investigate whether post-trained capabilities can be transferred across models without retraining, with a focus on transfer across different model
The pace at which useful things are shipping also seems to be accelerating. Model releases are coming faster, of course, but so are significant application and enterprise products (especially from Ant
The power of JAX Introducing gyaradax 🐉: A JAX solver for local flux-tube gyrokinetics with custom CUDA kernels for acceleration. This entire code was vibecoded by @ggalletti_ and me in a month. Valid
arXiv:2604.06754v1 Announce Type: new Abstract: I examine the technology of machine learning from the perspective of rhetoric, which is simply the art of persuasion. Rather than being a neutral and 'o
arXiv:2604.06420v2 Announce Type: cross Abstract: In recommender systems, collecting, storing, and processing large-scale interaction data is increasingly costly in terms of time, energy, and computat
arXiv:2509.08016v2 Announce Type: replace Abstract: Video Large Language Models (VideoLLMs) face a critical bottleneck: increasing the number of input frames to capture fine-grained temporal detail le
Want to know the latest from Google Cloud? Find it here in one handy location. Check back regularly for our newest updates, announcements, resources, events, learning opportunities, and more. Tip: Not
(1/5) FP4 hardware is here, but 4-bit attention still kills model quality, blocking true end-to-end FP4 serving. To fix that, we propose Attn-QAT, the first systematic study of quantization-aware trai
Editor’s note: This blog post outlines Google Cloud’s GPU AI/ML infrastructure reliability strategy, and will be updated with links to new community articles as they appear. As we enter the era of mul
*AI Systems Performance Engineering* by Chris Fregly is a ~1,000-page book (published December 2025) covering GPU/CUDA kernel tuning, PyTorch optimization, distributed training, and high-throughput...
llama.cpp release **b8737** is a focused maintenance build that adds missing CUDA error handling to the ggml backend. Specifically, it checks the return values of NVIDIA CUB library calls used in t...
Ray Day Seattle (April 9, 2026) was an Anyscale event where ML engineers from Notion, Uber, Salesforce, and Apple shared real-world experiences scaling AI infrastructure with Ray. Notion highlight...
The specific tweet at that URL (status ID 2042079804271313343) could not be directly retrieved. However, based on the available context about Ben Golub's recent X/Twitter activity around Refine.ink...
Transformers.js, a library that enables running state-of-the-art Hugging Face machine learning models directly in the browser with no server required, has experienced explosive NPM download growth ...
This post shows you how to manage FM transitions in Amazon Bedrock, so you can make sure your AI applications remain operational as models evolve. We discuss the three lifecycle states, how to plan mi
Waypoint-1.5 is Overworld's updated real-time generative world model, trained on nearly 100x more data than its predecessor to deliver improved visual fidelity and environmental coherence. It intro...
We should view the history of physics as a long-running program synthesis task. Kepler and Newton were searching the space of possible symbolic models to find the simplest one that would best satisfy
An AI cow collar just created a billion-dollar company. Farmers draw boundaries on a phone app, and the collars guide cows using sound and vibration. It works by collecting over 6,000 data points per
Common Failure Modes Break VLM-Powered OCR in Production. 🔁 Repetition Loops — model spirals into infinite whitespace, exhausts resources, cascades latency across your system 🛑 Recitation Errors — saf
Google's Gemma 4 is pretty wild. You can now run it locally with OpenClaw in 3 steps. 1. Install Ollama 2. Pull Gemma 4 model 3. Launch OpenClaw with Gemma as the backend Private local AI agents in mi
We're seeing even more autonomous AI coworkers. The new MLE agent on the market is Disarray. In Kaggle competitions, Disarray: - won 28 medals across diverse domains (vision, NLP, tabular data) - plac
the current fear is is that AI homogenizes culture and turns humans into passive consumers one counterpoint: in Go, human play showed very little improvement from 1950 to 2016 until alphago beat lee s
Hi r/LocalLLaMA. I'm on the team at Blockway (disclosure: this is our model). Two weeks ago we posted the Volundr 32B Preview here, and you were blunt about what was wrong with it. This is v1, and mos
So I created this simple test (for myself) to see how good the new models are in analytic output. This is not asking them to draw a SVG (which just tests how much SVG or HTML they saw) but creating a
Qwen4s are hopefully coming pre-Xmas… there was all the announcements recently but no exact release date. I’m running qwen flash next 3.8 at about 28tokens per second and gotta be real, most of those
ui : Discover & Download Models from HF Hub (#29584) common : resolve - download tags and list cached sidecars A Q4_0-mtp style tag now resolves the sidecar file when no model file matches it, so a so
Great paper from NVIDIA sharing an open midtraining recipe for agentic coding. NVIDIA kept SFT identical and added one midtraining stage. SWE-bench Multilingual went from 55.8 to 62.8 on Nemotron 3.5
European 78B A3.4B model is now supported by llama.cpp, I am waiting for some GGUFs https://huggingface.co/Aleph-Alpha/Kolibri-1 Kolibri is Aleph Alpha's mixture-of-experts (MoE) reasoning model, with
Must-read paper integrating decision models like Jev into harnesses. They distilled an open 4B decision model, mostly from Jev's answers on the agent's own states, that beats Jev inside that agent and
**Ollama Cloud** provides a cloud-hosted model serving platform that *never retains user data* ('zero data retention') and does **not train on any incoming data**. The infrastructure is distributed ac
🔓 Open-source release Get DeepSeek-V4.1-Flash-1017: 🤗 Hugging Face: https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash-1017 🔗 ModelScope: https://modelscope.cn/models/deepseek-ai/DeepSeek-V4.1-Fla
Following a recent interesting post that challenges the performance of higher vs lower quants and generally advised sampling parameters (namely temp), I decided that I had too much free time on my han
arXiv:2610.21616v1 Announce Type: new Abstract: Medical segmentation uncertainty is often evaluated with calibration error or pixel-level error-detection scores, but these metrics do not show whether
arXiv:2610.21085v1 Announce Type: cross Abstract: An ensemble of language models is a jury, not an electorate. The answers are testimony from witnesses of unknown reliability, and the question is not
arXiv:2610.22065v1 Announce Type: new Abstract: Transformer-based models have become the backbone of a wide range of tasks, but their intensive computation and data movement incur substantial energy o
arXiv:2610.22328v1 Announce Type: cross Abstract: Image editing models produce impressive results for individual edits, but their quality often deteriorates over multiple editing turns. Each editing t
arXiv:2602.05273v2 Announce Type: replace Abstract: Enabling robots to explore and act in unfamiliar environments under ambiguous human instructions by interactively identifying task-relevant objects
arXiv:2610.21538v1 Announce Type: new Abstract: The Agent Status Protocol (ASP) defines a lightweight way for heterogeneous AI agents to report their operational state to a status server, and for obse
arXiv:2610.22298v1 Announce Type: cross Abstract: Large language models (LLMs) can generate differential diagnoses for complex cases, but a useful second opinion must also be factually grounded, clini
arXiv:2606.17090v2 Announce Type: replace-cross Abstract: ANEForge is a Python package that programs the Apple Neural Engine (ANE), the fixed-function neural accelerator on every recent Apple device,
arXiv:2610.22191v1 Announce Type: cross Abstract: In Hebbian learning from examples a Hopfield network of N neurons is not supplied with the K archetypes it has to retrieve but with M blurred examples
arXiv:2610.22263v1 Announce Type: new Abstract: Reinforcement learning has become a widely used approach to post-training large language models. In a typical implementation, learning is off-policy: Th
Beautiful work from @perplexity_ai @AravSrinivas with weights on @huggingface of course! https://huggingface.co/perplexity-ai/pplx-decider-flash-v1.2 https://huggingface.co/perplexity-ai/pplx-decider-
arXiv:2610.21006v1 Announce Type: new Abstract: To use language models to help us make decisions we would like to understand the rationale behind the language model's outputs. In principle, the langua
arXiv:2610.21151v1 Announce Type: cross Abstract: Cybersecurity interviews uncover critical security experiences, behaviors, and privacy concerns often not fully captured by conventional technical ass
arXiv:2610.20750v1 Announce Type: new Abstract: Vision-language-action (VLA) models are a promising approach to general purpose robot manipulation. While the internal computation of vision-language mo