All entries

last week we dropped a super comprehensive guide on runtime requirements for long running agents! this week i'll be diving into each requirement and runtime capability that meets it, here's the lineup

Lately I've been having fun with running coding agents fully locally. The setup I landed on is: - Pi agent - Gemma 4 26B A4B - Server of choice: LM Studio/Ollama/llama.cpp I wrote a step-by-step guide

arXiv:2602.17681v2 Announce Type: replace-cross Abstract: Post-training quantization (PTQ) is a widely used approach for reducing the memory and compute costs of large language models (LLMs). Recent s

arXiv:2604.22050v1 Announce Type: cross Abstract: Transformers are mostly relying on softmax attention, which introduces quadratic complexity with respect to sequence length and remains a major bottle

arXiv:2604.22235v1 Announce Type: cross Abstract: Industrial robots are widely used in manufacturing, yet most manipulation still depends on fixed waypoint scripts that are brittle to environmental ch

arXiv:2604.22244v1 Announce Type: new Abstract: Ensuring safety for black-box hybrid dynamical systems presents significant challenges due to their instantaneous state jumps and unknown explicit nonli

arXiv:2604.22056v1 Announce Type: new Abstract: Optimal wireless transmitter placement is a central task in radio-network planning, yet exhaustive search becomes prohibitively expensive at scale. This

arXiv:2604.22565v1 Announce Type: cross Abstract: Large Language Models (LLMs) can reason well, yet often miss decisive evidence when it is buried in long, noisy contexts. We introduce HiLight, an Evi

arXiv:2508.10695v2 Announce Type: replace-cross Abstract: Personalization is crucial for enhancing both the effectiveness and user satisfaction of language technologies, particularly in information-se

arXiv:2604.22164v1 Announce Type: new Abstract: Recent advances in deep learning have enabled the generation of videos from textual descriptions as well as the prediction of future sequences from inpu

arXiv:2604.22363v1 Announce Type: cross Abstract: Household environments present one of the most common, impactful yet challenging application domains for robotics. Within household scenarios, manipul

arXiv:2510.12328v5 Announce Type: replace Abstract: Accurate rainfall forecasting, particularly for extreme events, remains a significant challenge in climatology and the Earth system. This paper pres

arXiv:2604.01907v2 Announce Type: replace-cross Abstract: Annotated 3D scene data is scarce and expensive to acquire, while abundant unlabeled videos are readily available on the internet. In this pap

arXiv:2604.22061v1 Announce Type: cross Abstract: Patient-trial matching requires reasoning over long, heterogeneous electronic health records (EHRs) and complex eligibility criteria, posing significa

Ivan Levingston / Financial Times: Lithuania-based Vinted says it completed an ~€880M secondary share sale led by EQT, Teachers' Venture Growth, Schroders at an €8B valuation, up from €5B in 2024 — Se

Llamacpp is a tool for running large language models locally on personal computers, offering free access without relying on cloud services. The technology emphasizes speed, security, and computational

arXiv:2604.02861v2 Announce Type: replace-cross Abstract: The integration of large language models (LLMs) with graph-structured data has become a pivotal and fast evolving research frontier, drawing s

arXiv:2411.08027v3 Announce Type: replace-cross Abstract: Most learning-based approaches to complex physical reasoning sidestep the crucial problem of parameter identification (e.g., mass, friction) t

arXiv:2601.08919v2 Announce Type: replace-cross Abstract: A good deal of recent research has focused on how Large Language Models (LLMs) may be used as judges in place of humans to evaluate the qualit

This post from Ollama highlights the collaborative nature of open-source software development, suggesting that the value of OSS projects lies not just in the code itself but in the community and relat

Loan processors spend 40–60% of their time reconciling income across tax returns, pay stubs, W-2s, and bank statements. We built an end-to-end pipeline that automates it with LlamaParse + the Claude A

arXiv:2604.22161v1 Announce Type: new Abstract: We study the K-armed logistic bandit problem, where at each round, the agent observes K feature vectors associated with K actions. Existing approaches t

Long list Scam Altman has a incredible track record for being a con artist I don't think anyone has a 'former ally turned enemy' list this big with directly with people he worked with A massive new 18

arXiv:2604.22714v1 Announce Type: new Abstract: Internet photo collections exhibit an extremely long-tailed distribution: a few famous landmarks are densely photographed and easily reconstructed in 3D

Looking forward to the work coming out of @IneffableLabs 🇬🇧 Largest EU/UK raise ever 😮 Beat the previous UK largest seed raise (101m Stability AI!) by 999m 🚀 We have seen amazing things on our self-le

arXiv:2604.22034v1 Announce Type: cross Abstract: Kolmogorov-Arnold Networks (KANs) are a recent neural network architecture offering an alternative to Multilayer Perceptrons (MLPs) with improved expl

arXiv:2602.09329v2 Announce Type: replace Abstract: Quality benchmarks are essential for fairly and accurately tracking scientific progress and enabling practitioners to make informed methodological c

arXiv:2604.21957v1 Announce Type: cross Abstract: Recent works have demonstrated that attention-based transformer and large language model (LLM) architectures can achieve strong channel state predicti

arXiv:2506.16494v3 Announce Type: replace Abstract: Electrocardiograms (ECGs) provide non-invasive measurements of heart activity and are established tools for detecting cardiac arrhythmias. Although

Last year we introduced new geospatial analytics capabilities integrated for BigQuery. Building on this, we announced an expanded suite of tools at Google Cloud Next ‘26, designed to help your busines

arXiv:2604.21935v1 Announce Type: new Abstract: Although language models demonstrate remarkable proficiency on mathematical benchmarks, it remains unclear whether this reflects true mathematical reaso

arXiv:2604.22503v1 Announce Type: new Abstract: Hundreds of millions of people use artificial intelligence (AI) for writing assistance. Here, we evaluated how AI writing assistance distorts writer per

arXiv:2512.05794v2 Announce Type: replace-cross Abstract: Sparse autoencoders (SAEs) are a mechanistic interpretability technique that have been used to provide insight into learned concepts within la

Legacy, launched in 2023, was a blockchain business simulator that raised $54 million via a virtual 'land sale' in 2021 , but tanked almost immediately after launching . Molyneux later stated that fun

arXiv:2604.22085v1 Announce Type: new Abstract: The transition from stateless language model inference to persistent, multi session autonomous agents has revealed memory to be a primary architectural

Riley Griffin / Bloomberg: Meta says it signed a deal with Overview Energy for 1GW of space solar energy; the startup seeks to collect sunlight in satellites, with a demonstration in 2028 — Meta Platf

OpenAI: Microsoft and OpenAI amend their deal to let OpenAI serve all its products across any cloud provider; Microsoft will no longer pay a revenue share to OpenAI — Amended agreement provides long-t

Aaron Holmes / The Information: Microsoft and OpenAI remove a clause that would have given Microsoft IP rights until OpenAI achieved “AGI”; Microsoft retains use of OpenAI's models until 2032 — Micros

OpenAI and Microsoft's partnership-turned-situationship just got even less committed. And a clause about artificial general intelligence, which has for years dictated the future of their deal, has off

Microsoft Corp. has partnered with Accenture Plc on the largest-ever deployment of its artificial intelligence tool Microsoft 365 Copilot, rolling it out to the consultancy’s global workforce of more

Microsoft's MIT licensed VibeVoice speech-to-text model (think Whisper with speaker diarization) is really good - my notes on running the 5.71GB 4bit MLX conversion on an M5 MacBook, using about 60GB

microsoft/VibeVoice VibeVoice is Microsoft's Whisper-style audio model for speech-to-text, MIT licensed and with speaker diarization built into the model. Microsoft released it on January 21st, 2026 b

Xiaomi released and open-sourced MiMo-V2.5-Pro, delivering significant improvements over its predecessor in agentic capabilities, complex software engineering, and long-horizon tasks. The model is an

arXiv:2604.22633v1 Announce Type: cross Abstract: The Gaussian mixture model is widely used in unsupervised learning, owing to its simplicity and interpretability. However, a fundamental limitation of

ml-intern from @huggingface is such a cool repository, an 🤖 agentic harness that allows you to wield the larger🤗ecosystem to run all the tasks a ml researcher would. it's all one can ask for as a side

ml-intern now notifies you when it needs input! Amazing for those 12h+ autonomous LLM training runs The ML Intern can now ping you on Slack when it's finished training models, generating datasets, or