Knowledge catalogue
arXiv:2606.28867v1 Announce Type: new Abstract: Creative Commons licenses dominate African NLP corpus releases, but their compatibility rules are rarely applied. CC-BY-SA and CC-BY-NC cannot be combin
𝗚𝗟𝗠-𝟱.𝟮 (the latest open weights model) is having an Enterprise moment, and it is not an exaggeration.🚀 🔥 We have been impressed by how strongly GLM-5.2 is pushing long-horizon performance .. not just
You can embed this model practically anywhere - like a chrome extension This is transformersjs + rampart for real-time PII removal in your browser (personal email still blurred) You can see I'm toggli
As token usage explodes, model choice becomes product strategy. Teams are already testing models like GLM-5.2 because they want frontier quality, better tokenomics, and more control over cost, data, a
arXiv:2606.27163v1 Announce Type: cross Abstract: I describe my solution to the LeHome Challenge 2026, an ICRA 2026 competition on bimanual garment folding. The system placed 1st of 62 teams in the on
arXiv:2606.27089v1 Announce Type: new Abstract: Modern image generation model rapidly grows their sizes to meet high-fidelity image synthesis. However, they gradually become unaffordable for their eno
A huge moment for open source AI - as token usage skyrockets across orgs, so do concerns over cost & data/vendor lock-in & necessity of a multi-AI strategy Keep an eye on @Lux_Capital portfolio cos @h
📣📣 Meet Qwen-AgentWorld — a native language world model that simulates 7 agent environments (MCP, Search, Terminal, SWE, Web, OS, Android) within a single model. Environment modeling is the training o
We open-source Qwen-AgentWorld-35B-A3B (MoE, 35B/3B active, 256K context) and AgentWorldBench. Two routes, one roadmap: 🔬 Build the simulator — scalable, controllable, surpassing real environments 🧠 I
arXiv:2606.21701v1 Announce Type: cross Abstract: Long-term records of the Martian atmosphere based on general circulation models and reanalysis of atmospheric state variables are important to underst
arXiv:2509.23340v4 Announce Type: replace-cross Abstract: Automatically assessing the credibility of online sources presents an invaluable tool for navigating today's information ecosystem. However, e
arXiv:2502.16584v2 Announce Type: replace-cross Abstract: Recent advancements in audio tokenization have significantly enhanced the integration of audio capabilities into large language models (LLMs).
arXiv:2606.09027v1 Announce Type: cross Abstract: Large Language Models enable flexible natural-language planning but remain unreliable in determinism-critical domains due to their probabilistic natur
one popular theory is that research paper alpha* and lab publishing ~died when researchers realized that instead of fighting with marketing depts they could simply walk out the door and get >$100m for
arXiv:2606.03504v1 Announce Type: cross Abstract: We present BaltiVoice, a 16.8-hour read-speech corpus for Balti (ISO 639-3: bft), a Tibetic language spoken in Gilgit-Baltistan, Pakistan, with no pri
arXiv:2606.02100v1 Announce Type: new Abstract: Transformer models dominate modern NLP, but efficient, language-specific models remain scarce. In Portuguese, most focus on scale or accuracy, often neg
arXiv:2510.21364v2 Announce Type: replace Abstract: Transformer models have revolutionized NLP, yet many morphologically rich languages remain underrepresented in large-scale pre-training efforts. Wit
📢 New @heyjasper release ! 📢 MONET 🌸 : An Apache2.0 deduped and recaptioned dataset of 105M samples unlocking reproducible text-to-image research. Nano T2I 🖌️ : A codebase to train your own T2I model
arXiv:2605.26874v1 Announce Type: cross Abstract: LLM-based agents for industrial asset operations show limited accuracy when reasoning over flat document stores. AssetOpsBench (KDD 2026) establishes
today was a massive day for protein engineering. esmfold2 dropped—next gen of the esm series, fully open on @huggingscience. 1.1 billion predicted structures, 6.8 billion sequences. 800m more entries
arXiv:2605.25645v1 Announce Type: cross Abstract: We present the first end-to-end demonstration of fine-tuning and serving Google's Gemma 4 31B model on TPU hardware, providing an empirical comparison
arXiv:2605.23918v1 Announce Type: cross Abstract: The AI inference industry keeps models loaded in GPU memory around the clock to avoid cold-start latency, implicitly treating idle power as a fixed co
arXiv:2605.23215v1 Announce Type: cross Abstract: LLM-based agents for GPU kernel generation are advancing rapidly, yet their progress is fundamentally constrained by the benchmarks they optimize agai
arXiv:2412.14642v4 Announce Type: replace Abstract: Recently, Large Language Models (LLMs) have demonstrated great potential in natural language-driven molecule discovery. However, existing datasets a
I'm excited about the new @amd Ryzen AI Halo because we need more local hardware for AI builders! There's something fun and exciting about building on your own machines rather than sending to the clou
On prem. I'm excited about the new @amd Ryzen AI Halo because we need more local hardware for AI builders! There's something fun and exciting about building on your own machines rather than sending to
✨ Personal AI is the next computing platform. AI is shifting from something you access to something you build with, locally, at the edge, and across systems. We’re unlocking new possibilities for deve
The future of biology shouldn’t stay behind black-box APIs. Especially when it touches personal health. Whether you’re @bryan_johnson measuring every biomarker, or @sytses openly sharing and analyzing
arXiv:2408.17352v2 Announce Type: replace-cross Abstract: Automatic Speaker Verification (ASV) systems, which identify speakers based on their voice characteristics, have numerous applications, such a
arXiv:2511.21016v3 Announce Type: replace-cross Abstract: Linear State-Space Models (SSMs) offer an efficient alternative to softmax Attention with constant memory and linear compute, but their lossy,
LTX-2.3 is Lightricks' latest open-source audio-video generation model natively supported in ComfyUI, delivering major quality improvements including enhanced details, portrait video support, and impr
okay maybe it's a good time? We have a small colbert model trained at pplx, it is a continue-training of pplx-embed-0.6b, so native multilingual, just made it open and added a section how to use MaxSi
arXiv:2601.19667v2 Announce Type: replace-cross Abstract: We present SynCABEL (Synthetic Contextualized Augmentation for Biomedical Entity Linking), a framework that addresses a central bottleneck in
you can see more here (color stuff is at bottom): http://colorfeelings.replit.app - changing embedding model may change results - the similarity range was pretty small so normalizing really stretched
Poolside is hosting a 2-day model research hackathon in London. Join us to push an open-weight agent model as far as you can. RL and fine-tune Laguna XS.2, our latest-generation model, on Prime Intell
arXiv:2605.09908v1 Announce Type: cross Abstract: Current approaches to detecting depression and anxiety from speech primarily rely on machine learning techniques that utilize hand-engineered paraling
Local open-weight AI on a laptop has been improving more than twice as fast as Moore's Law! Between May 2024 and May 2026, the most expensive MacBook Pro you could buy stayed at 128 GB of unified memo
arXiv:2601.19831v2 Announce Type: replace-cross Abstract: Neural scaling laws predict how language model performance improves with increased training inputs. While aggregate metrics like validation lo
New friend just arrived! Been counting the days 🤪 Hello World Reachy Mini 🦾 As easy & cool as Lego, seriously promising. Shipped an app to the Reachy Mini App Store in just a few hours! 👉https://huggi
arXiv:2605.04998v1 Announce Type: cross Abstract: Chord progression generation is practically important but understudied. Most large-scale symbolic music systems target melody, multi-track arrangement
HF leaderboards are fantastic, thank you @ClementDelangue @Thom_Wolf @NielsRogge for making a critical facet of benchmarks so easy! Check out http://swebench.com as well The SWE-bench Verified leaderb
arXiv:2605.03884v1 Announce Type: new Abstract: Multi-agent LLM systems on edge devices need to hand off latent context efficiently, but the practical choices today are expensive re-prefill or full-pr
arXiv:2601.06395v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly multilingual, yet open models continue to underperform relative to proprietary systems, with the gap m
arXiv:2507.13563v2 Announce Type: replace Abstract: We introduce Balalaika, an open-source, data-centric pipeline for processing audio and producing prosody-aware annotations. It combines semantic VAD
Introducing nanowhale 🐳! A tiny DeepSeek model fully pretrained by an agent. Inspired by @karpathy's nanochat, we gave ml-intern the task of training a tiny MoE with all the architectural advancements
arXiv:2601.17617v3 Announce Type: replace-cross Abstract: LLM-powered search agents are increasingly being used for multi-step information seeking tasks, yet the IR community lacks empirical understan
ml-intern is fully on mobile now you can launch 8 A100s from your phone. while on the couch. while commuting. wherever I just did this while biking. same sessions as your desktop too — start a run on
arXiv:2604.26130v1 Announce Type: cross Abstract: Every RLHF-trained language model is shaped by a reward model, yet the mechanistic interpretability toolkit -- logit lens, direct logit attribution, a
Today we’re releasing Qwen-Scope 🔭, an open suite of sparse autoencoders for the Qwen model family. It turns SAE features into practical tools： 🎯 Inference — Steer model outputs by directly manipulati
arXiv:2604.24971v1 Announce Type: cross Abstract: We present PolyKV, a system in which multiple concurrent inference agents share a single, asymmetrically compressed KV cache pool. Rather than allocat
new in ml-intern: you can now actually see what's going on inside added native metric logging + trackio integration. every training run the agent kicks off now has live curves you can watch in real ti
THIS GUY LOST 200 IN ONE DAY BECAUSE THE STRING 'HERMES.md' WAS IN HIS GIT COMMITS HERMES.md is a real convention used in AI agent projects. it's a system prompt specification file. not some obscure e
Local models do seem likely to create an explosion of new use cases. Local compute >> cloud compute. This is where we are right now. And i’m not gonna lie it feels pretty magical 🧚♀️ Qwen3.6 27B runn
Cloud-hosted models will become more niche/seldom-used as much cheaper local models fulfill that which 90% of consumers need from AI. Lots of models to buy/use, but very few hardware options upon whic
For the last 72 hours since ml-intern launched we have had over 500+ autonomous AI research projects running on the Space at all times. Some insane ones I saw: 1. A new AI paradigm from scratch — tryi
LLaDA2.0-Uni is a unified diffusion large language model (dLLM) based on Mixture-of-Experts architecture that seamlessly integrates multimodal understanding and generation. The model supports text-to-
pi gives you wings wherever you are This is where we are right now. And i’m not gonna lie it feels pretty magical 🧚♀️ Qwen3.6 27B running inside of Pi coding agent via Llama.cpp on the MacBook Pro Fo
This is where we are right now. And i’m not gonna lie it feels pretty magical 🧚♀️ Qwen3.6 27B running inside of Pi coding agent via Llama.cpp on the MacBook Pro For non-trivial tasks on the @huggingf
Hugging Face Releases ml-intern: An Open-Source AI Agent that Automates the LLM Post-Training Workflow [The 'AI Intern' that actually ships SOTA models ] This isn't just another ML Research Loop wrapp
OpenAI: OpenAI releases Privacy Filter, an open-weight model for masking personally identifiable information in text, with 1.5B total and 50M active parameters — Our state of the art model for masking