Knowledge catalogue
What it is. stuntd is a local proxy for typed LLM decisions: choice, yes/no, score. Your app keeps calling its provider through it. stuntd records the decisions, trains a small head on top of Laya (th
arXiv:2609.25755v1 Announce Type: new Abstract: Applying large language models to Traditional Chinese Medicine (TCM) prescription generation reveals three clinically critical gaps: models produce end-
arXiv:2609.24025v1 Announce Type: new Abstract: We present a method for synthesizing reactive character behaviors for continuous games as compact, human-readable programs. Game AI practice still relie
arXiv:2609.23889v1 Announce Type: cross Abstract: Automated kernel vulnerability reproduction is essential for bug triage, patch validation, and regression testing, but still lacks an effective and ef
arXiv:2609.25356v1 Announce Type: new Abstract: Large language models (LLMs) offer great potential to automate a broad range of telecom engineering tasks by reasoning over standards, network configura
arXiv:2609.25482v1 Announce Type: new Abstract: Large language model (LLM) pretraining conventionally returns the raw final iterate. This couples two design choices: the learning-rate schedule that ge
arXiv:2609.24012v2 Announce Type: new Abstract: Validation of generative social simulators often stops at face validity: emergent network structure is compared descriptively, without quantified parame
Thanks @arena for the recognition! 🏆 Qwen-Image-2.1 is now the #1 open-source model in both the Image Edit and Text-to-Image Arenas. Try it now and show us what you create! 🎨 Qwen-Image-2.1 by @Alibab
arXiv:2609.24555v1 Announce Type: new Abstract: We introduce the Endless Exam, a benchmark for measuring mathematical progress from today's models toward artificial superintelligence through fourteen
The new Gemini 3.8 TTS models are super-cheap and can generate conversations between multiple voices (from 2,000+, or you can clone your own) - I built a little UI for it, then had Claude knock up a s
The sad thing is that Dario knows better. He was a PhD student. He knows the significance level of this result. He knows that if he had walked into Bill’s office (his advisor) with “we found an intere
arXiv:2609.26718v1 Announce Type: new Abstract: Long-context LLMs focus on retrieving distant evidence from extensive context, yet existing work has largely focused on overcoming distance alone. In th
arXiv:2609.26233v1 Announce Type: new Abstract: Text-to-video (T2V) services inherit their safety stack from image generation, pairing a keyword prompt filter with a per-frame checker that blocks a cl
There are countless CRISPR-like sequences hidden in genomes of many organisms (eg @Basecamp_Res). Well-known. Vast majority not interesting. This isn’t a noteworthy discovery. The hype level leads me
There’s an enormous amount of open training data on Hugging Face. What does it take to make it work together 🤗? For Marin’s 535B run, we built on 25T tokens from 152 datasets with licenses permitting
this is a new type of post we're trying where we share in-depth about how we do work using specific prompts and techniques you should be able to replicate let us know if it's useful or if you have any
This is both fun and a useful measure of how much better multimodal AI has gotten In a short time. Can AI tell if you've built your IKEA furniture wrong? Our new benchmark, the Furniture Assembly Benc
arXiv:2609.23363v1 Announce Type: new Abstract: Recent advances in large language models (LLMs) have led to the emergence of coding agents capable of performing complex engineering tasks, including re
arXiv:2609.24677v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used to make predictions from numerical time-series histories and textual events. Yet accuracy alone canno
Today we announced the Claude-led discovery of a molecular machine that we suspect could represent a new gene editing mechanism. Its precise function, biotechnological utility (if any), or level of si
arXiv:2609.26189v1 Announce Type: new Abstract: Retinal vessel segmentation in multi-domain deployment requires a source model to adapt to domains that differ in imaging conditions and annotation conv
arXiv:2609.23790v1 Announce Type: new Abstract: Every node in a multi-agent large language model (LLM) workflow retrieves context from memory and injects it into its prompt, where those injected token
arXiv:2609.22694v1 Announce Type: new Abstract: Public crash databases increasingly support automated safety analysis, but crash severity prediction remains difficult to translate into public-sector d
arXiv:2609.26063v1 Announce Type: new Abstract: Federated graph learning (FGL) enables multiple clients to collaboratively train graph models without sharing their private graph data, providing a prom
arXiv:2609.26168v1 Announce Type: cross Abstract: Recent work reports that vision--language models (VLMs) struggle to establish and maintain stable reference in repeated reference games. Rather than a
arXiv:2609.25008v1 Announce Type: new Abstract: I pretrained a language model end-to-end in Rust - alone, with no team, no PyTorch, and no Python in the training path - for $164 in rented GPU time. I
arXiv:2609.25237v1 Announce Type: cross Abstract: Post-training is becoming a service (PTaaS): a customer hands an operator data and a goal, and a forward-deployed engineer (FDE) returns a fine-tuned,
arXiv:2510.10211v4 Announce Type: replace Abstract: Molecular graph generation (MGG) is essentially a multi-class generative task, aimed at predicting categories of atoms and bonds under strict chemic
arXiv:2609.26314v1 Announce Type: new Abstract: Embodied world models predict the outcomes of robot actions to support learning and planning. For robots equipped with head and wrist cameras, this requ
arXiv:2609.26035v1 Announce Type: new Abstract: Conversational agents often express answers in a uniformly confident register. We test whether expressed uncertainty, provenance-aware assertion, and ex
arXiv:2609.26100v1 Announce Type: new Abstract: Speculative decoding accelerates large language model inference through collaboration between a lightweight draft model and a target verifier. Existing
arXiv:2609.25864v1 Announce Type: cross Abstract: Visual object removal can eliminate a target from video frames, yet its acoustic trace persists in the soundtrack, causing obvious audio-visual incons
arXiv:2609.25081v1 Announce Type: new Abstract: We describe ufakzeka-1, a 151M-parameter (182M with embeddings) decoder-only Turkish language model pretrained from scratch on 13.5B tokens of openly li
arXiv:2609.25932v1 Announce Type: new Abstract: 2D point cloud registration arises in laser odometry and Simultaneous Localization and Mapping (SLAM) for mobile robots. Iterative Closest Point (ICP) i
What's Changed server: fix intermittent 'model not found' errors. by @rick-github in #18438 server: apply structured outputs in a single pass on thinking models by @jessegross in #18479 app: avoid Sys
Overview This release focuses on backend performance and correctness, broader model coverage, and more robust server/router operation. It adds HRM-Text (DFM Mimir 1B) support, MiMo-V2.6 and HunyuanOCR
arXiv:2609.25145v1 Announce Type: cross Abstract: Variational autoencoders (VAEs) offer an efficient approach to amortized Bayesian inference for inverse problems, but posterior accuracy can depend st
arXiv:2602.13217v2 Announce Type: replace Abstract: Reasoning benchmarks need renewal along two axes: freshness and headroom. VeRA makes both executable and auditable by turning each item into a task
Saw a new open 27B model release that looks like it could be interesting for the Ollama crowd: VeriLoop E2. It is a Qwen3.8-27B post-train aimed at code, mathematics, scientific reasoning, and agentic
arXiv:2602.18307v2 Announce Type: replace-cross Abstract: Large language models have achieved striking results in interactive theorem proving, particularly in Lean. However, most benchmarks for LLM-ba
arXiv:2609.25773v1 Announce Type: new Abstract: HopChain has shown on still images that multi-hop data synthesis improves vision-language reasoning, because long chain-of-thought reasoning exposes err
arXiv:2609.26084v1 Announce Type: new Abstract: The integration of Vision-Language Models (VLMs) in autonomous Unmanned Aerial Vehicles (UAVs) offers unprecedented semantic reasoning capabilities. How
arXiv:2609.25376v1 Announce Type: new Abstract: Post-training quantization reduces the memory requirements of vision-language-action (VLA) models, but precision selection must account for the interact
arXiv:2609.24362v1 Announce Type: new Abstract: Sandboxed computer environments support multi-step reasoning with tools, executable programs, and persistent files, yet their extension from language mo
arXiv:2609.26204v1 Announce Type: cross Abstract: When a professional web developer's code fails a test, they do not simply re-read the stack trace. They open the application in a browser, click butto
We heard you loud and clear. ChatGPT Voice can now: - Use plugins like your email, calendar, and Slack. - Be powered by GPT-6 Astra, Sol, and Luna. - Be used in ChatGPT Work on web and mobile, so you
The post explains how a team accelerated Claude.ai’s performance by an average of three‑fold within two weeks. They leveraged the Claude model itself for end‑to‑end measurement, debugging, and iterati
We’re demonstrating how frontier models have continued to improve in realistic mental health conversations with MentalHealthBench. This new open benchmark was built with input from more than 80 mental
We’re launching Gemini 3.8 Flash TTS and Gemini 3.8 Flash-Lite TTS ⚡️ Our most expressive audio models yet let you create custom voices across 100+ languages or pick from 2,000+ ready-to-use ones. You
We’ve set up a molecular biology lab at Anthropic and we’re announcing our first discovery! Claude discovered a new CRISPR-like enzyme. 950 agents spent 21 hours searching through a database of DNA se
arXiv:2609.25006v1 Announce Type: new Abstract: Text classifiers trained on the ISOT/Kaggle 'Fake and Real News' corpus routinely report accuracy and F1 above 0.98, a level of performance that sits un
arXiv:2609.12708v2 Announce Type: replace-cross Abstract: AI coding assistants are becoming co-authors of production software, yet their evaluation centers on functional correctness, leaving open whet
In September 2026 user josh @eudaemonea shared that after Anthropic released its Functional Emotions paper he fed it into Claude and requested a song based on the research. Later that night he prompte
arXiv:2609.26705v1 Announce Type: cross Abstract: A fundamental question in physics is: When does classical behavior emerge from quantum systems? Bosonic Gaussian states provide a natural setting to e
arXiv:2609.25793v1 Announce Type: new Abstract: Zero-shot multimodal anomaly detection commonly assumes that RGB and point cloud modalities are equally reliable and can contribute uniformly to anomaly
arXiv:2603.02266v2 Announce Type: replace-cross Abstract: Test-Time Scaling has shown notable efficacy in addressing complex problems through scaling inference compute. However, within Large Audio-Lan
arXiv:2609.22910v1 Announce Type: new Abstract: Vision-language agents that crop and zoom are trained with rewards that credit a successful tool call, yet a successful call does not show that the mode
arXiv:2609.23665v1 Announce Type: cross Abstract: Constraint-following music generation asks a score to satisfy several user-specified properties at once, each checkable programmatically (key, meter,
I've been comparing and working on Gemma 4, Phi-4-Mini, and Qwen3-4B for local LLM use on an 8 GB Raspberry Pi 5. The results were indeed close, but each model has a different strength: Gemma 4 E2B: a
arXiv:2609.24094v1 Announce Type: cross Abstract: Visual analytics (VA) enables sensemaking through interactive visualization, but effective analysis often requires experts to translate high-level int