Knowledge catalogue
There are more document parsing models than ever, and they’re getting harder to tell apart. That’s why we built OpenDocRouter. Every model we serve is benchmarked on ParseBench, with latency and cost
arXiv:2610.11069v1 Announce Type: new Abstract: Large language model (LLM) assistants are being deployed to clinicians across health systems, and judgments about their readiness rest largely on benchm
arXiv:2610.10827v1 Announce Type: cross Abstract: Corrective feedback is among the best-evidenced drivers of second-language acquisition, yet corrections delivered during lessons rarely accumulate int
arXiv:2610.09070v1 Announce Type: cross Abstract: Multivariate ordinal data along with covariates are commonly collected in problems ranging from alignment of language models with human preferences, a
Hello llamas. I am posting this because I believe that, despite it being closed source models, the discussion will bring value to the local AI community. As many of you probably heard, GPT-6 Astra is
arXiv:2610.02741v1 Announce Type: new Abstract: Chain-of-thought (CoT) monitoring provides a promising approach for detecting undesirable model behavior. Looped language models (LoopLMs) repeatedly ap
arXiv:2610.03057v1 Announce Type: new Abstract: Relational foundation models are increasingly pretrained on synthetic databases, yet downstream benchmarks reveal little about why one synthetic corpus
arXiv:2610.00665v1 Announce Type: new Abstract: Background: Protein language models (PLMs) are increasingly used for sequence generation and property prediction, but their size makes fine-tuning and d
arXiv:2610.00416v1 Announce Type: new Abstract: Evaluating large language models becomes increasingly challenging as their capabilities advance: benchmarks can saturate, public test sets risk contamin
Something keeps happening in frontier AI, and the explanation we are given is always one size larger than the event. An OpenAI research model, running in a supposedly offline training environment, hit
arXiv:2609.36477v1 Announce Type: cross Abstract: Guard models are used as safety classifiers, with confidence scores driving downstream moderation decisions. We evaluate five guard models for prompt
arXiv:2609.30566v1 Announce Type: new Abstract: We present a new inference-time sampler for diffusion models that gives a pretrained model a capability it was never trained for: constructing the atlas
arXiv:2609.31199v1 Announce Type: cross Abstract: Large-scale Digital Surface Models (DSMs) can be produced cost-effectively from satellite images via stereo-photogrammetry. However, the resulting 3D
Financial Times: Mentions of open models in latest US earnings calls surged 6x YoY, with open models hitting 56% of Vercel tokens in August and 40% of AT&T's AI workloads — US businesses far beyond Si
AI grad student here. With all the recent interest in Jev, I thought I would share something I built la few months ago that brings ML models and LLMs together in a different way than Jev does for diff
OpenAI: OpenAI says it paused training, evaluation, and inference with tool-use of its most capable models after a model bypassed internet restrictions during training — Summary — An agent attempting
arXiv:2609.30264v1 Announce Type: new Abstract: Latent world models are typically trained to predict factual transitions, whereas model predictive control (MPC) must compare alternative actions from t
Note that this is an experimental model meant to show how you can train your own specialized decision models fairly easily! You can also check out the model weights here, along with the full tutorial
arXiv:2609.24209v1 Announce Type: new Abstract: The Platonic Representation Hypothesis (PRH) claims that independently trained models converge on a shared statistical model of reality, yet recent work
Vacations give you time to think and explore. I came across a few things and made a few discoveries of my own. It turns out that, as a programmer, I no longer need the smartest and most expensive AI m
arXiv:2609.15903v1 Announce Type: new Abstract: Discrete diffusion and flow models are a promising alternative to autoregressive language models, but compressing many-step sampling into fewer steps ty
arXiv:2609.13918v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used in specialized university courses, but control-systems questions require coordinated terminology, not
Governing models across accounts is the next step after automatic model registration. This post extends managed MLflow and Amazon SageMaker AI Model Registry sync to two cross-account governance topol
Hello everyone. I felt current LLM benchmark harnesses hand you headline numbers but offer no tooling to see how models actually answered each question (they dump everything to a JSONL or Parquet file
arXiv:2609.02163v1 Announce Type: new Abstract: Information-theoretic measures derived from autoregressive language models are widely used to characterize the expectations that shape human reading, bu
arXiv:2608.30022v1 Announce Type: new Abstract: Introduction: NICE guidelines provide evidence-based recommendations for clinical care but remain largely in unstructured natural language. Existing app
arXiv:2608.28929v1 Announce Type: cross Abstract: Large-scale diffusion models have fueled numerous profitable downstream applications for AI-related businesses, including visual editing and content c
arXiv:2508.16013v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly deployed in politically sensitive contexts, raising concerns about their susceptibility to ideological
arXiv:2608.25761v1 Announce Type: new Abstract: One common trade-off in the use of large language models involves reducing the size of the model while increasing the amount of computation at inference
arXiv:2608.25005v1 Announce Type: new Abstract: The imperfective paradox provides a useful test of compositional semantic analysis. Recent work constructs an NLI benchmark and reports that models freq
arXiv:2608.16931v1 Announce Type: new Abstract: Electroencephalography (EEG) foundation models have recently emerged as a promising paradigm for EEG decoding by learning reusable representations from
arXiv:2608.16507v1 Announce Type: new Abstract: Due to the limited amount of information, modeling longitudinal rare-disease data can benefit from integrating clinical knowledge. Yet, elicitation of e
arXiv:2608.14179v1 Announce Type: new Abstract: Large language models (LLMs) have shown remarkable reasoning and generative capabilities, motivating their use as universal reasoning engines for percep
arXiv:2608.13552v1 Announce Type: new Abstract: Video world models simulate future states conditioned on current observations and user actions. Recent systems have demonstrated impressive video consis
arXiv:2608.10120v1 Announce Type: new Abstract: Modern sequence models, from Transformers to State Space Models, have enabled powerful generative modeling across diverse domains, yet they are typicall
arXiv:2608.05168v1 Announce Type: new Abstract: Large language models often fail on reasoning tasks despite possessing the capability to solve them. We argue that many such failures arise from localiz
arXiv:2503.10367v2 Announce Type: replace-cross Abstract: Edge devices host domain-specific small language models (SLMs) with limited resources, while private clouds offer larger LLMs. We propose G-Bo
arXiv:2607.29274v1 Announce Type: cross Abstract: Claims that language models homogenise are usually measured against human judgements collected for the study, which makes the human side an artifact o
arXiv:2603.06828v2 Announce Type: replace-cross Abstract: We uncover a behavioral law of long-horizon vision-language models: models that maintain temporally grounded beliefs generalize better. Standa
Try Qwen3.8-Max on Hermes Agent and you will have to doubt on how much these open frontier models have caught up with frontier closed models. These new open models are insanely good. Meet Qwen3.8-Max:
arXiv:2512.15011v3 Announce Type: replace Abstract: Artificial intelligence (AI) increasingly generates the very content used to train future AI systems. This feedback loop can degrade model quality,
arXiv:2607.27178v1 Announce Type: new Abstract: State-of-the-art retrieval models increasingly rely on closed training data, creating a reproducibility gap. We present an open end-to-end recipe for tr
I’ve spent the past month trying to find the point where an extremely small TTS model stops feeling like a size experiment and starts feeling genuinely useful. Today I’m releasing Inflect v2, with two
Reuters: Sources: OpenAI's models breached Hugging Face from July 11 to 13 and OpenAI realized their models were behind the hack several days later — The OpenAI agent that broke into tech firm Hugging
arXiv:2502.16167v2 Announce Type: replace-cross Abstract: Diffusion models (DMs) have advanced text-to-image (T2I) synthesis, yet their personalization capabilities raise serious privacy and copyright
arXiv:2607.12796v1 Announce Type: cross Abstract: When a language model must pick one answer from a large space of equally valid options, which does it pick -- and how often is it the same answer ever
arXiv:2602.16918v2 Announce Type: replace-cross Abstract: We present Xray-Visual, a unified vision model architecture for large-scale image and video understanding trained on industry-scale social med
Better Models: Worse Tools Armin reports on a weird problem he ran into while hacking on Pi: The short version is that newer Claude models sometimes call Pi’s edit tool with extra, invented fields in
arXiv:2504.03711v2 Announce Type: replace-cross Abstract: Artificial intelligence (AI)-driven electronic design automation (EDA) techniques have been extensively explored for VLSI circuit design appli
arXiv:2607.01736v1 Announce Type: cross Abstract: We study how to predict the downstream closed-loop performance of a learned latent world model from validation-time diagnostics alone. Choosing the ri
arXiv:2607.00836v1 Announce Type: cross Abstract: World models are increasingly used in embodied intelligence and generative simulation, yet their scope remains ambiguous across communities. This tuto
arXiv:2606.28524v1 Announce Type: new Abstract: Recent work suggests that Large Language Models (LLMs) are sensitive to the belief states of agents described by text, as measured by the false belief t
Tired: The US government regulating open-source AI models Wired: The US government training and releasing open-source AI models Today, we are releasing Rampart: a 14.7MB machine learning model designe
When does combining LLMs help? Great analysis on combining language models, measured across 67 models from 21 providers. Any policy that routes, votes, cascades, or runs a mixture of agents and then r
Frontier models are getting really expensive Model providers give us a bunch of features to reduce costs, but the support landscape is….inconsistent We made prompt caching support model-agnostic in de
Transitioning from using a single video model to generate a clip to achieving a finished video is like the transition from coding models that merely autocomplete to coding models that write working so
arXiv:2606.24597v1 Announce Type: new Abstract: A world model predicts environment dynamics based on current observations and actions, serving as a core cognitive mechanism for reasoning and planning.
arXiv:2606.11074v1 Announce Type: cross Abstract: With the widespread deployment of Multimodal Large Language Models (MLLMs) in social interaction, understanding and controlling their behavior under c
arXiv:2606.09827v1 Announce Type: cross Abstract: Temporal modeling is essential for robotic manipulation, as effective control requires both memory of past interactions and imagination of future stat
arXiv:2606.04284v1 Announce Type: cross Abstract: Preference modeling plays a central role in reinforcement learning from human feedback (RLHF), enabling large language models (LLMs) to align with hum