The path to preventing rheumatoid arthritis
Identification of precursor immune system features and the beginning of clinical trials with this objective
RESEARCH
-
AI Identifies Precursor Immune Features for Rheumatoid Arthritis Prevention
By
–
-

Scaling Language Models with Infinite Compute via Ensemble Distillation
By
–
As data and compute scales differently, what do we do when we have infinite compute? To answer this, this paper shows you can still scale LMs by cranking up regularization, training many small clones on the same corpus, then ensemble → distill, netting 5x data-efficiency
-
Replicate shares detailed experiments blog post with results
By
–
You can read all our experiments in detail (including who we thought lost) in our latest blog post:
-

PrediBench: AI Models Profiting on Polymarket Benchmark
By
–
We're thrilled to introduce PrediBench, our first production at @presage_labs
! PrediBench a live benchmark that answers the question "could an AI model earn money on Polymarket?" TL;DR: Some models like Grok-4 or GPT-5 do beat the crowd of human betters, and they turn a profit! -
Problem Complexity and Human Baseline Improvements in RL Research
By
–
Cheers for taking a swing at it, but the problem is far from trivial, even if the final solutions are fairly compact code. Note that they upgraded the human baselines later. The Muesli paper has higher numbers than the original DQN paper.
-

Genome Editing T Cells Boost Cancer Immune Response
By
–
Elegant ways to rev up the immune system vs cancer keep expanding: Genome editing of engineered T cells https://
nature.com/articles/s4158
6-025-09507-9
… -

A2D-VL Diffusion Model Outperforms VLMs with Efficient Training
By
–
A2D-VL outperforms prior diffusion VLMs in visual question-answering while requiring significantly less training compute. Our novel adaptation techniques are critical for retaining model capabilities, finally enabling the conversion of state-of-the-art autoregressive VLMs to
-
Runway advances autoregressive-to-diffusion multimodal AI models
By
–
This work is a step towards our goal of unifying multimodal understanding and generation in order to build multimodal simulators of the world. Learn more: https://
runwayml.com/research/autor
egressive-to-diffusion-vlms
… -
VLMs Sequential Generation Limits Parallelization Efficiency
By
–
Standard Vision-language models (VLMs) reason about images and videos through language, powering a wide variety of applications from image captioning to visual question answering.
— Runway (@runwayml) 24 septembre 2025
Autoregressive VLMs generate tokens sequentially, which prevents parallelization and limits… pic.twitter.com/54ahfojDZuStandard Vision-language models (VLMs) reason about images and videos through language, powering a wide variety of applications from image captioning to visual question answering. Autoregressive VLMs generate tokens sequentially, which prevents parallelization and limits
-
A2D-VL 7B: Diffusion-Based Parallel Vision-Language Model
By
–
We trained a state-of-the-art diffusion VLM, A2D-VL 7B for parallel generation by finetuning an existing autoregressive VLM on the diffusion language modeling task, using the masked diffusion framework which "noises" tokens by masking them and "de-noises" tokens by predicting the… pic.twitter.com/zqU3szysQ1
— Runway (@runwayml) 24 septembre 2025We trained a state-of-the-art diffusion VLM, A2D-VL 7B for parallel generation by finetuning an existing autoregressive VLM on the diffusion language modeling task, using the masked diffusion framework which "noises" tokens by masking them and "de-noises" tokens by predicting the