#Research
Curated coverage on «Research»: releases, research, benchmarks, open-source.
OpenVLHarness Gives Multimodal Models Memory and Tools: +9.7–12.6 Points
OpenVLHarness, a harness with tools and persistent multimodal memory, lifted the average score of eight MLLMs by 9.7–12.6 points on 22 benchmarks, using at most 37%…
Stateful Harness Lifts World Model Accuracy on Hidden State from 32% to 92%
Researchers split rule execution from video rendering: Stateful Harness with a frozen MiniMax-H3 gets the correct outcome in 92% of WorldState-Bench pairs, versus…
Hybrid LLMs: Recurrent Layers Suppress Attention, and Staged Training Helps
Researchers describe Competing Learning: in hybrid models, recurrent layers learn retrieval faster and suppress attention. They tested staged training on models up…
SEAM teaches TTS new words without audio and cuts data needs by 75%
RouteWeaver teaches an LLM router to pick its own mode, reaching 61.4% accuracy
SpatialScout: Best VLM Agent Builds Only 41.71% of a Room's 3D Map
Omni-Woodpecker Cuts Hallucinations in Omni-LLMs Without Retraining: +12.9 on CMM
Reverse-engineering expensive websites with AI: why half of the web's 'complex 3D' can be assembled in two evenings
Impressive promo sites with complex lighting and volumetric graphics used to require a month and a half of design studio work plus a dedicated WebGL developer.
Google Unveils PaperOrchestra: An AI System That Writes Scientific Papers Automatically
Researchers have built PaperOrchestra, a multi-agent system that automates the hard work of turning rough notes and experimental data into a finished scientific…
Reasoning Drift in AI: How a Model Degrades While the Service Keeps Running
Stanford Online Posts Lecture 12 of AA274A: Classical Computer Vision for Robots
Claude Mythos Is Big Tech-Only, CaveMan Cuts Token Spend Threefold
Why Multimodal Models Can't See Web Interfaces
Regulators Sound the Alarm: Anthropic's Mythos Model Threatens Global Financial Stability
Anthropic's new Mythos AI model, built to find software bugs, has alarmed central banks. Experts fear it could undermine the resilience of banking infrastructure.
UK Regulator Lets Largest Banks Test AI in Real-World Conditions
The UK's Financial Conduct Authority (FCA) has picked Barclays, Lloyds and UBS for pilot trials of AI technologies in the country's banking sector.