All news
10613
Building AI Document-Processing Pipelines with LangExtract and OpenAI
A new guide walks through building pipelines that extract structured data from text using Google's LangExtract and OpenAI language models.
EgoX Merges Camera, Hands and Objects Into One 3D Scene, With 65.6% Lower Hand Error
From first-person video, EgoX reconstructs camera, scene, hands and objects in shared metric coordinates in a single pass. Camera error is 68.9% lower.
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%…
ActionRoPE Turns Player Actions into Coordinates and Cuts Scene Drift by 66%
Heartbeat Thinking Teaches Voice Agents to Work While You're Still Talking: Latency Down 36.4%
OpenDS-World: The Best AI Agent Solved 39% of Deep Search Tasks on the Live Web
SEAM teaches TTS new words without audio and cuts data needs by 75%
GPT agents lose up to 11.3 points of accuracy when the simulator report sits in a file
When PHREEQC's long output moves from context into a file, GPT-5.1 and GPT-5.2 answer worse by 11.3 and 7.9 points. Claude Opus 4.6 and Sonnet 4.6 show no drop.
VerifierBench: 19 LLMs Wrote Verifiers, and the Best Scored Only 62.1
A new benchmark tests whether agents can write their own code to check solutions. Across 222 tasks, 19 models scored 10.6 to 62.1, and the verifiers most often…
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
Researchers Explain How JEPA Selects Features: Relationships Matter, Not Lone Features
Reverse-engineering expensive websites with AI: why half of the web's 'complex 3D' can be assembled in two evenings
Google Unveils PaperOrchestra: An AI System That Writes Scientific Papers Automatically
Why Microsoft, OpenAI, and Anthropic Are Telling You Not to Trust Their Own AI
Sam Altman Responds to New Yorker Criticism After Attack on His Home
OpenAI CEO Sam Altman has published a response to a high-profile New Yorker article questioning his honesty, amid reports of an attack on his private property.
Fine-Tuning Gemma 4 with GPUs on Cloud Run: From 89% to 94% in Animal Classification
A complete breakdown of fine-tuning Gemma 4 on custom data in Google Cloud. An architecture with native support for video and audio, QLoRA quantization, and…