Typhoon OCR is an open, lightweight vision-language model that reads Thai and English documents and returns clean, structured text.
Robots used to explore by following simple rules or short-term rewards, which often made them waste time and backtrack a lot.
XR is a new, training-free team of AI helpers that finds images using both a reference picture and a short text edit (like “same jacket but red”).
PRiSM is a new open-source benchmark that checks how well speech models hear and write down tiny speech sounds called phones.
Think3D lets AI models stop guessing from flat pictures and start exploring real 3D space, like walking around a room in a video game.
The paper studies how to make and judge scientific images that are not just pretty but scientifically correct.
This paper builds MemoryRewardBench, a big test that checks if reward models (AI judges) can fairly grade how other AIs manage long-term memory, not just whether their final answers are right.
The paper shows how to build tiny, fast safety checkers (called probes) that look inside a big AI’s brain activity to spot dangerous cyber-attack requests.
FrankenMotion is a new AI that makes human motion by controlling each body part over time, like a careful puppeteer.
This paper is the first big map of how AI can fix real software problems, not just write short code snippets.
Agent skills are like apps for AI helpers, but many of them are not carefully checked for safety yet.
The paper turns messy character descriptions from stories into neat, executable rules so role‑playing AIs act like the character in each specific scene.