
Adverb
@advadnoun
Followers
12K
Following
30K
Media
3K
Statuses
18K
RT @moultano: People should talk about games not just as good or bad, but in how much of the time they spent playing them that they wish th….
0
6
0
RT @joannejang: i think everyone in ai should think about what their "line" is. where if your company knowingly crosses that line and won'….
0
92
0
RT @dvsch: I didn’t make a bbvday this year because I was so busy with Phantoms, but I’ve been thinking about it for 6 months. With the rec….
0
1
0
Super good. "Vision" Language Models.
🚨 Our latest work shows that SOTA VLMs (o3, o4-mini, Sonnet, Gemini Pro) fail at counting legs due to bias⁉️. See simple cases where VLMs get it wrong, no matter how you prompt them. 🧪 Think your VLM can do better? Try it yourself here: 1/n.#ICML2025
2
0
6
RT @minimaxir: So this is *not* the OpenAI OSS model like I thought, as it has a 256k context window while the OSS model has a context wind….
0
1
0
We love a Borgesian title ♥️.
Introducing Runway Aleph, a new way to edit, transform and generate video. Aleph is a state-of-the-art in-context video model, setting a new frontier for multi-task visual generation, with the ability to perform a wide range of edits on an input video such as adding, removing
0
0
4
RT @keyonV: We propose a method to measure these inductive biases. We call it an inductive bias probe. Two steps:.1. Fit a foundation mode….
0
16
0
RT @MeidasTouch: NEW via CNN / @KFILE: Newly uncovered archived video footage and photos reveal fresh details about Donald Trump’s past rel….
0
401
0