Loading activity…
Assistant Prof @CIS_Penn and Staff ML Researcher at @Apple (MLR) | ex-FAIR | PhD @HKUniversity | Research on Generative AI & World Models. また、日本語もできます。
AI
According to thoma_gu, OmniGuide steers a frozen robot model using vision-language models, geometry and human guidance.
AI
Pika’s seven-second benchmark measures transformer computation for a 15-second 768p clip, not total API request time.
YouTubeAI
The post pitches a “play it, rebuild it” approach and says users can train one agent or a whole team.
XAI
The author says their first-year PhD student at Penn leads the effort and sees it as a step toward physical AI.
AI
A researcher describes Normalizing Trajectory Models as a step toward high-quality few-step generation with exact trajectory likelihood.
AI
The author says their blog maps 16 overlapping research traditions by what models represent and predict, how they connect to actions, and what they’re used for—not as mutually exclusive categories.
AI
Researchers on X compare the new Explorative Modeling paper to earlier IMLE methods in algorithms, loss, and motivation.
