I released torchdistill v1.1.5 last week - Reimplemented "Streamlined Knowledge Distillation" method - trackio / wandb support - FSDP/FSDP2 support - "accumulation mode" for forward hook manager and more github.com/yoshitomo-ma...
Yoshitomo Matsubara
Directory member with public evidence across Vision & synthetic media, AI research, Compute & infrastructure.
- AI signals
- 1 past 30d
- Sources
- 1 distinct domains
- Discussions
- 1 past 30d
- Latest signal
- 21d ago
Articles & links
Recent commentary
Call for emergency reviewers #NeurIPS2026 I'm looking for two emergency reviewers: - Multimodal (text + vision) benchmark - AI for Science (text-focused) benchmark If you have experience in either domains, send me a DM including your OpenReview profile and Google Scholar links
Attending #CVPR2026 Hit me up if you want to discuss peer-review systems (suggestion/feedback), knowledge distillation, or ML OSS
Came up w/ a crazy idea from #NeurIPS2026 complaints Create "AI-permissive" and "Legacy/Classic" tracks, expanding the idea of ICML'26 review policy The latter uses "AI-content" detectors w/ thresholds tuned to maximize recall for papers and reviews, and takes strong actions (DR, ban, etc) WDYT?
In Yoshitomo Matsubara's orbit
Center = Yoshitomo Matsubara. Left = members they follow (green edges). Right = members who follow them (blue edges). Top = mutual follows (orange edges, slightly larger). Drag any node to reposition; click to open that profile.
Are you Yoshitomo Matsubara? Show it.
Add the Who’s Who of AI badge to your site or bio. It links back to this profile.
Markdown: [](https://aiweekly.co/whos-who/person/yoshitomo-matsubara-net)