Ryosuke Matsuda

🎉 Excited to share that our paper has been accepted to CVPR 2026 and is now available on arXiv! SLVMEval: Synthetic Meta Evaluation Benchmark for Text-to-Long Video Generation 🔗 arxiv.org/abs/2603.29186 #CVPR2026 #arXiv [1/N]

I'm putting together a list of top CVPR 2026 papers collecting must-see papers with links to code, demos, and posters all in one place basically my notes so I don't miss anything important link: github.com/SkalskiP/top-c…

Pretrained ViTs like DINOv2 or CLIP are great, but they produce fixed, generic representations that encode the most salient visual concepts (e.g., "cat"). In human vision, prior priming with language changes how people parse an image. We believe visual encoders should do the same 🚨 Introducing Steerable Visual Representations, a new family of visual features you can steer with text towards specific visual concepts.

Introducing Project Glasswing: an urgent initiative to help secure the world’s most critical software. It’s powered by our newest frontier model, Claude Mythos Preview, which can find software vulnerabilities better than all but the most skilled humans. anthropic.com/glasswing

✅ Our experiments show that humans can reliably identify the better long video, while existing evaluation systems still fall short on 9 out of 10 aspects. Would be happy if you check it out! 🙌 📄 Paper: arxiv.org/abs/2603.29186 🚀 Project Page : slvmeval.github.io [5/N]

📊 This gives us a testbed for evaluating whether existing systems can correctly rank long-video pairs when the quality difference should be obvious to people. In other words, SLVMEval tests a fundamental requirement for reliable long-video evaluation. [4/N]

🎉 Excited to share that our paper has been accepted to CVPR 2026 and is now available on arXiv! SLVMEval: Synthetic Meta Evaluation Benchmark for Text-to-Long Video Generation 🔗 arxiv.org/abs/2603.29186 #CVPR2026 #arXiv [1/N]

Claude Code skills for academic research pipeline github.com/Imbad0202/acad…

🚀MIT Flow Matching and Diffusion Lecture 2026 Released (diffusion.csail.mit.edu)! We just released our new MIT 2026 course on flow matching and diffusion models! We teach the full stack of modern AI image, video, protein generators - theory and practice. We include: 📺 Videos: Step-by-step derivations. 📝 Notes: Mathematically self-contained lecture notes 💻 Coding: Hands-on exercises for every component We fully improved last years’ iteration and added new topics: latent spaces, diffusion transformers, building language models with discrete diffusion models. Everything is available here: diffusion.csail.mit.edu A huge thanks to Tommi Jaakkola for his support in making this class possible and Ashay Athalye (MIT SOUL) for the incredible production! Was fun to do this with @RShprints! #MachineLearning #GenerativeAI #MIT #DiffusionModels #AI

Tired to go back to the original papers again and again? Our monograph: a systematic and fundamental recipe you can rely on! 📘 We’re excited to release 《The Principles of Diffusion Models》— with @DrYangSong, @gimdong58085414, @mittu1204, and @StefanoErmon. It traces the core ideas that shaped diffusion modeling and explains how today’s models work, why they work, and where they’re heading. 🧵You’ll find the link and a few highlights in the thread. We’d love to hear your thoughts and join some discussions! ⚡ Stay tuned for our markdown version, where you can drop your comments!

#NLP2026 にて，主著論文「多段算術推論タスクにおける思考の連鎖の忠実性」が委員特別賞を受賞しました! 共著者は@y_aoneko , @ttk_kuribayashi , shusaku sone, @ma38taniguchi , @ana_brrr, @KeisukeS_, @inuikentaro さんです． 共著者の皆様の多くのサポートに感謝申し上げます! @tohoku_nlp

#NLP2026 にて主著1件の発表をします！ LINEヤフーとの共同研究で，先日CVPR2026 mainに採択された内容を発表します！ 長尺動画に関するベンチマークを提案していますので，マルチモーダルに興味ある方はぜひ見に来て下さい！📹️ 日時：3/10 (火) 11:15-12:45 場所：C2-01 (C会場 2F大会議室202)

[1/9] What happens when you treat vision as a first-class citizen during multimodal pretraining? To find out, we studied the design space of training Transfusion-style models that input and output all modalities, from scratch. Here is what we learned about visual representations, data, world modeling, architecture, and scaling behavior! Paper: arxiv.org/abs/2603.03276 Website: beyond-llms.github.io @TongPetersb, @DavidJFan, @__JohnNguyen__, @ellisbrown, @GaoyueZhou, @JasonQSY, @boyangzheng, @webalorn, @han_junlin, @rob_fergus, @NailaMurray, @gh_marjan, @ml_perception, Nicolas Ballas, @_amirbar, Michael Rabbat, Jakob Verbeek, @LukeZettlemoyer, @koustuvsinha, @ylecun, @sainingxie

大規模視覚言語モデル内部におけるダイアグラムの表現を分析した論文が arXiv で公開されました！ #NLP2026 でも発表予定です！

@naka_BB5 ありがとう！

@VolumeisRyo すごすぎ！！おめでとう！！！

主著論文が #CVPR2026 にmainでAcceptされました！！🎉 @CVPR M1 のうちに国際会議に採択されて，大変光栄に思います． 沢山の助言や指導をして頂き，共著者の感謝申し上げます．🙏

共著論文が #CVPR2026 に採択されました🎉 M1 で CVPR はすごい！めでたい！

LINEヤフー Tech Blog 🆕 『高性能な日本語マルチモーダル基盤モデル「clip-japanese-base-v2」の公開』 - 日本語特化CLIPを高性能化し公開 - 大規模データ収集と精密フィルタによる精度の底上げ - 知識蒸留によるさらなる精度改善 techblog.lycorp.co.jp/ja/20251218a