Andrei Manolache

"Learning (Approximately) Equivariant Networks via Constrained Optimization" will be an Oral 🗣️ at NeurIPS! (w/ @Mniepert & @lfochamon) ACE goes beyond fixed equivariance, augmentations, and regularizers by learning from data when to enforce symmetry and when to break it. 🧵2/9

⏰ The CoLLAs abstract deadline is only 10 days away! We invite researchers to explore all facets of ML adaptation, from incorporating new capabilities during continuous training to efficiently removing outdated or harmful data. - 𝗔𝗯𝘀𝘁𝗿𝗮𝗰𝘁 𝗗𝗲𝗮𝗱𝗹𝗶𝗻𝗲: April 10, 2026 - 𝗦𝘂𝗯𝗺𝗶𝘀𝘀𝗶𝗼𝗻 𝗗𝗲𝗮𝗱𝗹𝗶𝗻𝗲: April 15, 2026 - 𝗖𝗼𝗻𝗳𝗲𝗿𝗲𝗻𝗰𝗲 𝗗𝗮𝘁𝗲𝘀: Sep 14–17, 2026 📚 Accepted papers will be published in the Proceedings of Machine Learning Research (PMLR). 🔗 𝗙𝗼𝗿 𝗳𝘂𝗹𝗹 𝗱𝗲𝘁𝗮𝗶𝗹𝘀 𝗼𝗻 𝘁𝗵𝗲 𝗖𝗮𝗹𝗹 𝗳𝗼𝗿 𝗣𝗮𝗽𝗲𝗿𝘀: lifelong-ml.cc/Conferences/20…

We’re bringing the CoLLAs 2026 community to Bucharest, Romania 🇷🇴 next September! 🧠 Focus: Adaptation, Continual Learning, Unlearning 📅 Submit by mid-April Chat about CoLLAs topics or must-see spots in Bucharest at #NeurIPS2025 with Sarath, Razvan, and Eleni! 🚀

I respect that @iclr_conf had to respond to the OR leak, but I disagree with resetting scores. Many students worked hard on rebuttals and improved their papers in good faith. I hope the organizers reconsider and revert the reset. If you agree, feel free to retweet.

@kchonyc @orf_bnw Also happened to me yesterday with Nano Banana. ChatGPT managed to generate one with a transparent background, but the Nano Banana one was nicer.

these image generation models ... still think checker board patterns are transparent ... google nano banana pro kicked in its butt by google image search. 🤦 @orf_bnw please evaluate this transparent background capability, pretty please

@Mniepert @lfochamon ChronoGraph (w/ A. Lutu, I. Pintilie & @ilarele) is a real-world dataset of microservice telemetry that links multivariate time series with a dependency graph and incident labels, enabling evaluation of forecasting and anomaly detection methods under propagation effects. 🧵8/9

@Mniepert @lfochamon Inspired by JEPA, C-FREE (w/ B. Ariguib & @mniepert) uses a predictive objective over egonets spanning 2D and 3D graphs, avoiding negatives, reconstructions, and augmentations. This simple multimodal design delivers strong results from low- to large-scale regimes. 🔬 🧵6/9

"Learning (Approximately) Equivariant Networks via Constrained Optimization" will be an Oral 🗣️ at NeurIPS! (w/ @Mniepert & @lfochamon) ACE goes beyond fixed equivariance, augmentations, and regularizers by learning from data when to enforce symmetry and when to break it. 🧵2/9

@Mniepert @lfochamon @ilarele 📅 Dec 7, BERT2S Workshop Oral @ NeurIPS 📄 Preprint: arxiv.org/pdf/2509.04449 🧵9/9

Looking forward to #NeurIPS next week! I’m presenting three works across equivariant learning, molecular graph pretraining, and real-world graph-based time series: • ACE (NeurIPS Oral) • C-FREE (NPGML Poster) • ChronoGraph (BERT2S Oral) Details in the thread ⬇️🧵1/9

For #ISMB2026, some rules have been changed regarding proceedings paper submissions that the community should be aware of:

@PetarV_93 Btw, did you know that the studio hired Lorien Testard (main composer) because they just stumbled upon his work on some random forum? :) Best outcome for everyone involved.

@andreimano2 what's your favourite track? :) i'm currently oscillating between rouge d'iris and goblu (after failing to beat simon for months i've gotten a bit sick of the main theme 😅)

finally finished expedition 33 🥲🫠

@PetarV_93 Lumière definitely lived rent-free in my head the most, but I really like everything Gestral Village-related :P (except for Golgra's theme, that thing triggers my PTSD)

@SainttLord @PetarV_93 P5 is also amazing, but "dim dim dam dada dim dim da" just hits differently