Christoph Lampert (MLCV@ISTA)

@mlcv-at-ista.bsky.social

Professor at ISTA (Institute of Science and Technology Austria), heading the Machine Learning and Computer Vision group. We work on Trustworthy ML (robustness, fairness, privacy) and transfer learning (continual, meta, lifelong). ๐Ÿ”— https://cvml.ist.ac.at

How can we make large language models safe, secure & trustworthy? ๐Ÿ” Join us for the LLM Safety & Security Workshop, part of the ELLIS UnConference (in Copenhagen ๐Ÿ‡ฉ๐Ÿ‡ฐ on Dec 2), co-located with #EurIPS. ๐Ÿ“… Submit contributions by Oct 28, 2025 ๐Ÿ”— All info: eurips.cc/ellis

Bild

๐Ÿ“ข ๐—–๐—ฎ๐—น๐—น ๐—ณ๐—ผ๐—ฟ ๐—ฃ๐—ผ๐˜€๐˜๐—ฒ๐—ฟ๐˜€: ๐—Ÿ๐—Ÿ๐—  ๐—ฆ๐—ฎ๐—ณ๐—ฒ๐˜๐˜† ๐—ฎ๐—ป๐—ฑ ๐—ฆ๐—ฒ๐—ฐ๐˜‚๐—ฟ๐—ถ๐˜๐˜† ๐—ช๐—ผ๐—ฟ๐—ธ๐˜€๐—ต๐—ผ๐—ฝ @ ๐—˜๐—Ÿ๐—Ÿ๐—œ๐—ฆ ๐—จ๐—ป๐—–๐—ผ๐—ป๐—ณ๐—ฒ๐—ฟ๐—ฒ๐—ป๐—ฐ๐—ฒ ๐Ÿ“… December 2, 2025 ๐Ÿ“ Copenhagen An opportunity to discuss your work with colleagues working on similar problems in LLM safety and security

Bild

Finally a workshop on Differential Privacy in Europe! Organized by Monika Henzinger at IST Austria next year in September, so reserve the date! Monikaโ€™s STOC keynote, where the workshop was announced, was about the intersection of privacy and dynamic algorithms. Lots of questions in this space!

First European Workshop on Differential Privacy
September 17, 2026
At IST Austria

Remember that your main audience of the rebuttal is the AC. Make sure the rebuttal is self-contained, clearly makes your points, and is concise! If your rebuttal lacks context for the AC, revise until a person who is not your co-author or the reviewer understands the points.

Ahmad Beirami@abeirami.bsky.social ยท last yr.

Only 2 out of 120 papers in my NeurIPS SAC batch have all reviewer scores โ‰ฅ4! Don't despair with the low scores and focus on writing a clear and concise rebuttal! Good luck!

Are you looking for an opportunity to do curiosity-driven basic ML research after your PhD? Look no further! Apply for a postdoc position in my group at ISTA (ELLIS Unit Vienna)! Topics are flexible, as long as they fit to our general research group's interests, see cvml.ista.ac.at/Postdoc-ML.h...

Machine Learning and Computer Vision Group -- Christoph Lampert -- ISTA

Computer Vision and Machine Learning, ISTA: open postdoc positions, Machine Learning, curiosity-driven, fully-funded

cvml.ista.ac.at

๐Ÿš€ Weโ€™ve released the source code for ๐—”๐—ฆ๐—œ๐——๐—˜ (presented as an ๐—ข๐—ฟ๐—ฎ๐—น at the #ICLR2025 BuildTrust workshop)! ๐Ÿ” ASIDE boosts prompt injection robustness without safety-tuning: we simply rotate embeddings of marked tokens by 90ยฐ during instruction-tuning and inference. ๐Ÿ‘‡ code & docs๐Ÿ‘‡

Bild

Iโ€™ll present our ๐—”๐—ฆ๐—œ๐——๐—˜ paper as an ๐—ข๐—ฟ๐—ฎ๐—น at the #ICLR2025 BuildTrust workshop! ๐Ÿš€ โœ… ASIDE = architecturally separating instructions and data in LLMs from layer 0 ๐Ÿ” +12โ€“44 ppโ†‘ separation, no utility lossโ€‹โ€‹ ๐Ÿ“‰ lowers promptโ€‘injection ASR (without safety tuning!) ๐Ÿš€ Talk: Hall 4 #6, 28 Apr, 4:45

Bild

(1/n) In our #ICLR2025 paper, we explore a fundamental issue that enables prompt injections: ๐‹๐‹๐Œ๐ฌโ€™ ๐ข๐ง๐š๐›๐ข๐ฅ๐ข๐ญ๐ฒ ๐ญ๐จ ๐ฌ๐ž๐ฉ๐š๐ซ๐š๐ญ๐ž ๐ข๐ง๐ฌ๐ญ๐ซ๐ฎ๐œ๐ญ๐ข๐จ๐ง๐ฌ ๐Ÿ๐ซ๐จ๐ฆ ๐๐š๐ญ๐š ๐ข๐ง ๐ญ๐ก๐ž๐ข๐ซ ๐ข๐ง๐ฉ๐ฎ๐ญ. โœ… Definition of separation ๐Ÿ‘‰ SEP Benchmark ๐Ÿ” LLM evals on SEP

Bild

๐Ÿ—บ๏ธ๐Ÿ” Discover the ELLIS Unit Vienna at ISTA ๐Ÿ‡ฆ๐Ÿ‡น - where curiosity-driven ML research leads to scientific excellence. ๐Ÿ’กSee the highlights below and dive deeper into their work by reading the full article here: ellis.eu/news/ellis-u...