PhD student @ExplainableML @TU_Muenchen @HelmholtzMunich. Passionate about ML research.

München, Bayern
Joined January 2020
Simon Roschmann retweeted
Paper Spotlight: What if we studied AI the way biologists study animals? In 2019 (at the time of GPT-2!), researchers argued in Nature for a new science: "machine behaviour". Today, it looks like a pretty good prediction of the current scientific field around frontier systems:
2
5
22
656
Simon Roschmann retweeted
What does an LLM think of you? LLMs pick up the slightest implicit cues about users. Often, they refuse to say who they think the user is. In our new preprint, we show how to read and change these hidden beliefs. Turns out they even affect whether the model refuses New paper🧵
2
9
17
633
Simon Roschmann retweeted
curious why agents behave the way they do, and how we can better control them? we're looking for TUM students interested in doing a bachelor's or master's thesis with us on mechanistic interpretability and agent control! please apply or just DM eml-munich.de/jobs#mech_inte…
1
2
3
100
Simon Roschmann retweeted
Paper Spotlight: What does an AI agent do when nobody gives it a task? The authors gave Claude Code a body on an unknown island, said only "Begin", and left it alone for 30 hours. It climbed hills, built towers, invented basketball and bowling, and ran physics experiments.
3
4
1
29
1,225
Simon Roschmann retweeted
Paper Highlight: Towards a Science of AI Agent Reliability Agents keep scoring higher on benchmarks, yet they still fail in real deployments. Accuracy alone hides this, and agent reliability barely improved over two years of model releases.
7
2
1
10
440
Simon Roschmann retweeted
We are looking for PhD students to start as soon as possible. Application deadline is August 10. Please apply, please share! 🙂
📢 Fully funded PhD @ Helmholtz Munich + TUM We're hiring PhD students to build trustworthy AI systems for science: explainable AI, VLMs, reliable adaptation, agentic workflows. ⏰ Priority deadline 10 Aug 2026. Application details below 👇
9
40
1
183
39,733
📢 Fully funded PhD @ Helmholtz Munich + TUM We're hiring PhD students to build trustworthy AI systems for science: explainable AI, VLMs, reliable adaptation, agentic workflows. ⏰ Priority deadline 10 Aug 2026. Application details below 👇
1
14
2
63
25,410
Happy to share that we have 8 papers accepted to #ICML2026! 🎉 Most of the authors will be traveling to Seoul, Korea 🇰🇷 — feel free to reach out and chat with them if you’re interested in the work. See the full thread below for our papers 👇
2
10
1
45
9,147
Simon Roschmann retweeted
Excited to be in San Diego at #NeurIPS2025 this week. We'll be presenting Noise Hypernetworks at Hall C,D,E #3605 Thu 4 Dec 11am! If you're interested in Diffusion/Flow Matching or Reward Alignment, I'd love to chat! Feel free to DM me if you'd like to connect.
Reward hacking is challenging when fine-tuning few-step Diffusion models. Direct fine-tuning on rewards can create artifacts that game metrics while degrading visual quality. We propose Noise Hypernetworks as a theoretically grounded solution, inspired by test-time optimization.
9
25
3,411
Our EML members have arrived in beautiful San Diego for #NeurIPS2025! 🌴 We’re excited to share our latest research — three poster presentations and one workshop presentation. Check out the thread below 👇 and come say hi to our authors!
1
4
1
12
4,219