Aleksandar Bojchevski (@abojchevski) header
Aleksandar Bojchevski (@abojchevski) profile picture

Trustworthy Machine Learning. Graphs. Professor at the University of Cologne. He/Him. 🏳️‍🌈 Open PhD/PostDoc positions: https://nitter.cf/t.co/QSCqXRzlEu

Germany
Joined August 2009
Photo by Aleksandar Bojchevski (@abojchevski)Photo by Aleksandar Bojchevski (@abojchevski)Photo by Aleksandar Bojchevski (@abojchevski)Photo by Aleksandar Bojchevski (@abojchevski)Photo by Aleksandar Bojchevski (@abojchevski)Photo by Aleksandar Bojchevski (@abojchevski)Photo by Aleksandar Bojchevski (@abojchevski)Photo by Aleksandar Bojchevski (@abojchevski)Photo by Aleksandar Bojchevski (@abojchevski)
What if the teacher is wrong? Standard on-policy distillation learns from it anyway. RG-OPD doesn't. We gate distillation using verifier reward + the teacher–student likelihood gap, keeping the same reverse-KL objective. 📈 +2.9 pts vs OPD @ 1K 📈 +8.2 pts vs base @ 8K
1
2
9
707
Aleksandar Bojchevski retweeted
Jailbreaking research assumes a fixed model. Test-time training breaks that assumption: the attacker gets a lever on the weights, not just the prompt. We show this opens a new attack surface that undermines LLM safety guardrails. 🧵 (1/6)
1
6
1
7
822
Aleksandar Bojchevski retweeted
1/5 Ever wondered how to apply conformal prediction when there's epistemic uncertainty? Our new paper addresses this question!CP can benefit from models like Bayesian, evidential, and credal predictors to have better prediction sets,for instance, in terms of conditional coverage.
1
5
1
14
2,923
Aleksandar Bojchevski retweeted
🚨 Robust conformal prediction is expensive as we need around 10000 forward passes per input. Or Is it? Checkout our ICLR2025 paper: openreview.net/forum?id=ltrx… We extend conformal sets to worst case noise under any smoothing, with much less samples. Joint work with @abojchevski
1
1
1
4
810
Aleksandar Bojchevski retweeted
Want to learn continuous & discrete Flow Matching? We've just released: 📙 A guide covering Flow Matching basics & advanced methods arxiv.org/abs/2412.06264. 💻 An open source codebase with image & text examples github.com/facebookresearch/…. 🗣️ A Flow Matching tutorial #NeurIPS2024.
10
159
2
868
112,639
Aleksandar Bojchevski retweeted
Missed out on #Swift tickets? No worries—swing by our #SVFT poster at #NeurIPS2024 and catch *real* headliners! 🎤💃🕺 📌Where: East Exhibit Hall A-C #2207, Poster Session 4 East ⏲️When: Thu 12 Dec, 4:30 PM - 7:30 PM PST #AI #MachineLearning #PEFT #NeurIPS24
🚀 Exciting new paper alert! Achieve up to 96% full performance with just 0.006-0.25% of trainable parameters!✨ How? It’s all in the singular vectors! Introducing 🎯SVFT: Singular Vectors guided Fine-Tuning for PEFT. Here’s a quick breakdown!🧵 #AI #MachineLearning #NLP #CV
9
1
27
4,050
Aleksandar Bojchevski retweeted
A common question nowadays: Which is better, diffusion or flow matching? 🤔 Our answer: They’re two sides of the same coin. We wrote a blog post to show how diffusion models and Gaussian flow matching are equivalent. That’s great: It means you can use them interchangeably.
16
201
28
940
173,507
Aleksandar Bojchevski retweeted
Replying to @guennemann
@guennemann kicking of the LOG meetup in Aachen.
1
1
15
741
Aleksandar Bojchevski retweeted
1/ Can Large Language Models (LLMs) truly reason? Or are they just sophisticated pattern matchers? In our latest preprint, we explore this key question through a large-scale study of both open-source like Llama, Phi, Gemma, and Mistral and leading closed models, including the recent OpenAI GPT-4o and o1-series. arxiv.org/pdf/2410.05229 Work done with @i_mirzadeh, @KeivanAlizadeh2, Hooman Shahrokhi, Samy Bengio, @OncelTuzel. #LLM #Reasoning #Mathematics #AGI #Research #Apple
385
1,184
408
5,505
1,613,071
Move over Taylor there's another SVFT in town.
🎉 Thrilled to share that SVFT is officially accepted at #NeurIPS24! 🙌 See you all in Vancouver! w/ incredible co-authors @vijaylingam08 @VavreAditya @aneeshk1412 @gauthamkrishna_ Joydeep Ghosh @AlexGDimakis @eunsolc @abojchevski @sujaysanghavi
4
10
1,464
Aleksandar Bojchevski retweeted
I am happy to announce that @abojchevski, Michael Schaub, Martin Grohe, and I are organizing a @LogConference local meet-up in Aachen (27.11.-28.11.), including keynotes from @guennemann and @BurkholzRebekka. See log-rwth.github.io/log-meetu… for more information.
1
18
51
6,004
Aleksandar Bojchevski retweeted
✨🎨🏰Super excited to share our new paper Ensemble everything everywhere: Multi-scale aggregation for adversarial robustness Inspired by biology we 1) get adversarial robustness + interpretability for free, 2) turn classifiers into generators & 3) design attacks on vLLMs 1/12
25
192
37
1,020
248,735
Aleksandar Bojchevski retweeted
#ICML2024 With conformal prediction (CP) we return sets that include the true class with guaranteed high probability, With robust CP we maintain this probability even for worst case (adversarial) noisy input. With CAS (our method) we have robust CP with efficient (small) sets.
1
5
27
2,946
Aleksandar Bojchevski retweeted
🎉Happy to announce that our paper – SVFT: Parameter-Efficient Fine-Tuning with Singular Vectors has been accepted for an oral presentation at WANT @icmlconf!✨#ICML2024 #MachineLearning Paper: openreview.net/forum?id=DOUs…
🚀 Exciting new paper alert! Achieve up to 96% full performance with just 0.006-0.25% of trainable parameters!✨ How? It’s all in the singular vectors! Introducing 🎯SVFT: Singular Vectors guided Fine-Tuning for PEFT. Here’s a quick breakdown!🧵 #AI #MachineLearning #NLP #CV
3
7
32
4,692
Aleksandar Bojchevski retweeted
🤔 Ever wondered how vulnerable Graph Neural Networks (GNNs) really are? 🚀 Check out our slightly late, but crucial, #ICLR2024 paper: "Rethinking Label Poisoning for GNNs: Pitfalls and Attacks"! 🔥
1
5
13
1,147
Read all about our highly parameter-efficient fine tuning approach that Pareto-dominates LoRA and other baselines.
🚀 Exciting new paper alert! Achieve up to 96% full performance with just 0.006-0.25% of trainable parameters!✨ How? It’s all in the singular vectors! Introducing 🎯SVFT: Singular Vectors guided Fine-Tuning for PEFT. Here’s a quick breakdown!🧵 #AI #MachineLearning #NLP #CV
6
12
2,033
Aleksandar Bojchevski retweeted
This paper made me smile a lot while working on it, so I want to share a bit about it arxiv.org/abs/2405.09676. We draw a parallel story to the Eckart-Young Theorem (from numerical analysis) in stochastic optimization/learning problems. (with Josh Cutler and Dima Drusvyatskiy)
3
21
1
98
13,639