#ICML2026 kicks off in three days! We're excited to be presenting eight papers at the main conference this year. See the thread below for each paper, plus presentation times and locations 👇 Talk to our authors if you are interested!
1
3
15
1,110
1/ Tue, Jul 7, 2026 • 2:00 PM – 3:45 PM KST · HALL A #2713 Diamond Maps: Efficient Reward Alignment via Stochastic Flow Maps @peholderrieth*, Douglas Chen*,@LucaEyring*, @ishin_shah, Giri Anantharaman, @electronickale, @zeynepakata, Tommi Jaakkola, @nmboffi, and @max_simchowitz Paper: arxiv.org/abs/2602.05993 Code: github.com/PeterHolderrieth/…

Diamond Maps: Efficient Reward Alignment via Stochastic Flow Maps

Flow and diffusion models produce high-quality samples, but adapting them to user preferences or constraints post-training remains costly and brittle, a challenge commonly called reward alignment....

arxiv.org
1
1
242
3/ Wed, Jul 8, 2026 • 10:30 AM – 12:15 PM KST · HALL A #316 · POSTER Mantis: Lightweight Foundation Model for Time Series Classification @Vasya2104, Songkang Wen, Shifeng Xie, @SimonRoschmann, Marius Alonso, Hongbo Guo, Romain Ilbert, Malik Tiomoko,@QBouniot, @zeynepakata, Lujia Pan, Jianfeng Zhang, @IevgenRedko Paper: arxiv.org/abs/2502.15637 Code: github.com/vfeofanov/mantis

Mantis: Lightweight Foundation Model for Time Series Classification

While foundation models have revolutionized various domains, their application to time series classification remains rather under-explored, with existing literature predominantly focused on...

arxiv.org
1
158
4/ Wed, Jul 8, 2026 • 5:00 PM – 6:45 PM KST · HALL A #3204 · POSTER TimeSAE: Sparse Decoding for Faithful Explanations of Black-Box Time Series Models @oublal_khalid, @QBouniot, Qi Gan, Stéphan Clémençon, @zeynepakata Paper: arxiv.org/abs/2601.09776 Code: oublalkhalid.github.io/TimeS…

TimeSAE: Causal Sparse Decoding for Faithful Explanations of...

As black box models and pretrained models gain traction in time series applications, understanding and explaining their predictions becomes increasingly vital, especially in high-stakes domains...

arxiv.org
1
168
5/ Thu, Jul 9, 2026 • 10:30 AM – 12:15 PM KST · HALL A #2803 · POSTER (Spotlight) Dissecting Multimodal In-Context Learning: Modality Asymmetries and Circuit Dynamics in Modern Transformers @YiranHuang9,@confusezius,@QBouniot, @wenjia43411575,@zeynepakata. Paper: arxiv.org/abs/2601.20796 Code: github.com/YiranHuangIrene/m…

Dissecting Multimodal In-Context Learning: Modality Asymmetries...

Transformer-based multimodal large language models often exhibit in-context learning (ICL) abilities. Motivated by this phenomenon, we ask: how do transformers learn to associate information...

arxiv.org
1
1
1
112
6/ Thu, Jul 9, 2026 • 2:30 PM – 4:15 PM KST · HALL A #2614 · POSTER The Latent Color Subspace: Emergent Order in High-Dimensional Chaos @MateuszPach, @JessicaBader, @QBouniot, Serge Belongie, @zeynepakata Paper: arxiv.org/pdf/2603.12261 Code: github.com/ExplainableML/LCS
1
85
7/ Thu, Jul 9, 2026 • 5:00 PM – 6:45 PM KST · HALL A #2302 · POSTER Sparse Autoencoders are Topic Models Leander Girrbach, @zeynepakata Paper: arxiv.org/pdf/2511.16309 Code: github.com/ExplainableML/SAE…
1
90
8/ Thu, Jul 9, 2026 • 5:00 PM – 6:45 PM KST · HALL A #3710 · POSTER SOTAlign: Semi-Supervised Alignment of Unimodal Vision and Language Models via Optimal Transport @SimonRoschmann*, Paul Krzakala*, Sonia Mazelet, @QBouniot, @zeynepakata Paper: arxiv.org/abs/2602.23353 Code: github.com/ExplainableML/SOT…

SOTAlign: Semi-Supervised Alignment of Unimodal Vision and...

The Platonic Representation Hypothesis posits that neural networks trained on different modalities converge toward a shared statistical model of the world. Recent work exploits this convergence by...

arxiv.org
100
Sort replies: Relevant Recent Liked