Publications of S Wu

Binz, M.; Akata, E.; Bethge, M.; Brändle, F.; Callaway, F.; Coda-Forno, J.; Dayan, P.; Demircan, C.; Eckstein, M.; Éltetö, N. et al.; Griffiths, T.; Haridi, S.; Jagadish, A.; Li, J.-A.; Kipnis, A.; Kumar, S.; Ludwig, T.; Mathony, M.; Mattar, M.; Modirshanechi, A.; Nath, S.; Peterson, J.; Rmus, M.; Russek, E.; Saanum, T.; Schubert, J.; Schulze Buschoff, L.; Singhi, N.; Sui, X.; Thalmann, M.; Theis, F.; Truong, V.; Udandarao, V.; Voudouris, K.; Wilson, R.; Witte, K.; Wu, S.; Wulff, D.; Xiong, H.; Schulz, E.: A foundation model to predict and capture human cognition. Nature 644 (8078), pp. 1002 - 1009 (2025)

Wu, S.; Thalmann, M.; Schulz, E.: Two types of motifs enhance human recall and generalization of long sequences. Communications Psychology 3 (1), 3 (2025)

Wu, S.; Éltetö, N.; Dasgupta, I.; Schulz, E.: Chunking as a rational solution to the speed-accuracy trade-off in a serial reaction time task. Scientific Reports 13, 7680 (2023)

Wu, S.; Alaniz, S.; Karthik, S.; Dayan, P.; Schulz, E.; Akata, Z.: Concept-Guided Interpretability via Neural Chunking. In: Thirty-ninth Conference on Neural Information Processing Systems (NeurIPS 2025). Thirty-ninth Conference on Neural Information Processing Systems (NeurIPS 2025), Vancouver, Canada, December 10, 2024 - December 15, 2024. (2025)

Wu, S.; Thalmann, M.; Dayan, P.; Akata, Z.; Schulz, E.: Building, Reusing, and Generalizing Abstract Representations from Concrete Sequences. In: Thirteenth International Conference on Learning Representations (ICLR 2025). Thirteenth International Conference on Learning Representations (ICLR 2025), Singapore, April 24, 2025 - April 28, 2025. (2025)

Wu, S.; Thalmann, M.; Schulz, E.: Learning abstractions from discrete sequences. In: 46th Annual Conference of the Cognitive Science Society (CogSci 2024). 46th Annual Conference of the Cognitive Science Society (CogSci 2024), Rotterdam, The Netherlands, July 24, 2024 - July 27, 2024. (2024)

Schreiber, A.; Wu, S.; Wu, C.; Indiveri, G.; Schulz, E.: Biologically-plausible hierarchical chunking on mixed-signal neuromorphic hardware. In: NeurIPS 2023 Workshop: Machine Learning with New Compute Paradigms. NeurIPS 2023 Workshop: Machine Learning with New Compute Paradigms, New Orleans, LA, USA, December 16, 2023. (2023)

Wu, S.; Thalmann, M.; Schulz, E.: Projectional motifs facilitate sequence memorization and transfer. In: 2023 Conference on Cognitive Computational Neuroscience, P-3.118, pp. 1294 - 1296. Conference on Cognitive Computational Neuroscience (CCN 2023), Oxford, UK, August 24, 2023 - August 27, 2023. (2023)

Wu, S.; Éltetö, N.; Dasgupta, I.; Schulz, E.: Learning Structure from the Ground up: Hierarchical Representation Learning by Chunking. In: Advances in Neural Information Processing Systems 35: 36th Conference on Neural Information Processing Systems (NeurIPS 2022), pp. 36706 - 36721 (Eds. Koyejo, S.; Mohamed, S.). Thirty-sixth Conference on Neural Information Processing Systems (NeurIPS 2022), New Orleans, LA, USA, November 28, 2022 - December 09, 2022. Curran, Red Hook, NY, USA (2023)

Wu, S.; Éltetö, N.; Dasgupta, I.; Schulz, E.: Learning Structure from the Ground up: Hierarchical Representation Learning by Chunking. In: Tenth International Conference on Learning Representations (ICLR 2022). Tenth International Conference on Learning Representations (ICLR 2022), April 25, 2022 - April 29, 2022. (2022)

Wu, S.; Yoerueten, M.; Wichmann, F.; Schulz, E.: Normalized Cuts Characterize Visual Recognition Difficulty of Amorphous Image Sub-parts. Computational and Systems Neuroscience Meeting (COSYNE 2024), Lisboa, Portugal (2024)

Wu, S.; Elteto, N.; Dasgupta, I.; Schulz, E.: Chunking as a rational solution to the speed-accuracy trade-off in a serial reaction time task. 43rd Annual Conference of the Cognitive Science Society (CogSci 2021), Wien, Austria (2021)

Binz, M.; Akata, E.; Almaatouq, A.; Alsobay, M.; Ariasov, O.; Brändle, F.; Broska, D.; Burton, J.; Busch, N.; Callaway, F. et al.; Cheung, V.; Christian, B.; Coda-Forno, J.; Demircan, C.; Dentella, V.; Eckstein, M.; Éltetö, N.; Franke, M.; Griffiths, T.; Günther, F.; Haridi, S.; Hellmann, S.; Herytash, S.; Hof, L.; Holton, E.; Hoxha, I.; Hussain, Z.; Jagadish, A.; Kara, E.; Kriegmair, V.; Leivada, E.; Ji-An, L.; Ludwig, T.; Maier, M.; Mattar, M.; Mathony, M.; Modirshanechi, A.; Na, R.; Nadverniuk, M.; Nasioulas, A.; Nath, S.; Niemeyer, H.; Nussenbaum, K.; Olschewski, S.; Pachur, T.; Palminteri, S.; Petrenco, A.; Phaneuf-Hadd, C.; Pirrone, A.; Rausch, M.; Raveling, L.; Reddy, S.; Rmus, M.; Russek, E.; Saanum, T.; Sandbrink, K.; Schiekiera, L.; Schubert, J.; Schulze Buschoff, L.; Singhi, N.; Somerville, L.; Spektor, M.; Sui, X.; Summerfield, C.; Thalmann, M.; Thoma, A.; Tikhomirova, T.; Truong, V.; Tsvilodub, P.; Voudouris, K.; Wilson, R.; Witte, K.; Wu, S.; Wulff, D.; Xiong, H.-D.; Xu, S.; Ying, L.; Zhang, X.; Zhu, J.-Q.; Schulz, E.: Post-training makes large language models less human-like. (submitted)

Binz, M.; Akata, E.; Bethge, M.; Brändle, F.; Callaway, F.; Coda-Forno, J.; Dayan, P.; Demircan, C.; Eckstein, M.; Éltetö, N. et al.; Griffiths, T.; Haridi, S.; Jagadish, A.; Ji-An; Kipnis, A.; Kumar, S.; Ludwig, T.; Mathony, M.; Mattar, M.; Modirshanechi, A.; Nath, S.; Peterson, J.; Rmus, M.; Russek, E.; Saanum, T.; Scharfenberg, N.; Schubert, J.; Schulze Buschoff, L.; Singhi, N.; Sui, X.; Thalmann, M.; Theis, F.; Truong, V.; Udandarao, V.; Voudouris, K.; Wilson, R.; Witte, K.; Wu, S.; Wulff, D.; Xiong, H.; Schulz, E.: Centaur: a foundation model of human cognition. (submitted)

Wu, S.; Thalmann, M.; Schulz, E.: Motif Learning Facilitates Sequence Memorization and Generalization. (submitted)