LIONS @ NeurIPS 2025
NeurIPS logo © NeurIPS 2025
6 papers from the LIONS group have been accepted to the 2025 edition of NeurIPS conference. Congratulations to all!
This year, the 39th Annual Conference on Neural Information Processing Systems conference will be held in San Diego, USA from 2 to 7 December.
Below is a list of NeurIPS 2025 papers with at least one LIONS author:
- Generalized Gradient Norm Clipping & Non-Euclidean (L_0,L_1)-Smoothness by Thomas Pethick, Wanyun Xie, Mete Erdogan, Kimon Antonakopoulos, Tony Silveti-Falls, Volkan Cevher (Oral)
- Efficient Large Language Model Inference with Neural Block Linearization by Mete Erdogan, Francesco Tonin, Volkan Cevher
- Robustness in Both Domains: CLIP Needs a Robust Text Encoder by Elias Abad Rocamora, Christian Schlarmann, Naman Deep Singh, Yongtao Wu, Matthias Hein, Volkan Cevher
- Learning Equilibria from Data: Provably Efficient Multi-Agent Imitation Learning by Till Freihaut, Luca Viano, Volkan Cevher, Matthieu Geist, Giorgia Ramponi
- Ascent Fails to Forget by Ioannis Mavrothalassitis, Pol Puigdemont Plana, Noam Itzhak Levi, Volkan Cevher
- Linear Attention for Efficient Bidirectional Sequence Modeling by Arshia Afzal, Elias Abad Rocamora, Leyla Naz Candogan, Pol Puigdemont Plana, Francesco Tonin, Yongtao Wu, Mahsa Shoaran, Volkan Cevher