Model Merging and Safety Alignment: One Bad Model Spoils the Bunch HAAK Hammoud, U Michieli, F Pizzati, P Torr, A Bibi, B Ghanem, M Ozay arXiv preprint arXiv:2406.14563, 2024 | | 2024 |
Localizing Events in Videos with Multimodal Queries G Zhang, MLA Fok, Y Xia, Y Tang, D Cremers, P Torr, V Tresp, J Gu arXiv preprint arXiv:2406.10079, 2024 | | 2024 |
Towards Interpretable Deep Local Learning with Successive Gradient Reconciliation Y Yang, X Li, M Alfarra, H Hammoud, A Bibi, P Torr, B Ghanem arXiv preprint arXiv:2406.05222, 2024 | | 2024 |
Learning Visual Prompts for Guiding the Attention of Vision Transformers R Rezaei, MJ Sabet, J Gu, D Rueckert, P Torr, A Khakzar arXiv preprint arXiv:2406.03303, 2024 | | 2024 |
HelloFresh: LLM Evaluations on Streams of Real-World Human Editorial Actions across X Community Notes and Wikipedia edits T Franzmeyer, A Shtedritski, S Albanie, P Torr, JF Henriques, JN Foerster arXiv preprint arXiv:2406.03428, 2024 | | 2024 |
Universal In-Context Approximation By Prompting Fully Recurrent Models A Petrov, TA Lamb, A Paren, PHS Torr, A Bibi arXiv preprint arXiv:2406.01424, 2024 | | 2024 |
Behind every domain there is a shift: Adapting distortion-aware vision transformers for panoramic semantic segmentation J Zhang, K Yang, H Shi, S Reiß, K Peng, C Ma, H Fu, PHS Torr, K Wang, ... IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024 | 20 | 2024 |
Model Merging and Safety Alignment: One Bad Model Spoils the Bunch H Abed Al Kader Hammoud, U Michieli, F Pizzati, P Torr, A Bibi, ... arXiv e-prints, arXiv: 2406.14563, 2024 | | 2024 |
Managing extreme AI risks amid rapid progress Y Bengio, G Hinton, A Yao, D Song, P Abbeel, T Darrell, YN Harari, ... Science 384 (6698), 842-845, 2024 | 12 | 2024 |
Direct3D: Scalable Image-to-3D Generation via 3D Latent Diffusion Transformer S Wu, Y Lin, F Zhang, Y Zeng, J Xu, P Torr, X Cao, Y Yao arXiv preprint arXiv:2405.14832, 2024 | | 2024 |
Towards Certification of Uncertainty Calibration under Adversarial Attacks C Emde, F Pinto, T Lukasiewicz, PHS Torr, A Bibi arXiv preprint arXiv:2405.13922, 2024 | | 2024 |
When LLMs step into the 3D World: A Survey and Meta-Analysis of 3D Tasks via Multi-modal Large Language Models X Ma, Y Bhalgat, B Smart, S Chen, X Li, J Ding, J Gu, DZ Chen, S Peng, ... arXiv preprint arXiv:2405.10255, 2024 | 1 | 2024 |
Select to Perfect: Imitating desired behavior from large multi-agent data T Franzmeyer, E Elkind, P Torr, J Foerster, J Henriques arXiv preprint arXiv:2405.03735, 2024 | | 2024 |
Near to mid-term risks and opportunities of open source generative ai F Eiras, A Petrov, B Vidgen, CS de Witt, F Pizzati, K Elkins, ... arXiv preprint arXiv:2404.17047, 2024 | 2 | 2024 |
Energy-latency manipulation of multi-modal large language models via verbose samples K Gao, J Gu, Y Bai, ST Xia, P Torr, W Liu, Z Li arXiv preprint arXiv:2404.16557, 2024 | 2 | 2024 |
An MRP Formulation for Supervised Learning: Generalized Temporal Difference Learning Models Y Pan, J Wen, C Xiao, P Torr arXiv preprint arXiv:2404.15518, 2024 | | 2024 |
Continual learning on a diet: Learning from sparsely labeled streams under constrained computation W Zhang, Y Mohamed, B Ghanem, PHS Torr, A Bibi, M Elhoseiny arXiv preprint arXiv:2404.12766, 2024 | 2 | 2024 |
kNN-CLIP: Retrieval Enables Training-Free Segmentation on Continually Expanding Large Vocabularies Z Gui, S Sun, R Li, J Yuan, Z An, K Roth, A Prabhu, P Torr arXiv preprint arXiv:2404.09447, 2024 | | 2024 |
Latent guard: a safety framework for text-to-image generation R Liu, A Khakzar, J Gu, Q Chen, P Torr, F Pizzati arXiv preprint arXiv:2404.08031, 2024 | 2 | 2024 |
AnimateZoo: Zero-shot Video Generation of Cross-Species Animation via Subject Alignment Y Xu, Y Chen, Z Huang, Z He, G Wang, P Torr, L Lin arXiv preprint arXiv:2404.04946, 2024 | | 2024 |