Zobrazeno 1 - 10
of 8 257
pro vyhledávání: '"Jaakkola A"'
Autor:
Wang, Chenyu, Gupta, Sharut, Zhang, Xinyi, Tonekaboni, Sana, Jegelka, Stefanie, Jaakkola, Tommi, Uhler, Caroline
Multimodal representation learning seeks to relate and decompose information inherent in multiple modalities. By disentangling modality-specific information from information that is shared across modalities, we can improve interpretability and robust
Externí odkaz:
http://arxiv.org/abs/2410.23996
Autor:
Holderrieth, Peter, Havasi, Marton, Yim, Jason, Shaul, Neta, Gat, Itai, Jaakkola, Tommi, Karrer, Brian, Chen, Ricky T. Q., Lipman, Yaron
We introduce generator matching, a modality-agnostic framework for generative modeling using arbitrary Markov processes. Generators characterize the infinitesimal evolution of a Markov process, which we leverage for generative modeling in a similar v
Externí odkaz:
http://arxiv.org/abs/2410.20587
Autor:
Balla, Julia, Mishra-Sharma, Siddharth, Cuesta-Lazaro, Carolina, Jaakkola, Tommi, Smidt, Tess
Efficiently processing structured point cloud data while preserving multiscale information is a key challenge across domains, from graphics to atomistic modeling. Using a curated dataset of simulated galaxy positions and properties, represented as po
Externí odkaz:
http://arxiv.org/abs/2410.20516
Classical Hamiltonian mechanics has been widely used in machine learning in the form of Hamiltonian Monte Carlo for applications with predetermined force fields. In this work, we explore the potential of deliberately designing force fields for Hamilt
Externí odkaz:
http://arxiv.org/abs/2410.20470
Recent studies have identified one aggravating factor of LLM hallucinations as the knowledge inconsistency between pre-training and fine-tuning, where unfamiliar fine-tuning data mislead the LLM to fabricate plausible but wrong outputs. In this paper
Externí odkaz:
http://arxiv.org/abs/2410.19290
Autor:
Wang, Chenyu, Uehara, Masatoshi, He, Yichun, Wang, Amy, Biancalani, Tommaso, Lal, Avantika, Jaakkola, Tommi, Levine, Sergey, Wang, Hanchen, Regev, Aviv
Recent studies have demonstrated the strong empirical performance of diffusion models on discrete sequences across domains from natural language to biological sequence generation. For example, in the protein inverse folding task, conditional diffusio
Externí odkaz:
http://arxiv.org/abs/2410.13643
Autor:
Liu, Sulin, Nam, Juno, Campbell, Andrew, Stärk, Hannes, Xu, Yilun, Jaakkola, Tommi, Gómez-Bombarelli, Rafael
Discrete diffusion has achieved state-of-the-art performance, outperforming or approaching autoregressive models on standard benchmarks. In this work, we introduce Discrete Diffusion with Planned Denoising (DDPD), a novel framework that separates the
Externí odkaz:
http://arxiv.org/abs/2410.06264
Rationally identifying variables responsible for changes to a biological system can enable myriad applications in disease understanding and cell engineering. From a causality perspective, we are given two datasets generated by the same causal model,
Externí odkaz:
http://arxiv.org/abs/2410.03380
Molecular dynamics (MD) is a powerful technique for studying microscopic phenomena, but its computational cost has driven significant interest in the development of deep learning-based surrogate models. We introduce generative modeling of molecular t
Externí odkaz:
http://arxiv.org/abs/2409.17808
Autor:
Abdurakhimov, Leonid, Adam, Janos, Ahmad, Hasnain, Ahonen, Olli, Algaba, Manuel, Alonso, Guillermo, Bergholm, Ville, Beriwal, Rohit, Beuerle, Matthias, Bockstiegel, Clinton, Calzona, Alessio, Chan, Chun Fai, Cucurachi, Daniele, Dahl, Saga, Davletkaliyev, Rakhim, Fedorets, Olexiy, Frieiro, Alejandro Gomez, Gao, Zheming, Guldmyr, Johan, Guthrie, Andrew, Hassel, Juha, Heimonen, Hermanni, Heinsoo, Johannes, Hiltunen, Tuukka, Holland, Keiran, Hotari, Juho, Hsu, Hao, Huhtala, Antti, Hyyppä, Eric, Hämäläinen, Aleksi, Ikonen, Joni, Inel, Sinan, Janzso, David, Jaakkola, Teemu, Jenei, Mate, Jolin, Shan, Juliusson, Kristinn, Jussila, Jaakko, Khalid, Shabeeb, Kim, Seung-Goo, Koistinen, Miikka, Kokkoniemi, Roope, Komlev, Anton, Ockeloen-Korppi, Caspar, Koskinen, Otto, Kotilahti, Janne, Kuisma, Toivo, Kukushkin, Vladimir, Kumpulainen, Kari, Kuronen, Ilari, Kylmälä, Joonas, Lamponen, Niclas, Lamprich, Julia, Landra, Alessandro, Leib, Martin, Li, Tianyi, Liebermann, Per, Lintunen, Aleksi, Liu, Wei, Luus, Jürgen, Marxer, Fabian, de Griend, Arianne Meijer-van, Mitra, Kunal, Moqadam, Jalil Khatibi, Mrożek, Jakub, Mäkynen, Henrikki, Mäntylä, Janne, Naaranoja, Tiina, Nappi, Francesco, Niemi, Janne, Ortega, Lucas, Palma, Mario, Papič, Miha, Partanen, Matti, Penttilä, Jari, Plyushch, Alexander, Qiu, Wei, Rath, Aniket, Repo, Kari, Riipinen, Tomi, Ritvas, Jussi, Romero, Pedro Figueroa, Ruoho, Jarkko, Räbinä, Jukka, Saarinen, Sampo, Sagar, Indrajeet, Sargsyan, Hayk, Sarsby, Matthew, Savola, Niko, Savytskyi, Mykhailo, Selinmaa, Ville, Smirnov, Pavel, Suárez, Marco Marín, Sundström, Linus, Słupińska, Sandra, Takala, Eelis, Takmakov, Ivan, Tarasinski, Brian, Thapa, Manish, Tiainen, Jukka, Tosto, Francesca, Tuorila, Jani, Valenzuela, Carlos, Vasey, David, Vehmaanperä, Edwin, Vepsäläinen, Antti, Vienamo, Aapo, Vesanen, Panu, Välimaa, Alpo, Wesdorp, Jaap, Wurz, Nicola, Wybo, Elisabeth, Yang, Lily, Yurtalan, Ali
Quantum computing has tremendous potential to overcome some of the fundamental limitations present in classical information processing. Yet, today's technological limitations in the quality and scaling prevent exploiting its full potential. Quantum c
Externí odkaz:
http://arxiv.org/abs/2408.12433