Zobrazeno 1 - 10
of 5 825
pro vyhledávání: '"A. SOLIN"'
The covariance for clean data given a noisy observation is an important quantity in many conditional generation methods for diffusion models. Current methods require heavy test-time computation, altering the standard diffusion training process or den
Externí odkaz:
http://arxiv.org/abs/2410.11149
Differential equations are important mechanistic models that are integral to many scientific and engineering applications. With the abundance of available data there has been a growing interest in data-driven physics-informed models. Gaussian process
Externí odkaz:
http://arxiv.org/abs/2409.13876
The process of 3D scene reconstruction can be affected by numerous uncertainty sources in real-world scenes. While Neural Radiance Fields (NeRFs) and 3D Gaussian Splatting (GS) achieve high-fidelity rendering, they lack built-in mechanisms to directl
Externí odkaz:
http://arxiv.org/abs/2409.06407
Autor:
Kok, Manon, Solin, Arno
We present a lightweight magnetic field simultaneous localisation and mapping (SLAM) approach for drift correction in odometry paths, where the interest is purely in the odometry and not in map building. We represent the past magnetic field readings
Externí odkaz:
http://arxiv.org/abs/2409.01091
The Hilbert-space Gaussian Process (HGP) approach offers a hyperparameter-independent basis function approximation for speeding up Gaussian Process (GP) inference by projecting the GP onto M basis functions. These properties result in a favorable dat
Externí odkaz:
http://arxiv.org/abs/2408.02346
Autor:
Scannell, Aidan, Kujanpää, Kalle, Zhao, Yi, Nakhaei, Mohammadreza, Solin, Arno, Pajarinen, Joni
Learning representations for reinforcement learning (RL) has shown much promise for continuous control. We propose an efficient representation learning method using only a self-supervised latent-state consistency loss. Our approach employs an encoder
Externí odkaz:
http://arxiv.org/abs/2406.02696
Autor:
Tamir, Ella, Solin, Arno
Learning dynamical systems from sparse observations is critical in numerous fields, including biology, finance, and physics. Even if tackling such problems is standard in general information fusion, it remains challenging for contemporary machine lea
Externí odkaz:
http://arxiv.org/abs/2406.00561
Autor:
The SPD Collaboration, Abazov, V., Abramov, V., Afanasyev, L., Akhunzyanov, R., Akindinov, A., Alekseev, I., Aleshko, A., Alexakhin, V., Alexeev, G., Alimov, L., Allakhverdieva, A., Amoroso, A., Andreev, V., Andronov, E., Anikin, Yu., Anischenko, S., Anisenkov, A., Anosov, V., Antokhin, E., Antonov, A., Antsupov, S., Anufriev, A., Asadova, K., Ashraf, S., Astakhov, V., Aynikeev, A., Azarkin, M., Azorskiy, N., Bagulya, A., Baigarashev, D., Baldin, A., Baldina, E., Barbashina, N., Barnyakov, A., Barsov, S., Bartkevich, A., Baryshevsky, V., Basharina, K., Baskakov, A., Baskov, V., Batista, M., Baturitsky, M., Bautin, V., Bedareva, T., Belokurova, S., Belova, A., Belyaeva, E., Berdnikov, A., Berdnikov, Ya., Berezhnoy, A., Berngardt, A., Bespalov, Yu., Bleko, V., Bliznyuk, L., Bogoslovskii, D., Boiko, A., Boikov, A., Bolsunovskya, M., Boos, E., Borisov, V., Borsch, V., Budkouski, D., Bulanova, S., Bulekov, O., Bunichev, V., Burtebayev, N., Bychanok, D., Casanova, A., Cesar, G., Chemezov, D., Chepurnov, A., Chen, L., Chmill, V., Chukanov, A., Chuzo, A., Danilyuk, A., Datta, A., Dedovich, D., Demichev, M., Deng, G., Denisenko, I., Denisov, O., Derbysheva, T., Derkach, D., Didorenko, A., Dima, M. -O., Doinikov, A., Doronin, S., Dronik, V., Dubinin, F., Dunin, V., Durum, A., Egorov, A., El-Kholy, R., Enik, T., Ermak, D., Erofeev, D., Erokhin, A., Ezhov, D., Fedin, O., Fedotova, Ju., Feofilov, G., Filatov, Yu., Filimonov, S., Frolov, V., Galaktionov, K., Galoyan, A., Garkun, A., Gavrishchuk, O., Gerasimov, S., Gerassimov, S., Gilts, M., Gladilin, L., Golovanov, G., Golovnya, S., Golovtsov, V., Golubev, A., Golubykh, S., Goncharov, P., Gongadze, A., Greben, N., Gregoryev, A., Gribkov, D., Gridin, A., Gritsay, K., Gubachev, D., Guo, J., Gurchin, Yu., Gurinovich, A., Gurov, Yu., Guskov, A., Gutierrez, D., Guzman, F., Hakobyan, A., Han, D., Harkusha, S., Hu, Sh., Igolkin, S., Isupov, A., Ivanov, A., Ivanov, N., Ivantchenko, V., Jin, Sh., Kakurin, S., Kalinichenko, N., Kambar, Y., Kantsyrev, A., Kapitonov, I., Karjavine, V., Karpishkov, A., Katcin, A., Kekelidze, G., Kereibay, D., Khabarov, S., Kharyuzov, P., Khodzhibagiyan, H., Kidanov, E., Kidanova, E., Kim, V., Kiryanov, A., Kishchin, I., Kokoulina, E., Kolbasin, A., Komarov, V., Konak, A., Kopylov, Yu., Korjik, M., Korotkov, M., Korovkin, D., Korzenev, A., Kostenko, B., Kotova, A., Kotzinian, A., Kovalenko, V., Kovyazina, N., Kozhin, M., Kraeva, A., Kramarenko, V., Kremnev, A., Kruchonak, U., Kubankin, A., Kuchinskaia, O., Kulchitsky, Yu., Kuleshov, S., Kulikov, A., Kulikov, V., Kurbatov, V., Kurmanaliev, Zh., Kurochkin, Yu., Kutuzov, S., Kuznetsova, E., Kuyanov, I., Ladygin, E., Ladygin, V., Larionova, D., Lebedev, V., Levchuk, M., Li, P., Li, X., Li, Y., Livanov, A., Lednicki, R., Lobanov, A., Lobko, A., Loshmanova, K., Lukashevich, S., Luschevskaya, E., Lyashko, A. L'vov I., Lysan, V., Lyubovitskij, V., Madigozhin, D., Makarenko, V., Makarov, N., Makhmanazarov, R., Maleev, V., Maletic, D., Malinin, A., Maltsev, A., Maltsev, N., Malkhasyan, A., Malyshev, M., Mamoutova, O., Manakonov, A., Marova, A., Merkin, M., Meshkov, I., Metchinsky, V., Minko, O., Mitrankov, Yu., Mitrankova, M., Mkrtchyan, A., Mkrtchyan, H., Mohamed, R., Morozova, S., Morozikhin, A., Mosolova, E., Mossolov, V., Movchan, S., Mukhamejanov, Y., Mukhamejanova, A., Muzyaev, E., Myktybekov, D., Nagorniy, S., Nassurlla, M., Nechaeva, P., Negodaev, M., Nesterov, V., Nevmerzhitsky, M., Nigmatkulov, G., Nikiforov, D., Nikitin, V., Nikolaev, A., Oleynik, D., Onuchin, V., Orlov, I., Orlova, A., Ososkov, G., Panzieri, D., Parsamyan, B., Pavzderin, P., Pavlov, V., Pedraza, M., Perelygin, V., Peshkov, D., Petrosyan, A., Petrov, M., Petrov, V., Petrukhin, K., Piskun, A., Pivovarov, S., Polishchuk, I., Polozov, P., Polyanskii, V., Ponomarev, A., Popov, V., Popovich, S., Prokhorova, D., Prokofiev, N., Prokoshin, F., Puchkov, A., Pudin, I., Pyata, E., Ratnikov, F., Rasin, V., Red'kov, V., Reshetin, A., Reznikov, S., Rogacheva, N., Romakhov, S., Rouba, A., Rudnev, V., Rusinov, V., Rusov, D., Ryltsov, V., Saduyev, N., Safonov, A., Sakhiyev, S., Salamatin, K., Saleev, V., Samartsev, A., Samigullin, E., Samoylov, O., Saprunov, E., Savenkov, A., Seleznev, A., Semak, A., Senkov, D., Sergeev, A., Seryogin, L., Seryubin, S., Shabanov, A., Shahinyan, A., Shavrin, A., Shein, I., Sheremeteva, A., Shevchenko, V., Shilyaev, K., Shimansky, S., Shinbulatov, S., Shipilov, F., Shipilova, A., Shkarovskiy, S., Shoukovy, D., Shpakov, K., Shreyber, I., Shtejer, K., Shulyakovsky, R., Shunko, A., Sinelshchikova, S., Skachkova, A., Skalnenkov, A., Smirnov, A., Smirnov, S., Snesarev, A., Solin, A., Solin jr., A., Soldatov, E., Solovtsov, V., Song, J., Sosnov, D., Stavinskiy, A., Stekacheva, D., Streletskaya, E., Strikhanov, M., Suarez, O., Sukhikh, A., Sukhovarov, S., Sulin, V., Sultanov, R., Sun, P., Svirida, D., Syresin, E., Tadevosyan, V., Tarasov, O., Tarkovsky, E., Tchekhovsky, V., Tcherniaev, E., Terekhin, A., Terkulov, A., Tereshchenko, V., Teryaev, O., Teterin, P., Tishevsky, A., Tokmenin, V., Topilin, N., Tsiareshka, P., Tumasyan, A., Tyumenkov, G., Usenko, E., Uvarov, L., Uzhinsky, V., Uzikov, Yu., Valiev, F., Vasilieva, E., Vasyukov, A., Vechernin, V., Verkheev, A., Vertogradov, L., Vertogradova, Yu., Vidal, R., Voitishin, N., Volkov, I., Volkov, P., Vorobyov, A., Voskanyan, H., Wang, H., Wang, Y., Xu, T., Yanovich, A., Yeletskikh, I., Yerezhep, N., Yurchenko, S., Zakharov, A., Zamiatin, N., Zamora-Saá, J., Zarochentsev, A., Zelenov, A., Zemlyanichkina, E., Zhabitsky, M., Zhang, J., Zhang, Zh., Zhemchugov, A., Zherebchevsky, V., Zhevlakov, A., Zhigareva, N., Zhou, J., Zhuang, X., Zhukov, I., Zhuravlev, N., Zinin, A., Zmeev, S., Zolotykh, D., Zubarev, E., Zvyagina, A.
The Spin Physics Detector collaboration proposes to install a universal detector in the second interaction point of the NICA collider under construction (JINR, Dubna) to study the spin structure of the proton and deuteron and other spin-related pheno
Externí odkaz:
http://arxiv.org/abs/2404.08317
In the domains of image and audio, diffusion models have shown impressive performance. However, their application to discrete data types, such as language, has often been suboptimal compared to autoregressive generative models. This paper tackles the
Externí odkaz:
http://arxiv.org/abs/2405.17889
Retrosynthesis, the task of identifying precursors for a given molecule, can be naturally framed as a conditional graph generation task. Diffusion models are a particularly promising modelling approach, enabling post-hoc conditioning and trading off
Externí odkaz:
http://arxiv.org/abs/2405.17656