19 papers · ranked by Valyu relevance
Song, Heekang, Choi, Wan
In this paper, we propose an optimally structured gradient coding scheme to mitigate the straggler problem in distributed learning. Conventional gradient coding methods often assume homogeneous straggler models or rely on excessive data replication, limiting performance in real-world heterogeneous systems. To address…
Yuhang Wang, Weihua Chen, Linjing Song, Zhiping Xu + 6 more
With the rapid growth of data volume in sensor networks, lossy source coding systems achieve high-efficiency data compression with low distortion under limited transmission bandwidth. However, conventional compression algorithms rely on a two-stage framework with high computational complexity and frequently struggle to…
Neta Shaul, Chao Liu, Arash Vahdat, Julius Berner
Generation in video diffusion or flow models is computationally expensive due to the slow and iterative sampling process. Current state-of-the-art (SOTA) acceleration methods heavily rely on variational score distillation (VSD) and adversarial losses to distill diffusion models into few-step generators. Albeit…
Amedeo Chiefa, Luigi Del Debbio, Richard Kenway
Parton distribution functions (PDFs) play a central role in describing experimental data at colliders and provide insight into the structure of nucleons. As the LHC enters an era of high-precision measurements, a robust PDF determination with a reliable uncertainty quantification has become mandatory in order to match…
Authors not listed
The rigorous design of adsorption-based separation processes, such as Pressure Swing Adsorption (PSA) and Temperature Swing Adsorption (TSA), is fundamentally dependent on the accuracy of the underlying mathematical models describing equilibrium isotherms and transport kinetics. However, the current state of the art is…
Ronai, Or, Kulikov, Vladimir + 2 more
The remarkable success of diffusion and flow-matching models has ignited a surge of works on adapting them at test time for controlled generation tasks. Examples range from image editing to restoration, compression and personalization. However, due to the iterative nature of the sampling process in those models, it is…
Authors not listed
The GENERIC framework provides a robust structure for nonequilibrium dynamics but lacks a principled method to select reversible ($L$) and irreversible ($M$) brackets. Similarly, finite-time optimizations minimizing path-averaged reciprocal temperature exist but remain isolated. Here, we introduce the \textbf{Entropy…
Alexandros Karagiorgis, Susanne Dyck, Anwesha Das, Katja Kornysheva + 2 more
Remembering events in the correct order, and generating ordered sequences of actions, are fundamental abilities across species. Behavioral studies, and theoretical work, raise the possibility that the brain represents serial order by a domain-general neural code, following the principle of Competitive Queuing. However…
Brandon Wong, Brokoslaw Laschowski
Neural decoding can be viewed as a representation learning problem in which neural activity is mapped into an intermediate representation before downstream reconstruction. The choice of intermediate representation influences both performance and learning difficulty. Here we developed a novel framework for studying how…
Andrew Garrett Kurbis, Alex Mihailidis, Brokoslaw Laschowski
Decoding algorithms can be used to predict motor behaviour from patterns of neural activity. However, most studies rely on subject-optimized models, limiting generalization and scalability to novel subjects and tasks. Building on recent advances in deep learning and large-scale data, here we developed an EMG foundation…
Jannis Chemseddine, Gregor Kornhardt, Gabriele Steidl
We study the problem of learning generative models for discrete sequences in a continuous embedding space. Whereas prior approaches typically operate in Euclidean space or on the probability simplex, we instead work on the sphere $\mathbb S^{d-1}$. There the von Mises-Fisher (vMF) distribution induces a natural noise…
Hongjie Wu, Yiping Xie, Jiancheng Lv
Latent Flow Models have revolutionized compressed-space image synthesis, yet their application to high-fidelity inverse problems remains bottlenecked. In this paper, we trace this dilemma to a fundamental geometric limitation of pre-trained autoencoders, which we term \emph{First-Order Manifold Blindness}. Severe…
Yinhuan Huang, Hao Cao, Pu chen, Wenqi Guo + 1 more
Diffusion-based image compression methods, leveraging powerful generative priors, have demonstrated remarkable perceptual quality at ultra-low bitrates. However, adapting modern generative models to image compression often relies on carefully engineered conditioning or auxiliary branches, together with substantial…
Authors not listed
Physics-based coarse-grained (CG) models are widely used in (bio)molecular simulations, yet their parameterization remains challenging and labor-intensive. In this work, we demonstrate how recently developed gradient-based optimization methods can substantially accelerate the refinement of CG force field (FF)…
Ganchao Wei, Daniela de Albuquerque, Miles Martinez, Shiyang Pan + 1 more
While neuroscience experiments have repeatedly demonstrated the involvement of large populations of neurons in even simple behaviors, these studies have just as often reported that the collective dynamics of neural activity are approximately low-dimensional. As a result, methods for identifying low-dimensional latent…
Pengxi Fu, Zhen Wang, Jianxin Guo, Yushuai Zhang + 4 more
Modern communication systems increasingly leverage multiple information streams-including channel observations, statistical models, and contextual knowledge-to enhance decoding reliability. However, the varying and often unpredictable quality of these sources poses a critical challenge: rigid combination rules fail…
Wenbo Shi, Wenlong Xie, Jiashen Hu, Lishan Liu + 1 more
Future wireless networks require channel coding schemes that can provide high reliability, low latency, and strong adaptability under finite-blocklength and structurally heterogeneous transmission scenarios. Globally coupled low-density parity-check (GC-LDPC) codes are promising for such systems because their coupled…
Yikai Liu, Ming Chen, Guang Lin
Molecular dynamics (MD) provides a principled method for modeling equilibrium protein conformational energy landscapes, but its computational cost limits access to long timescales and larger protein systems. Recently, generative protein ensemble models and machine-learned coarse-grained force fields have emerged as…
Authors not listed
Fragment-based drug design (FBDD) has become a key approach in structure-based drug discovery, allowing researchers to systematically develop molecular fragments into potent ligands. Although recent generative AI models, such as diffusion-based approaches, show great potential for designing new molecules, applying them…