2043 papers
This survey systematically reviews decentralized federated learning methods from 2018 to early 2026, categorizing them into traditional distributed and blockchain-based architectures, proposing a unified challenge-driven taxonomy, and outlining future research directions to address security, privacy, and system-level trade-offs in coordinator-free settings.
XConv is a drop-in replacement for standard convolutional layers that significantly reduces memory usage during training by storing compressed activations and approximating weight gradients via randomized trace estimation, while maintaining performance comparable to exact gradient methods without imposing architectural constraints or requiring codebase modifications.
The paper proposes C2FMAE, a coarse-to-fine masked autoencoder that resolves the tension between global semantics and local details in self-supervised learning by employing a cascaded decoder and progressive masking curriculum on a newly constructed multi-granular dataset to achieve hierarchical visual understanding and superior performance across various vision tasks.
This paper identifies that deep neural networks frequently encode the absence of concepts to drive neuron activation—a phenomenon largely overlooked by standard explainable AI methods—and proposes simple extensions to attribution and feature visualization techniques to effectively reveal and leverage these "missing" concepts for better model interpretation and debiasing.
This paper establishes global universal approximation theorems for path-dependent functionals on spaces of piecewise linear paths using linear functionals of discrete-time signatures, demonstrating their applicability to Brownian motion-driven systems such as random and stochastic ordinary differential equations.
This paper introduces SparseLoom, a system that employs model stitching to recombine subgraphs from sparse models without re-training, thereby significantly improving throughput, reducing memory overhead, and lowering Service Level Objective violation rates for multi-DNN inference on edge SoCs compared to state-of-the-art systems.
The paper introduces Sensor-Conditioned Diffusion Policies (SCDP), a novel framework that enables robust humanoid locomotion using only onboard sensors by distilling privileged full-body knowledge through mixed-observation training and specialized denoising techniques, successfully achieving near-perfect simulation performance and real-world deployment on a G1 robot without explicit state estimation.
This paper introduces a-TMFG, a scalable algorithm that overcomes the memory and computational limitations of traditional Triangulated Maximally Filtered Graphs by leveraging k-Nearest Neighbors and on-the-fly correlation estimation to construct sparse graphs from massive datasets.
This paper introduces BRACE, a parameter-free algorithm for multi-armed bandits with noncompliance that simultaneously optimizes recommendation welfare and treatment learning by performing certified instrumental variable inversion only when identification is strong, otherwise providing honest structural intervals to navigate the trade-offs between mediated and direct-control regimes.
This paper demonstrates that language models can covertly acquire behavioral traits from a teacher model through "subliminal learning" on faithful paraphrases, where the student adopts the teacher's preferences even when the paraphrased content is semantically unrelated or explicitly contradicts those preferences, rendering content-based inspection ineffective.
TrainDeeploy is a novel framework that enables efficient, parameter-efficient on-device fine-tuning of both CNN and Transformer models on ultra-low-power, memory-constrained RISC-V SoCs, achieving significant reductions in memory usage and computational overhead while supporting end-to-end training at the extreme edge.
This paper proposes VSOPINN, a novel framework that integrates differentiable Voronoi tessellation with Physics-Informed Neural Networks to enable end-to-end optimization of sensor placement, thereby significantly enhancing the accuracy and robustness of high-fidelity flow field reconstruction under sparse measurements and sensor failures.
This paper advances the theoretical understanding of Gaussian process Thompson sampling (GP-TS) in Bayesian optimization by establishing a regret lower bound, deriving improved upper bounds for cumulative regret and the second moment of regret, and providing expected lenient regret bounds that address gaps in existing analyses compared to GP-UCB.
This paper proposes a unified, target-gradient-free generative sampling framework that enforces time-reversibility constraints via Maximum Mean Discrepancy minimization between forward and backward Markov trajectories, enabling efficient sampling from complex continuous, discrete, and hybrid distributions using only energy evaluations.
MM-Zero is the first RL-based framework to enable Vision Language Models to self-evolve from zero data by employing a multi-role system (Proposer, Coder, and Solver) trained with Group Relative Policy Optimization to generate visual concepts, render them via code, and solve multimodal reasoning tasks without any seed images.
This paper addresses the reproducibility crisis in music source separation by attempting to replicate the Band-Split RNN model, ultimately releasing an optimized version with improved performance and publicly available code to advocate for more transparent and sustainable research practices.
This paper verifies that persistent observers in causally invariant hypergraph substrates satisfy the Conant-Ashby Good Regulator Theorem, thereby necessitating internal models that lead to natural gradient descent as the unique learning rule and yielding a model-dependent closed-form formula for Vanchurin's regime parameter with a quantum-classical threshold at .
This paper proposes a novel integrated online reliability prediction framework for satellite electronics that combines a Wiener process-based degradation model with a two-stage adaptive active learning strategy to significantly improve prediction accuracy while reducing data requirements under limited and variable operational conditions.
This paper introduces Quality over Quantity (QoQ), a systematic framework that leverages influence functions to automatically curate high-quality robot learning demonstrations by quantifying each sample's contribution to reducing validation loss, thereby significantly improving policy performance over manual or heuristic data selection methods.
This paper presents FlexServe, a high-performance and secure LLM serving system for mobile devices that leverages a novel Flexible Resource Isolation mechanism to overcome the significant overhead of ARM TrustZone, achieving up to 10.05× faster time-to-first-token and 24.30× faster multi-model workflow execution compared to baseline designs.