Related papers: Fast Beam-Brainstorm: Few-Step Generative Site-Spe…
Generalized few-shot semantic segmentation (GFSS) aims to segment objects of both base and novel classes, using sufficient samples of base classes and few samples of novel classes. Representative GFSS approaches typically employ a two-phase…
We address a challenging lifelong few-shot image generation task for the first time. In this situation, a generative model learns a sequence of tasks using only a few samples per task. Consequently, the learned model encounters both…
Federated Learning faces significant challenges in statistical and system heterogeneity, along with high energy consumption, necessitating efficient client selection strategies. Traditional approaches, including heuristic and learning-based…
Channel knowledge map (CKM) is emerging as a critical enabler for environment-aware 6G networks, offering a site-specific database to significantly reduce pilot overhead. However, existing CKM construction methods typically rely on sparse…
State space models (SSMs) have high performance on long sequence modeling but require sophisticated initialization techniques and specialized implementations for high quality and runtime performance. We study whether a simple alternative…
Flow-based generative models, such as diffusion models and flow matching models, have achieved remarkable success in learning complex data distributions. However, a critical gap remains for their deployment in safety-critical domains: the…
We propose an efficient batching strategy for variable-length decoding on GPU architectures. During decoding, when candidates terminate or are pruned according to heuristics, our streaming approach periodically "refills" the batch before…
Ephemeral Fast Radio Bursts (FRBs) must be powered by some of the most energetic processes in the Universe. That makes them highly interesting in their own right and as precise probes for estimating cosmological parameters. This field thus…
Multi-modal fusion is of great significance in neuroscience which integrates information from different modalities and can achieve better performance than uni-modal methods in downstream tasks. Current multi-modal fusion methods in brain…
Prompt learning as a parameter-efficient method that has been widely adopted to adapt Vision-Language Models (VLMs) to downstream tasks. While hard-prompt design requires domain expertise and iterative optimization, soft-prompt methods rely…
Bridge models have been investigated in speech enhancement but are mostly single-task, with constrained general speech restoration (GSR) capability. In this work, we propose VoiceBridge, a one-step latent bridge model (LBM) for GSR, capable…
Federated Learning (FL) enables collaborative model training across decentralized clients without sharing private data. However, FL suffers from biased global models due to non-IID and long-tail data distributions. We propose…
Fast broadcasting (FB) is a popular near video-on-demand system where a video is divided into equal size segments those are repeatedly transmitted over a number of channels following a pattern. For user satisfaction, it is required to…
Non-autoregressive text to speech (TTS) models such as FastSpeech can synthesize speech significantly faster than previous autoregressive models with comparable quality. The training of FastSpeech model relies on an autoregressive teacher…
Distribution Matching Distillation (DMD) distills score-based generative models into efficient one-step generators, without requiring a one-to-one correspondence with the sampling trajectories of their teachers. Yet, the limited capacity of…
Recent developments demonstrate that parametric four-wave mixing (FWM) in high-Q microresonators is a highly promising and effective approach for optical frequency comb generation, with applications including spectroscopy, optical clocks,…
This letter presents a novel design method for switchable dual band transmissive frequency selective surface (FSS). The proposed FSS possesses characteristics of maintaining passband characteristics at high frequencies, while switching from…
Generating reliable pseudo masks from image-level labels is challenging in the weakly supervised semantic segmentation (WSSS) task due to the lack of spatial information. Prevalent class activation map (CAM)-based solutions are challenged…
Extremely large-scale multiple-input multiple-output (XL-MIMO) systems are capable of improving spectral efficiency by employing far more antennas than conventional massive MIMO at the base station (BS). However, beam training in multiuser…
In this paper we address the problem of performing statistical inference for large scale data sets i.e., Big Data. The volume and dimensionality of the data may be so high that it cannot be processed or stored in a single computing node. We…