Zobrazeno 1 - 10
of 10 276
pro vyhledávání: '"LI, Shen"'
Semi-supervised learning (SSL) has made notable advancements in medical image segmentation (MIS), particularly in scenarios with limited labeled data and significantly enhancing data utilization efficiency. Previous methods primarily focus on complex
Externí odkaz:
http://arxiv.org/abs/2411.13147
This paper shows a proof-of-concept that, given a typical 3-channel images but in a randomly permuted channel order, a model (termed as Chanel-Orderer) with ad-hoc inductive biases in terms of both architecture and loss functions can accurately predi
Externí odkaz:
http://arxiv.org/abs/2411.13021
Quantization stands as a pivotal technique for large language model (LLM) serving, yet it poses significant challenges particularly in achieving effective low-bit quantization. The limited numerical mapping makes the quantized model produce a non-tri
Externí odkaz:
http://arxiv.org/abs/2411.07762
Large language models achieve exceptional performance on various downstream tasks through supervised fine-tuning. However, the diversity of downstream tasks and practical requirements makes deploying multiple full-parameter fine-tuned models challeng
Externí odkaz:
http://arxiv.org/abs/2410.08666
Autor:
Sheng, Yajie, Chen, Bin, Lei, Yi, Deng, Jingxin, Xu, Jiwei, Fu, Mengfan, Zhuge, Qunbi, Li, Shen
Performance of concatenated multilevel coding with probabilistic shaping (PS) and Voronoi constellations (VCs) is analysed over AWGN channel. Numerical results show that VCs provide up to 1.3 dB SNR gains over PS-QAM with CCDM blocklength of 200.
Externí odkaz:
http://arxiv.org/abs/2409.20041
Autor:
Li, Shen, Xu, Jianqing, Wu, Jiaying, Xiong, Miao, Deng, Ailin, Ji, Jiazhen, Huang, Yuge, Feng, Wenjie, Ding, Shouhong, Hooi, Bryan
Synthetic face recognition (SFR) aims to generate synthetic face datasets that mimic the distribution of real face data, which allows for training face recognition models in a privacy-preserving manner. Despite the remarkable potential of diffusion m
Externí odkaz:
http://arxiv.org/abs/2409.17576
Interactive preference learning systems present humans with queries as pairs of options; humans then select their preferred choice, allowing the system to infer preferences from these binary choices. While binary choice feedback is simple and widely
Externí odkaz:
http://arxiv.org/abs/2409.05798
Aligned LLMs are secure, capable of recognizing and refusing to answer malicious questions. However, the role of internal parameters in maintaining such security is not well understood yet, further these models can be vulnerable to security degradati
Externí odkaz:
http://arxiv.org/abs/2408.17003
Offline reinforcement learning (RL) can learn optimal policies from pre-collected offline datasets without interacting with the environment, but the sampled actions of the agent cannot often cover the action distribution under a given state, resultin
Externí odkaz:
http://arxiv.org/abs/2406.09089
The advent of pre-trained large language models (LLMs) has revolutionized various natural language processing tasks. These models predominantly employ an auto-regressive decoding mechanism that utilizes Key-Value (KV) caches to eliminate redundant ca
Externí odkaz:
http://arxiv.org/abs/2406.07056