7 citations · 12 across the 10 of their papers we have counts for
12 papers
Forking: Sudden Overfitting Under Replay
Shanbin Yu, Shaoyang Guo, Haoran Zhao +2
This paper studies forking, a generalization failure discovered in NanoGPT autoresearch. Under data replay, models with an over-encoding n-gram memory branch show a sharp separatio…
Why Do Conventional World Models Fail to Learn Cellular Automata?
Shaoyang Guo, Ziming Liu
Although conventional world models - auto-regressive or diffusion models based on transformers or convolutional networks - may learn surface statistics of world dynamics, can they…
Epsilon: Exploring Comprehensive Visual-Semantic Projection for Multi-Label Zero-Shot Learning
Ziming Liu, Jingcai Guo, Song Guo +1
This paper investigates a challenging problem of zero-shot learning in the multi-label scenario (MLZSL), wherein the model is trained to recognize multiple unseen classes within a…
ParsNets: A Parsimonious Orthogonal and Low-Rank Linear Networks for Zero-Shot Learning
Jingcai Guo, Qihua Zhou, Ruibing Li +5
This paper provides a novel parsimonious yet efficient design for zero-shot learning (ZSL), dubbed ParsNets, where we are interested in learning a composition of on-device friendly…
GBE-MLZSL: A Group Bi-Enhancement Framework for Multi-Label Zero-Shot Learning
Ziming Liu, Jingcai Guo, Xiaocheng Lu +3
This paper investigates a challenging problem of zero-shot learning in the multi-label scenario (MLZSL), wherein, the model is trained to recognize multiple unseen classes within a…
DRPT: Disentangled and Recurrent Prompt Tuning for Compositional Zero-Shot Learning
Xiaocheng Lu, Ziming Liu, Song Guo +4
Compositional Zero-shot Learning (CZSL) aims to recognize novel concepts composed of known knowledge without training samples. Standard CZSL either identifies visual primitives or…
Decomposed Soft Prompt Guided Fusion Enhancing for Compositional Zero-Shot Learning
Xiaocheng Lu, Ziming Liu, Song Guo +1
Compositional Zero-Shot Learning (CZSL) aims to recognize novel concepts formed by known states and objects during training. Existing methods either learn the combined state-object…
ProCC: Progressive Cross-primitive Compatibility for Open-World Compositional Zero-Shot Learning
Fushuo Huo, Wenchao Xu, Song Guo +4
Open-World Compositional Zero-shot Learning (OW-CZSL) aims to recognize novel compositions of state and object primitives in images with no priors on the compositional space, which…
Fed-FSNet: Mitigating Non-I.I.D. Federated Learning via Fuzzy Synthesizing Network
Jingcai Guo, Song Guo, Jie Zhang +1
Federated learning (FL) has emerged as a promising privacy-preserving distributed machine learning framework recently. It aims at collaboratively learning a shared global model by…
Anchor Sampling for Federated Learning with Partial Client Participation
Feijie Wu, Song Guo, Zhihao Qu +3
Compared with full client participation, partial client participation is a more practical scenario in federated learning, but it may amplify some challenges in federated learning,…
Towards Unbiased Multi-label Zero-Shot Learning with Pyramid and Semantic Attention
Ziming Liu, Song Guo, Jingcai Guo +2
Multi-label zero-shot learning extends conventional single-label zero-shot learning to a more realistic scenario that aims at recognizing multiple unseen labels of classes for each…
From Deterioration to Acceleration: A Calibration Approach to Rehabilitating Step Asynchronism in Federated Optimization
Feijie Wu, Song Guo, Haozhao Wang +4
In the setting of federated optimization, where a global model is aggregated periodically, step asynchronism occurs when participants conduct model training by efficiently utilizin…