97 citations · 312 across the 45 of their papers we have counts for
46 papers
Fast Cross-Scenario Adaptation of CSI Models via Channel Conditional Parameter Generation
Xudong Zou, Siyu Wu, Zunlei Feng +4
Deep learning has shown strong potential for massive multiple-input multiple-output (Massive MIMO) physical-layer tasks, including channel state information (CSI) feedback and chan…
Diffusion Model Quantization: A Review
Qian Zeng, Chenggong Hu, Mingli Song +1
Recent success of large text-to-image models has empirically underscored the exceptional performance of diffusion models in generative tasks. To facilitate their efficient deployme…
Reinforced Model Merging
Jiaqi Han, Jingwen Ye, Shunyu Liu +4
The success of large language models has garnered widespread attention for model merging techniques, especially training-free methods which combine model capabilities within the pa…
Boosting MLLM Reasoning with Text-Debiased Hint-GRPO
Qihan Huang, Weilong Dai, Jinlong Liu +6
MLLM reasoning has drawn widespread research for its excellent problem-solving capability. Current reasoning methods fall into two types: PRM, which supervises the intermediate rea…
Holistic Semantic Representation for Navigational Trajectory Generation
Ji Cao, Tongya Zheng, Qinghong Guo +6
Trajectory generation has garnered significant attention from researchers in the field of spatio-temporal analysis, as it can generate substantial synthesized human mobility trajec…
Training-free Heterogeneous Model Merging
Zhengqi Xu, Han Zheng, Jie Song +2
Model merging has attracted significant attention as a powerful paradigm for model reuse, facilitating the integration of task-specific models into a singular, versatile framework…
A Large-scale Universal Evaluation Benchmark For Face Forgery Detection
Yijun Bei, Hengrui Lou, Jinsong Geng +5
With the rapid development of AI-generated content (AIGC) technology, the production of realistic fake facial images and videos that deceive human visual perception has become poss…
A Comprehensive Study of Structural Pruning for Vision Models
Changhao Li, Haoling Li, Mengqi Xue +6
Structural pruning has emerged as a promising approach for producing more efficient models. Nevertheless, the community suffers from a lack of standardized benchmarks and metrics,…
Transmission Interface Power Flow Adjustment: A Deep Reinforcement Learning Approach based on Multi-task Attribution Map
Shunyu Liu, Wei Luo, Yanzhen Zhou +5
Transmission interface power flow adjustment is a critical measure to ensure the security and economy operation of power systems. However, conventional model-based adjustment schem…
On the Concept Trustworthiness in Concept Bottleneck Models
Qihan Huang, Jie Song, Jingwen Hu +3
Concept Bottleneck Models (CBMs), which break down the reasoning process into the input-to-concept mapping and the concept-to-label prediction, have garnered significant attention…
Training-Free Pretrained Model Merging
Zhengqi Xu, Ke Yuan, Huiqiong Wang +3
Recently, model merging techniques have surfaced as a solution to combine multiple single-talent models into a single multi-talent model. However, previous endeavors in this field…
Disentangled Condensation for Large-scale Graphs
Zhenbang Xiao, Yu Wang, Shunyu Liu +4
Graph condensation has emerged as an intriguing technique to save the expensive training costs of Graph Neural Networks (GNNs) by substituting a condensed small graph with the orig…
Powerformer: A Section-adaptive Transformer for Power Flow Adjustment
Kaixuan Chen, Wei Luo, Shunyu Liu +6
In this paper, we present a novel transformer architecture tailored for learning robust power system state representations, which strives to optimize power dispatch for the power f…
Agent-Aware Training for Agent-Agnostic Action Advising in Deep Reinforcement Learning
Yaoquan Wei, Shunyu Liu, Jie Song +4
Action advising endeavors to leverage supplementary guidance from expert teachers to alleviate the issue of sampling inefficiency in Deep Reinforcement Learning (DRL). Previous age…
ModelGiF: Gradient Fields for Model Functional Distance
Jie Song, Zhengqi Xu, Sai Wu +2
The last decade has witnessed the success of deep learning and the surge of publicly released trained models, which necessitates the quantification of the model functional distance…
Adversarial Erasing with Pruned Elements: Towards Better Graph Lottery Ticket
Yuwen Wang, Shunyu Liu, Kaixuan Chen +5
Graph Lottery Ticket (GLT), a combination of core subgraph and sparse subnetwork, has been proposed to mitigate the computational cost of deep Graph Neural Networks (GNNs) on large…
Curricular Subgoals for Inverse Reinforcement Learning
Shunyu Liu, Yunpeng Qing, Shuqi Xu +6
Inverse Reinforcement Learning (IRL) aims to reconstruct the reward function from expert demonstrations to facilitate policy learning, and has demonstrated its remarkable success i…
Improving Expressivity of GNNs with Subgraph-specific Factor Embedded Normalization
Kaixuan Chen, Shunyu Liu, Tongtian Zhu +5
Graph Neural Networks (GNNs) have emerged as a powerful category of learning architecture for handling graph-structured data. However, existing GNNs typically ignore crucial struct…
Message-passing selection: Towards interpretable GNNs for graph classification
Wenda Li, Kaixuan Chen, Shunyu Liu +5
In this paper, we strive to develop an interpretable GNNs' inference paradigm, termed MSInterpreter, which can serve as a plug-and-play scheme readily applicable to various GNNs' b…
Lookaround Optimizer: steps around, 1 step average
Jiangtao Zhang, Shunyu Liu, Jie Song +3
Weight Average (WA) is an active research topic due to its simplicity in ensembling deep networks and the effectiveness in promoting generalization. Existing weight average approac…
Decentralized SGD and Average-direction SAM are Asymptotically Equivalent
Tongtian Zhu, Fengxiang He, Kaixuan Chen +2
Decentralized stochastic gradient descent (D-SGD) allows collaborative learning on massive devices simultaneously without the control of a central server. However, existing theorie…
Improved Projection-free Online Continuous Submodular Maximization
Yucheng Liao, Yuanyu Wan, Chang Yao +1
We investigate the problem of online learning with monotone and continuous DR-submodular reward functions, which has received great attention recently. To efficiently handle this p…
Is Centralized Training with Decentralized Execution Framework Centralized Enough for MARL?
Yihe Zhou, Shunyu Liu, Yunpeng Qing +4
Centralized Training with Decentralized Execution (CTDE) has recently emerged as a popular framework for cooperative Multi-Agent Reinforcement Learning (MARL), where agents can use…
Temporal Aggregation and Propagation Graph Neural Networks for Dynamic Representation
Tongya Zheng, Xinchao Wang, Zunlei Feng +6
Temporal graphs exhibit dynamic interactions between nodes over continuous time, whose topologies evolve with time elapsing. The whole temporal neighborhood of nodes reveals the va…