Publications (37)
Dual prototype attentive graph network for cross-market recommendation
Li Fan, Menglin Kong, Yang Xiang +2
Cross-market recommender systems (CMRS) aim to utilize historical data from mature markets to promote multinational products in emerging markets. However, existing CMRS approaches…
Chain-of-Thought Enhanced Shallow Transformers for Wireless Symbol Detection
Li Fan, Peng Wang, Jing Yang +1
Transformers have shown potential in solving wireless communication problems, particularly via in-context learning (ICL), where models adapt to new tasks through prompts without re…
Mobile Robot Navigation in Complex Polygonal Workspaces Using Conformal Navigation Transformations
Li Fan, Jianchang Liu
This work proposes a novel transformation termed the conformal navigation transformation to achieve collision-free navigation of a robot in a workspace populated with arbitrary pol…
Time Dependent Scattering from a Grating
Li Fan, Peter Monk
Computing the electromagnetic field due to a periodic grating is critical for assessing the performance of thin film solar voltaic devices. In this paper we investigate the computa…
Using Neural Networks for Fast SAR Roughness Estimation of High Resolution Images
Li Fan, Jeova Farias Sales Rocha Neto
The analysis of Synthetic Aperture Radar (SAR) imagery is an important step in remote sensing applications, and it is a challenging problem due to its inherent speckle noise. One t…
Topological model for derived category associated to sphere with four binaries
Jianmin Chen, Li Fan, Yu Qiu +1
We construct a geometric model for the derived category of the weighted projective line of type , given by a graded sphere with four binaries. Precise…
Categorical realization of collapsing subsurfaces and perverse schobers
Li Fan, Suiqi Lu
We study the categorification of collapsed Riemann surfaces with quadratic differentials allowing arbitrary order zeros and poles via the Verdier quotient. We establish an isomorph…
Topological model for q-deformed rational number and categorification
Li Fan, Yu Qiu
Let be a bigraded 3-decorated disk with an arc system . We associate a bigraded simple closed arc on to any…
Eight-channel reconfigurable microring filters with tunable frequency, extinction ratio and bandwidth
Hao Shen, Maroof H. Khan, Li Fan +5
We demonstrate an eight-channel reconfigurable optical filter on a silicon chip consisting of cascaded microring resonators and integrated compact heaters. With an embedded Mach-Ze…
A CMOS compatible microring-based on-chip isolator with 18dB optical isolation
Li Fan, Jian Wang, Hao Shen +4
We demonstrate strong optical nonreciprocity in microring add-drop filters with asymmetric input and output coupling coefficients. Up to 18dB isolation was achieved with a silicon-…
HierarchicalKV: A GPU Hash Table with Cache Semantics for Continuous Online Embedding Storage
Haidong Rong, Jiashu Yao, Matthias Langer +12
Traditional GPU hash tables preserve every inserted key -- a dictionary assumption that wastes scarce High Bandwidth Memory (HBM) when embedding tables routinely exceed single-GPU…
Drop-port study of microresonator frequency combs: power transfer and time-domain characterization
Pei-Hsun Wang, Yi Xuan, Li Fan +6
We use a drop-port geometry to study power transfer in silicon nitride on-chip microresonator frequency comb generators. In sharp contrast with the traditional transmission geometr…
Federated Linear Bandits with Finite Adversarial Actions
Li Fan, Ruida Zhou, Chao Tian +1
We study a federated linear bandits model, where clients communicate with a central server to solve a linear contextual bandits problem with finite adversarial action sets that…
Dynamic Knowledge Exchange and Dual-diversity Review: Concisely Unleashing the Potential of a Multi-Agent Research Team
Weilun Yu, Shixiang Tang, Yonggui Huang +7
Scientific progress increasingly relies on effective collaboration among researchers, a dynamic that large language models (LLMs) have only begun to emulate. While recent LLM-based…
Swarm-Inspired Generation of Collective Behaviors in Graph Dynamical Systems
Ji Chen, Song Chen, Chengzhang Gong +2
Collective behavior arises when locally interacting units produce coordinated global organization, from synchronization in dynamical systems to task-relevant information flow on gr…
Discriminative Representation Learning for Clinical Prediction
Yang Zhang, Li Fan, Samuel Lawrence +1
Foundation models in healthcare have largely adopted self supervised pretraining objectives inherited from natural language processing and computer vision, emphasizing reconstructi…
Rapidly reconfigurable radio-frequency arbitrary waveforms synthesized on a CMOS photonic chip
Jian Wang, Hao Shen, Li Fan +9
Photonic methods of radio-frequency waveform generation and processing provide performance and flexibility over electronic methods due to the ultrawide bandwidth offered by the opt…
A New Era in Human Factors Engineering: A Survey of the Applications and Prospects of Large Multimodal Models
Li Fan, Lee Ching-Hung, Han Su +3
In recent years, the potential applications of Large Multimodal Models (LMMs) in fields such as healthcare, social psychology, and industrial design have attracted wide research at…
Skeleton Supervised Airway Segmentation
Mingyue Zhao, Han Li, Li Fan +3
Fully-supervised airway segmentation has accomplished significant triumphs over the years in aiding pre-operative diagnosis and intra-operative navigation. However, full voxel-leve…
Perfecting Imperfect Physical Neural Networks with Transferable Robustness using Sharpness-Aware Training
Tengji Xu, Zeyu Luo, Shaojie Liu +5
AI models are essential in science and engineering, but recent advances are pushing the limits of traditional digital hardware. To address these limitations, physical neural networ…
Decision Feedback In-Context Learning for Wireless Symbol Detection
Li Fan, Wei Shen, Jing Yang +1
Pre-trained Transformers, through in-context learning (ICL), have demonstrated exceptional capabilities to adapt to new tasks using example prompts without model update. Transforme…
A Hierarchical Quantized Tokenization Framework for Task-Adaptive Graph Representation Learning
Yang Xiang, Li Fan, Chenke Yin +2
Foundation models in language and vision benefit from a unified discrete token interface that converts raw inputs into sequences for scalable pre-training and inference. For graphs…
Spectrum-Adapted Polynomial Approximation for Matrix Functions
Li Fan, David I Shuman, Shashanka Ubaru +1
We propose and investigate two new methods to approximate for large, sparse, Hermitian matrices . The main idea behind both methods is to first estimat…
A Silicon Optical Transistor
Leo T. Varghese, Li Fan, Jian Wang +5
A fundamental road block for all-optical information processing is the difficulty in realizing a silicon optical transistor with the ability to provide optical gain, input output i…
RDSA: A Robust Deep Graph Clustering Framework via Dual Soft Assignment
Yang Xiang, Li Fan, Tulika Saha +4
Graph clustering is an essential aspect of network analysis that involves grouping nodes into separate clusters. Recent developments in deep learning have resulted in graph cluster…
Dg enhanced orbit categories and applications
Li Fan, Bernhard Keller, Yu Qiu
Our aim in this paper is to prove two results related to the three constructions of cluster categories: as orbit categories, as singularity categories and as cosingularity categori…
PENet: Towards Precise and Efficient Image Guided Depth Completion
Mu Hu, Shuling Wang, Bin Li +3
Image guided depth completion is the task of generating a dense depth map from a sparse depth map and a high quality image. In this task, how to fuse the color and depth modalities…
Priority-aware Gray-box Placement of Virtual Machines in Cloud Platforms
Xia Liu, Li Fan
Virtual machine (VM) placement is very important for cloud platforms. While techniques, such as live virtual machine migration, are very useful to balance the load in the data cent…
Harnessing Light for Cold-Start Recommendations: Leveraging Epistemic Uncertainty to Enhance Performance in User-Item Interactions
Yang Xiang, Li Fan, Chenke Yin +2
Most recent paradigms of generative model-based recommendation still face challenges related to the cold-start problem. Existing models addressing cold item recommendations mainly…
GDDS: Pulmonary Bronchioles Segmentation with Group Deep Dense Supervision
Mingyue Zhao, Shang Zhao, Quan Quan +4
Airway segmentation, especially bronchioles segmentation, is an important but challenging task because distal bronchus are sparsely distributed and of a fine scale. Existing neural…
Uncertainty-Aware Semantic Decoding for LLM-Based Sequential Recommendation
Chenke Yin, Li Fan, Jia Wang +4
Large language models have been widely applied to sequential recommendation tasks, yet during inference, they continue to rely on decoding strategies developed for natural language…
Conformal Navigation Transformations with Application to Robot Navigation in Complex Workspaces
Li Fan, Jianchang Liu, Wenle Zhang +1
Navigation functions provide both path and motion planning, which can be used to ensure obstacle avoidance and convergence in the sphere world. When dealing with complex and realis…
Beyond Terabit/s Integrated Neuromorphic Photonic Processor for DSP-Free Optical Interconnects
Benshan Wang, Qiarong Xiao, Tengji Xu +5
The rapid expansion of generative AI drives unprecedented demands for high-performance computing. Training large-scale AI models now requires vast interconnected GPU clusters acros…
Implicit Reasoning in Large Language Models: A Comprehensive Survey
Jindong Li, Yali Fu, Li Fan +6
Large Language Models (LLMs) have demonstrated strong generalization across a wide range of tasks. Reasoning with LLMs is central to solving multi-step problems and complex decisio…
Decision Feedback In-Context Symbol Detection over Block-Fading Channels
Li Fan, Jing Yang, Cong Shen
Pre-trained Transformers, through in-context learning (ICL), have demonstrated exceptional capabilities to adapt to new tasks using example prompts \textit{without model update}. T…
FDD Massive MIMO Uplink and Downlink Channel Reciprocity Properties: Full or Partial Reciprocity?
Zhimeng Zhong, Li Fan, Shibin Ge
One challenge for FDD massive MIMO communication system is how to obtain the downlink channel state information (CSI) at the base station. Except for traditional codebook feedback…
Uplink Achievable Rate for Massive MIMO with Low-Resolution ADC
Li Fan, Shi Jin, Chao-Kai Wen +1
In this letter, we derive an approximate analytical expression for the uplink achievable rate of a massive multi-input multi-output (MIMO) antenna system when finite precision anal…