Publications (11)
Supercharging Packet-level Network Simulation of Large Model Training via Memoization and Fast-Forwarding
Fei Long, Kaihui Gao, Li Chen +6
Packet-level discrete-event simulation (PLDES) is a prevalent tool for evaluating detailed performance of large model training. Although PLDES offers high fidelity and generality,…
Task-Specific Distance Correlation Matching for Few-Shot Action Recognition
Fei Long, Yao Zhang, Jiaming Lv +2
Few-shot action recognition (FSAR) has recently made notable progress through set matching and efficient adaptation of large-scale pre-trained models. However, two key limitations…
TTCS: Test-Time Curriculum Synthesis for Self-Evolving
Chengyi Yang, Zhishang Xiang, Yunbo Tang +5
Test-Time Training offers a promising way to improve the reasoning ability of large language models (LLMs) by adapting the model using only the test questions. However, existing me…
DMA: Online RAG Alignment with Human Feedback
Yu Bai, Yukai Miao, Dawei Wang +9
Retrieval-augmented generation (RAG) systems often rely on static retrieval, limiting adaptation to evolving intent and content drift. We introduce Dynamic Memory Alignment (DMA),…
A Clustering Framework for Unsupervised and Semi-supervised New Intent Discovery
Hanlei Zhang, Hua Xu, Xin Wang +2
New intent discovery is of great value to natural language processing, allowing for a better understanding of user needs and providing friendly services. However, most existing met…
Joint Distribution Matters: Deep Brownian Distance Covariance for Few-Shot Classification
Jiangtao Xie, Fei Long, Jiaming Lv +2
Few-shot classification is a challenging problem as only very few training examples are given for each new task. One of the effective research lines to address this challenge focus…
Primary damage production in the presence of extended defects and growth of vacancy-type dislocation loops in hcp zirconium
Cong Dai, Fei Long, Peyman Saidi +3
Production rates in long-term predictive radiation damage accumulation models are generally considered independent of the material's microstructure for reactor components. In this…
Joint CNN and Transformer Network via weakly supervised Learning for efficient crowd counting
Fusen Wang, Kai Liu, Fei Long +3
Currently, for crowd counting, the fully supervised methods via density map estimation are the mainstream research directions. However, such methods need location-level annotation…
PyGWalker: On-the-fly Assistant for Exploratory Visual Data Analysis
Yue Yu, Leixian Shen, Fei Long +2
Exploratory visual data analysis tools empower data analysts to efficiently and intuitively explore data insights throughout the entire analysis cycle. However, the gap between com…
Unsupervised Multimodal Clustering for Semantics Discovery in Multimodal Utterances
Hanlei Zhang, Hua Xu, Fei Long +2
Discovering the semantics of multimodal utterances is essential for understanding human language and enhancing human-machine interactions. Existing methods manifest limitations in…
Beacon-enabled TDMA Ultraviolet Communication Network System Design and Realization
Yuchen Pan, Fei Long, Ping Li +5
Nonline of sight (NLOS) ultraviolet (UV) scattering communication can serve as a good candidate for outdoor optical wireless communication (OWC) in the cases of non-perfect transmi…