Institution profile

Tongji University

Academic institutionasia · cn
Official website
Research library1,481linked papers
Opportunities0open roles
Selected work

Representative Papers

Fog Intelligence for Network Anomaly Detection

Mar 01, 2020IEEE Network

Detecting anomalous behaviors in large-scale mobile communication networks is challenging due to the high dimensionality and distributed nature of monitoring data. Method: This paper proposes a fog-intelligence architecture that integrates lightweight edge inference with cloud-based collaborative learning. It innovatively unifies federated learning, distributed machine learning, and edge computing to jointly address scalability, privacy preservation, and real-time responsiveness—overcoming deployment bottlenecks of conventional centralized models in wireless networks. Contribution/Results: Through lightweight model design and cross-layer cooperative optimization, the architecture significantly improves both timeliness and accuracy of anomaly detection. It achieves millisecond-level response and high-precision identification across networks with up to ten million endpoints, enabling real-time, secure, and scalable intelligent network management.

15 citationsRead paper

Data-Driven Merton's Strategies via Policy Randomization

Dec 19, 2023

This paper addresses the Merton expected utility maximization problem in an incomplete market with fully unknown dynamics: the market comprises a stock and latent state-factor processes, while investors observe only prices and instantaneous volatility—rendering factor dynamics and market parameters unidentifiable. We propose a novel continuous-time reinforcement learning (RL) framework that, for the first time, employs Gaussian policy randomization as an analytical tool—not merely for exploration—and rigorously prove that the randomized policy’s mean coincides with the optimal control of the original problem, thereby bridging RL and classical portfolio theory. We design online and offline actor-critic algorithms integrating policy improvement theorems with randomized policy analysis. Under stochastic volatility, our method substantially outperforms conventional parametric interpolation approaches. Both simulation studies and empirical tests confirm its robustness and capacity to generate alpha.

10 citations1 influentialRead paper

LLM2CLIP: Powerful Language Model Unlocks Richer Visual Representation

Nov 07, 2024arXiv.org

To address CLIP’s limitations in comprehending long, complex image captions and achieving fine-grained cross-modal alignment, this paper proposes a lightweight, LLM-augmented framework. Methodologically, it introduces (1) a novel caption-to-caption contrastive fine-tuning paradigm that circumvents adaptation challenges arising from LLMs’ autoregressive nature; (2) freezing the CLIP visual encoder while enhancing only the text branch via LLM integration and parameter-efficient tuning; and (3) preserving the original visual backbone—eliminating architectural modifications and substantially reducing training overhead. Evaluated on zero-shot cross-modal retrieval, cross-lingual retrieval, and multimodal large language model pretraining, the method consistently outperforms CLIP, EVA02, and SigLIP2. Notably, it achieves nearly 4× faster training than LoRA while maintaining superior accuracy.

7 citations2 influentialRead paper

On Efficient Variants of Segment Anything Model: A Survey

Oct 07, 2024arXiv.org

While the Segment Anything Model (SAM) exhibits strong generalization capability, its substantial computational overhead hinders deployment on resource-constrained edge devices. This work presents a systematic survey of efficient SAM variants tailored for edge deployment. We introduce the first unified evaluation framework spanning diverse hardware platforms—including CPU, GPU, and Edge TPU—and conduct joint accuracy–latency–memory benchmarking on COCO and SA-1B. Our analysis categorizes acceleration techniques along six technical axes: model pruning, knowledge distillation, lightweight attention mechanisms, quantization, module substitution, and hardware-aware compilation—characterizing their Pareto-optimal trade-offs. The core contributions are: (1) an open-source, fully reproducible edge-SAM benchmark; and (2) empirical insights into the applicability domains and fundamental accuracy-efficiency trade-offs of each acceleration strategy—providing both theoretical foundations and practical guidelines for designing lightweight vision foundation models.

7 citationsRead paper

DE3-BERT: Distance-Enhanced Early Exiting for BERT based on Prototypical Networks

Feb 03, 2024arXiv.org

Existing BERT early-exit methods rely solely on per-sample local signals (e.g., entropy) to determine exit decisions, neglecting inter-class global structure—leading to biased reliability estimation and suboptimal exit choices. Method: This work introduces prototype networks into early-exit mechanisms for the first time, proposing a distance-enhanced reliability assessment paradigm that jointly models local entropy and Euclidean distance to class prototypes. A dual-signal, synergistic hybrid gating strategy is designed and integrated into BERT’s hierarchical inference architecture—requiring zero additional parameters or computational overhead. Contribution/Results: The method achieves significant improvements over state-of-the-art approaches on the GLUE benchmark across multiple acceleration ratios, consistently attaining higher accuracy. It exhibits strong generalization across diverse tasks and datasets, while offering enhanced interpretability through geometrically grounded exit decisions based on prototype distances and uncertainty.

6 citations1 influentialRead paper
Recent publications

Latest Papers