activity
20222025
most citedWeakly Supervised Two-Stage Training Scheme for Deep Video Fight Detection Model

2 citations · 4 across the 7 of their papers we have counts for

collaborators
Showing 2025Show all

5 papers · 1 filter

math.DS2025

Normal distribution of Lyapunov exponents of periodic orbits for expanding circle maps

Kostiantyn Drach, Zhi Fu, Vadim Kaloshin +2

For a smooth expanding circle map, we show that the empirical distribution of Lyapunov exponents of periodic points of any fixed period is close to normal, with an error that decre…

cs.IR2025

HyMiRec: A Hybrid Multi-interest Learning Framework for LLM-based Sequential Recommendation

Jingyi Zhou, Cheng Chen, Kai Zuo +5

Large language models (LLMs) have recently demonstrated strong potential for sequential recommendation. However, current LLM-based approaches face critical limitations in modeling…

cs.MM2025

Taming Modality Entanglement in Continual Audio-Visual Segmentation

Yuyang Hong, Qi Yang, Tao Zhang +5

Recently, significant progress has been made in multi-modal continual learning, aiming to learn new tasks sequentially in multi-modal settings while preserving performance on previ…

cs.IR2025

FinBERT2: A Specialized Bidirectional Encoder for Bridging the Gap in Finance-Specific Deployment of Large Language Models

Xuan Xu, Fufang Wen, Beilin Chu +7

In natural language processing (NLP), the focus has shifted from encoder-only tiny language models like BERT to decoder-only large language models(LLMs) such as GPT-3. However, LLM…

cs.HC2025

A Review of Behavioral Closed-Loop Paradigm from Sensing to Intervention for Ingestion Health

Jun Fang, Yanuo Zhou, Ka I Chan +8

Ingestive behavior plays a critical role in health, yet many existing interventions remain limited to static guidance or manual self-tracking. With the increasing integration of se…