Publications (16)
VAST: A Vision-Audio-Subtitle-Text Omni-Modality Foundation Model and Dataset
Sihan Chen, Handong Li, Qunbo Wang +4
Vision and text have been fully explored in contemporary video-text foundational models, while other modalities such as audio and subtitles in videos have not received sufficient a…
COSA: Concatenated Sample Pretrained Vision-Language Foundation Model
Sihan Chen, Xingjian He, Handong Li +3
Due to the limited scale and quality of video-text training corpus, most vision-language foundation models employ image-text datasets for pretraining and primarily focus on modelin…
AdaSpark: Adaptive Sparsity for Efficient Long-Video Understanding
Handong Li, Zikang Liu, Longteng Guo +10
Processing long-form videos with Video Large Language Models (Video-LLMs) is computationally prohibitive. Current efficiency methods often compromise fine-grained perception throug…
Thinking in Streaming Video
Zikang Liu, Longteng Guo, Handong Li +7
Real-time understanding of continuous video streams is essential for interactive assistants and multimodal agents operating in dynamic environments. However, most existing video re…
TimeThink: Reasoning with Time for Video LLMs
Handong Li, Longteng Guo, Zikang Liu +8
Video reasoning requires models to identify and verify temporally localized evidence within long video sequences. Recent Video Large Language Models (Video-LLMs) have shown promisi…
Explore the Limits of Omni-modal Pretraining at Scale
Yiyuan Zhang, Handong Li, Jing Liu +1
We propose to build omni-modal intelligence, which is capable of understanding any modality and learning universal representations. In specific, we propose a scalable pretraining p…
Research on Portfolio Liquidation Strategy under Discrete Times
Qixuan Luo, Yu Shi, Handong Li
This paper presents an optimal strategy for portfolio liquidation under discrete time conditions. We assume that N risky assets held will be liquidated according to the same time i…
Current induced anisotropic magnetoresistance in topological insulator films
Jian Wang, Handong Li, Cui-Zu Chang +7
Topological insulators are insulating in the bulk but possess spin-momentum locked metallic surface states protected by time-reversal symmetry. The existence of these surface state…
Tunable Semimetallic State in Compressive-strained SrIrO3 Films Revealed by Transport Behaviors
Lunyong Zhang, Qifeng Liang, Ye Xiong +11
Orthorhombic SrIrO3 is a typical spin-orbit-coupling correlated metal that shows diversified physical properties under the external stimuli. Here nonlinear Hall effect and weakly t…
A Method for Predicting VaR by Aggregating Generalized Distributions Driven by the Dynamic Conditional Score
Shijia Song, Handong Li
Constructing a more effective value at risk (VaR) prediction model has long been a goal in financial risk management. In this paper, we propose a novel parametric approach and prov…
Unveiling Early Warning Signals of Systemic Risks in Banks: A Recurrence Network-Based Approach
Shijia Song, Handong Li
Bank crisis is challenging to define but can be manifested through bank contagion. This study presents a comprehensive framework grounded in nonlinear time series analysis to ident…
Value-at-Risk forecasting model based on normal inverse Gaussian distribution driven by dynamic conditional score
Shijia Song, Handong Li
Under the framework of dynamic conditional score, we propose a parametric forecasting model for Value-at-Risk based on the normal inverse Gaussian distribution (Hereinafter NIG-DCS…
Interplay between topological insulators and superconductors
Jian Wang, Cui-Zu Chang, Handong Li +8
Topological insulators are insulating in the bulk but possess metallic surface states protected by time-reversal symmetry. Here, we report a detailed electronic transport study in…
Enhancing Vision-Language Pre-Training with Jointly Learned Questioner and Dense Captioner
Zikang Liu, Sihan Chen, Longteng Guo +3
Large pre-trained multimodal models have demonstrated significant success in a range of downstream tasks, including image captioning, image-text retrieval, visual question answerin…
Growth and band alignment of Bi2Se3 topological insulator on H-terminated Si(111) van der Waals surface
Handong Li, Lei Gao, Hui Li +4
The van der Waals epitaxy of single crystalline Bi2Se3 film was achieved on hydrogen passivated Si(111) (H:Si) substrate by physical vapor deposition. Valence band structures of Bi…
Breaking the Encoder Barrier for Seamless Video-Language Understanding
Handong Li, Yiyuan Zhang, Longteng Guo +2
Most Video-Large Language Models (Video-LLMs) adopt an encoder-decoder framework, where a vision encoder extracts frame-wise features for processing by a language model. However, t…