2 citations · 2 across the 7 of their papers we have counts for
7 papers
Trade in Minutes! Rationality-Driven Agentic System for Quantitative Financial Trading
Zifan Song, Kaitao Song, Guosheng Hu +5
Recent advancements in large language models (LLMs) and agentic systems have shown exceptional decision-making capabilities, revealing significant potential for autonomic finance.…
A Comprehensive Evaluation on Quantization Techniques for Large Language Models
Yutong Liu, Cairong Zhao, Guosheng Hu
For large language models (LLMs), post-training quantization (PTQ) significantly reduces memory and computational overhead. Despite rapid advancements, existing papers often lack e…
Cross-Modal Distillation For Widely Differing Modalities
Cairong Zhao, Yufeng Jin, Zifan Song +3
Deep learning achieved great progress recently, however, it is not easy or efficient to further improve its performance by increasing the size of the model. Multi-modal learning ca…
Toward Rich Video Human-Motion2D Generation
Ruihao Xi, Xuekuan Wang, Yongcheng Li +5
Generating realistic and controllable human motions, particularly those involving rich multi-character interactions, remains a significant challenge due to data scarcity and the co…
Cap2Sum: Learning to Summarize Videos by Generating Captions
Cairong Zhao, Chutian Wang, Zifan Song +3
With the rapid growth of video data on the internet, video summarization is becoming a very important AI technology. However, due to the high labelling cost of video summarization,…
StyleShot: A Snapshot on Any Style
Junyao Gao, Yanchen Liu, Yanan Sun +4
In this paper, we show that, a good style representation is crucial and sufficient for generalized style transfer without test-time tuning. We achieve this through constructing a s…
AlchemistCoder: Harmonizing and Eliciting Code Capability by Hindsight Tuning on Multi-source Data
Zifan Song, Yudong Wang, Wenwei Zhang +8
Open-source Large Language Models (LLMs) and their specialized variants, particularly Code LLMs, have recently delivered impressive performance. However, previous Code LLMs are typ…