6 papers
Enhancing Few-Shot Out-of-Distribution Detection via the Refinement of Foreground and Background
Tianyu Li, Zongqian Wu, Songyue Cai +2
CLIP-based foreground-background (FG-BG) decomposition methods have demonstrated remarkable effectiveness in improving few-shot out-of-distribution (OOD) detection performance. How…
Mitigating Strategy-Selection Bias in Reasoning for More Effective Test-Time Scaling
Zongqian Wu, Baoduo Xu, Tianyu Li +3
Test-time scaling (TTS) has been shown to improve the performance of large language models (LLMs) by sampling and aggregating diverse reasoning paths. However, existing research ha…
Rethinking Chain-of-Thought from the Perspective of Self-Training
Zongqian Wu, Baoduo Xu, Ruochen Cui +3
Chain-of-thought (CoT) reasoning has emerged as an effective approach for activating latent capabilities in LLMs. Interestingly, we observe that both CoT reasoning and self-trainin…
Is Depth All You Need? An Exploration of Iterative Reasoning in LLMs
Zongqian Wu, Tianyu Li, Baoduo Xu +4
Deep iterative chain-of-thought (CoT) reasoning enables LLMs to tackle complex tasks by progressively activating relevant pre-trained knowledge. However, it faces challenges in ens…
MMGPL: Multimodal Medical Data Analysis with Graph Prompt Learning
Liang Peng, Songyue Cai, Zongqian Wu +3
Prompt learning has demonstrated impressive efficacy in the fine-tuning of multimodal large models to a wide range of downstream tasks. Nonetheless, applying existing prompt learni…
Noisy Node Classification by Bi-level Optimization based Multi-teacher Distillation
Yujing Liu, Zongqian Wu, Zhengyu Lu +4
Previous graph neural networks (GNNs) usually assume that the graph data is with clean labels for representation learning, but it is not true in real applications. In this paper, w…