11 papers
Cognitive Loop of Thought: Reversible Hierarchical Markov Chain for Efficient Mathematical Reasoning
Jia-Chen Zhang, Yu-Jie Xiong, Zheng Zhou
Multi-step Chain-of-Thought (CoT) has significantly advanced the mathematical reasoning capabilities of LLMs by leveraging explicit reasoning steps. However, the widespread adoptio…
Expert Pyramid Tuning: Efficient Parameter Fine-Tuning for Expertise-Driven Task Allocation
Jia-Chen Zhang, Zhen-Wei Yan, Yu-Jie Xiong +1
Parameter-Efficient Fine-Tuning (PEFT) has become a dominant paradigm for deploying LLMs in multi-task scenarios due to its extreme parameter efficiency. While Mixture-of-Experts (…
Gradient-Direction-Aware Density Control for 3D Gaussian Splatting
Zheng Zhou, Yu-Jie Xiong, Jia-Chen Zhang +3
The emergence of 3D Gaussian Splatting (3DGS) has significantly advanced Novel View Synthesis (NVS) through explicit scene representation, enabling real-time photorealistic renderi…
Mixture of Routers
Jia-Chen Zhang, Yu-Jie Xiong, Xi-He Qiu +3
Supervised fine-tuning (SFT) is a milestone in aligning large language models with human instructions and adapting them to downstream tasks. In particular, Low-Rank Adaptation (LoR…
Understanding Before Reasoning: Enhancing Chain-of-Thought with Iterative Summarization Pre-Prompting
Dong-Hai Zhu, Yu-Jie Xiong, Jia-Chen Zhang +2
Chain-of-Thought (CoT) Prompting is a dominant paradigm in Large Language Models (LLMs) to enhance complex reasoning. It guides LLMs to present multi-step reasoning, rather than ge…
Sugar-Coated Poison: Benign Generation Unlocks LLM Jailbreaking
Yu-Hang Wu, Yu-Jie Xiong, Hao Zhang +2
With the increasingly deep integration of large language models (LLMs) across diverse domains, the effectiveness of their safety mechanisms is encountering severe challenges. Curre…