9 papers
SpecCoder: Specification-Aware Code Generation with Curriculum Dual-Task Reinforcement Learning
Yixuan Li, Mingxuan Huang, Jiajing Wang +4
Large language models (LLMs) have made substantial progress in code generation but still struggle with challenging programming tasks that require understanding rich natural languag…
MedCritical: Enhancing Medical Reasoning in Small Language Models via Self-Collaborative Correction
Xinchun Su, Chunxu Luo, Yixuan Li +2
In the field of medicine, complex reasoning tasks such as clinical diagnosis, treatment planning, and medical knowledge integration pose significant challenges, where small languag…
LogReasoner: Empowering LLMs with Expert-like Coarse-to-Fine Reasoning for Automated Log Analysis
Lipeng Ma, Yixuan Li, Weidong Yang +7
Log analysis is crucial for monitoring system health and diagnosing failures in complex systems. Recent advances in large language models (LLMs) offer new opportunities for automat…
PseudoBridge: Pseudo Code as the Bridge for Better Semantic and Logic Alignment in Code Retrieval
Yixuan Li, Xinyi Liu, Weidong Yang +4
Code retrieval aims to find relevant code snippets matching natural language queries within massive codebases, playing a vital role in software development. Recent advances leverag…
DeepThink3D: Enhancing Large Language Models with Programmatic Reasoning in Complex 3D Situated Reasoning Tasks
Jiayi Song, Rui Wan, Lipeng Ma +4
This work enhances the ability of large language models (LLMs) to perform complex reasoning in 3D scenes. Recent work has addressed the 3D situated reasoning task by invoking tool…
ChemAU: Harness the Reasoning of LLMs in Chemical Research with Adaptive Uncertainty Estimation
Xinyi Liu, Lipeng Ma, Yixuan Li +5
Large Language Models (LLMs) are widely used across various scenarios due to their exceptional reasoning capabilities and natural language understanding. While LLMs demonstrate str…
AdaptiveLog: An Adaptive Log Analysis Framework with the Collaboration of Large and Small Language Model
Lipeng Ma, Weidong Yang, Yixuan Li +6
Automated log analysis is crucial to ensure high availability and reliability of complex systems. The advent of LLMs in NLP has ushered in a new era of language model-driven automa…
Towards Unified Representation of Multi-Modal Pre-training for 3D Understanding via Differentiable Rendering
Ben Fei, Yixuan Li, Weidong Yang +2
State-of-the-art 3D models, which excel in recognition tasks, typically depend on large-scale datasets and well-defined category sets. Recent advances in multi-modal pre-training h…
3DMambaComplete: Exploring Structured State Space Model for Point Cloud Completion
Yixuan Li, Weidong Yang, Ben Fei
Point cloud completion aims to generate a complete and high-fidelity point cloud from an initially incomplete and low-quality input. A prevalent strategy involves leveraging Transf…