13 papers
ParaTempo: Efficient Parallel Reasoning via Temporal Confidence
Xuteng Zhang, Wenhao Zeng, Xiaodong Gu +5
Parallel reasoning improves the accuracy and robustness of large reasoning models by exploring multiple solution paths, but its computational cost grows with reasoning depth and br…
In Line with Context: Repository-Level Code Generation via Context Inlining
Chao Hu, Wenhao Zeng, Yuling Shi +2
Repository-level code generation has attracted growing attention in recent years. Unlike function-level code generation, it requires the model to understand the entire repository,…
GlimpRouter: Efficient Collaborative Inference by Glimpsing One Token of Thoughts
Wenhao Zeng, Xuteng Zhang, Yuling Shi +4
Large Reasoning Models (LRMs) achieve remarkable performance by explicitly generating multi-step chains of thought, but this capability incurs substantial inference latency and com…
Neuron-Guided Interpretation of Code LLMs: Where, Why, and How?
Zhe Yin, Xiaodong Gu, Beijun Shen
Code language models excel on code intelligence tasks, yet their internal interpretability is underexplored. Existing neuron interpretability techniques from NLP are suboptimal for…
Readability-Robust Code Summarization via Meta Curriculum Learning
Wenhao Zeng, Yitian Chai, Hao Zhou +3
Code summarization has emerged as a fundamental technique in the field of program comprehension. While code language models have shown significant advancements, the current models…
CatchAll: Repository-Aware Exception Handling with Knowledge-Guided LLMs
Qingxiao Tao, Xiaodong Gu, Hao Zhong +1
Exception handling is a vital forward error-recovery mechanism in many programming languages, enabling developers to manage runtime anomalies through structured constructs (e.g., t…