Keyu Chen
Research Subjects
Keyu Chen has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
- Ruizhi Qiao
Tencent Youtu Lab
2 shared publications - Bo Ren
Tencent Youtu Lab
1 shared publication - Haoqian Wu
Tencent Youtu Lab
1 shared publication - Wei Wen
Tencent Youtu Lab
1 shared publication - Xiao Wang
Anhui University
1 shared publication - Xing Sun
Tencent Youtu Lab, Shanghai, China
1 shared publication
Latest Publications
- Open Access
Adaptive Dual Reasoner: Large Reasoning Models Can Think Efficiently by Hybrid Reasoning
Although Long Reasoning Models (LRMs) have achieved superior performance on various reasoning scenarios, they often suffer from increased computational costs and inference latency caused by overthinking. To address these limitations, we propose Adaptive Dual Reasoner, which supports two reasoning modes: fast thinking and slow thinking. ADR dynamically alternates between these modes based on the contextual complexity during reasoning. ADR is trained in two stages: (1) A cold-start stage using supervised fine-tuning (SFT) to equip the model with the ability to integrate both fast and slow reasoning modes, in which we construct a hybrid reasoning dataset through a dedicated pipeline to provide large-scale supervision. (2) A reinforcement learning stage for optimizing reasoning effort, where we introduce Entropy-guided Hybrid Policy Optimization EHPO, an RL training framework employing an entropy-guided dynamic rollout strategy for branching at high-entropy units and a difficulty-aware penalty to balance fast and slow reasoning. Across challenging mathematical reasoning benchmarks, ADR achieves an effective balance between reasoning performance and efficiency among state-of-the-art approaches. Specifically, ADR yields a performance gain of up to 6.1%, while reducing the reasoning output length by 49.5% to 59.3%.
Open AccessAdaptive Dual Reasoner: Large Reasoning Models Can Think Efficiently by Hybrid Reasoning
Although Long Reasoning Models (LRMs) have achieved superior performance on various reasoning scenarios, they often suffer from increased computational costs and inference latency caused by overthinking. To address these limitations, we propose Adaptive Dual Reasoner, which supports two reasoning modes: fast thinking and slow thinking. ADR dynamically alternates between these modes based on the contextual complexity during reasoning. ADR is trained in two stages: (1) A cold-start stage using supervised fine-tuning (SFT) to equip the model with the ability to integrate both fast and slow reasoning modes, in which we construct a hybrid reasoning dataset through a dedicated pipeline to provide large-scale supervision. (2) A reinforcement learning stage for optimizing reasoning effort, where we introduce Entropy-guided Hybrid Policy Optimization EHPO, an RL training framework employing an entropy-guided dynamic rollout strategy for branching at high-entropy units and a difficulty-aware penalty to balance fast and slow reasoning. Across challenging mathematical reasoning benchmarks, ADR achieves an effective balance between reasoning performance and efficiency among state-of-the-art approaches. Specifically, ADR yields a performance gain of up to 6.1%, while reducing the reasoning output length by 49.5% to 59.3%.
- Top Cited Papers
- 18 February 2023
- Published by Springer Nature
- p. 624-641
See Finer, See More: Implicit Modality Alignment for Text-Based Person Retrieval
- 18 February 2023
- Published by Springer Nature
- p. 624-641
Top Cited PapersSee Finer, See More: Implicit Modality Alignment for Text-Based Person Retrieval