Formalizing PARITY Circuit Lower Bounds in Lean
使用Lean和切换引理形式化Hastad的PARITY下界，证明了对于固定深度d的电路计算PARITY需要指数级大小，并构造了一个多项式大小、对数深度的有界扇入公式家族。
0 citationsRead paper
Selected work
Representative Papers
MoveBench: A Benchmark for Global-Scale Wildlife Movement Forecasting
研究通过构建MoveBench，一个包含2.6百万个GPS点的大规模基准，来解决野生动物运动预测的问题，并采用概率评估方法分析了不同预测技术的有效性。
0 citationsRead paper
Object Counting Across Modalities: Taxonomies, Benchmarks, Applications, and Open Challenges
论文探讨了从特定类别密度回归到开放词汇基础模型支持的计数方法转变，提出五轴分类法解决现有评估基础设施不足的问题。
0 citationsRead paper
SCI-CLIP: Segment-Centric Inference with Reference Memory for Training-Free Open-Vocabulary Segmentation
This work addresses the challenges in training-free open-vocabulary segmentation—namely, the lack of a unified reasoning abstraction and the difficulty in simultaneously preserving spatial consistency and contextual awareness—by proposing a region-centric unified inference framework. Built upon frozen CLIP features, the method propagates visual information through a region-consistent interaction graph and integrates cross-window feature enhancement with offline reference memory retrieval to achieve end-to-end context restoration and retrieval alignment. For the first time, region-level abstraction is consistently applied throughout feature interaction, context modeling, and retrieval refinement. The approach substantially improves segmentation structural quality, inference robustness, and retrieval alignment across eight benchmarks, establishing a new state of the art in training-free open-vocabulary segmentation.
0 citationsRead paper
Game-Theoretic Inverse Reinforcement Learning for Modeling Competitive Human Driving: A Cut-in Prediction Study
This study addresses the challenge of predicting high-risk cut-in maneuvers by human drivers in competitive driving scenarios by proposing a data-driven modeling approach that integrates game theory with inverse reinforcement learning. For the first time, game-theoretic inverse reinforcement learning is applied to cut-in behavior prediction, leveraging high-dimensional driving features and trained on the high-fidelity highD dataset. The work systematically uncovers the trade-off mechanism between instantaneous and temporally consistent features in balancing precision and recall. Experimental results demonstrate that the proposed method achieves an overall prediction accuracy exceeding 75%, with a cut-in prediction precision of 51% and recall of 49%, substantially outperforming conventional physics-based game-theoretic approaches, which yield only 4.4% precision.
0 citationsRead paper
Recent publications
Latest Papers
Formalizing PARITY Circuit Lower Bounds in Lean
使用Lean和切换引理形式化Hastad的PARITY下界，证明了对于固定深度d的电路计算PARITY需要指数级大小，并构造了一个多项式大小、对数深度的有界扇入公式家族。
0 citationsRead paper
MoveBench: A Benchmark for Global-Scale Wildlife Movement Forecasting
研究通过构建MoveBench，一个包含2.6百万个GPS点的大规模基准，来解决野生动物运动预测的问题，并采用概率评估方法分析了不同预测技术的有效性。
0 citationsRead paper
Object Counting Across Modalities: Taxonomies, Benchmarks, Applications, and Open Challenges
论文探讨了从特定类别密度回归到开放词汇基础模型支持的计数方法转变，提出五轴分类法解决现有评估基础设施不足的问题。
0 citationsRead paper
SCI-CLIP: Segment-Centric Inference with Reference Memory for Training-Free Open-Vocabulary Segmentation
This work addresses the challenges in training-free open-vocabulary segmentation—namely, the lack of a unified reasoning abstraction and the difficulty in simultaneously preserving spatial consistency and contextual awareness—by proposing a region-centric unified inference framework. Built upon frozen CLIP features, the method propagates visual information through a region-consistent interaction graph and integrates cross-window feature enhancement with offline reference memory retrieval to achieve end-to-end context restoration and retrieval alignment. For the first time, region-level abstraction is consistently applied throughout feature interaction, context modeling, and retrieval refinement. The approach substantially improves segmentation structural quality, inference robustness, and retrieval alignment across eight benchmarks, establishing a new state of the art in training-free open-vocabulary segmentation.
0 citationsRead paper
Game-Theoretic Inverse Reinforcement Learning for Modeling Competitive Human Driving: A Cut-in Prediction Study
This study addresses the challenge of predicting high-risk cut-in maneuvers by human drivers in competitive driving scenarios by proposing a data-driven modeling approach that integrates game theory with inverse reinforcement learning. For the first time, game-theoretic inverse reinforcement learning is applied to cut-in behavior prediction, leveraging high-dimensional driving features and trained on the high-fidelity highD dataset. The work systematically uncovers the trade-off mechanism between instantaneous and temporally consistent features in balancing precision and recall. Experimental results demonstrate that the proposed method achieves an overall prediction accuracy exceeding 75%, with a cut-in prediction precision of 51% and recall of 49%, substantially outperforming conventional physics-based game-theoretic approaches, which yield only 4.4% precision.
0 citationsRead paper