Institution profile

University of Wyoming

Academic institutionnorthamerica · us
Official website
Research library17linked papers
Opportunities0open roles
Selected work

Representative Papers

SCI-CLIP: Segment-Centric Inference with Reference Memory for Training-Free Open-Vocabulary Segmentation

Aug 06, 2026

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

Aug 06, 2026

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

Parameter Golf: What Really Works?

Jul 01, 2026

This work addresses the challenge of training highly efficient language models under stringent constraints—limited to a 16MB model size and 10 minutes of training time on 8×H100 GPUs—through a community-driven competition. The study proposes a comprehensive taxonomy encompassing 84 techniques across four categories: model architecture, training strategies, weight compression, and encoding optimization. Leveraging a large volume of participant submissions, it quantitatively evaluates the empirical contribution of each technique to bits-per-byte (BPB) performance and identifies methods with strong generalization capabilities. Over three competition phases, the best-reported BPB improved from 1.2244 to 1.058, reflecting a 13.6% gain and demonstrating that the cumulative effect of numerous small improvements can yield substantial overall performance enhancements.

0 citationsRead paper
Recent publications

Latest Papers

SCI-CLIP: Segment-Centric Inference with Reference Memory for Training-Free Open-Vocabulary Segmentation

Aug 06, 2026

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

Aug 06, 2026

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

Parameter Golf: What Really Works?

Jul 01, 2026

This work addresses the challenge of training highly efficient language models under stringent constraints—limited to a 16MB model size and 10 minutes of training time on 8×H100 GPUs—through a community-driven competition. The study proposes a comprehensive taxonomy encompassing 84 techniques across four categories: model architecture, training strategies, weight compression, and encoding optimization. Leveraging a large volume of participant submissions, it quantitatively evaluates the empirical contribution of each technique to bits-per-byte (BPB) performance and identifies methods with strong generalization capabilities. Over three competition phases, the best-reported BPB improved from 1.2244 to 1.058, reflecting a 13.6% gain and demonstrating that the cumulative effect of numerous small improvements can yield substantial overall performance enhancements.

0 citationsRead paper