Separating Stream Stability from Long-Term Recall in Language Models
本文区分了流式语言模型的稳定性与长期记忆问题，通过引入三个时间范围并提出ThreeH评估方法来解决这一区分问题。
0 citationsRead paper
Selected work
Representative Papers
Signed Rescue Routing: Harm-Aware Cascades for Efficient LLM Inference
为提高LLM推理效率，提出Signed Rescue Routing方法，通过预测大小模型纠错和误替事件差值来优化请求路由，优于传统基于不确定性的方法。
0 citationsRead paper
RouteSparse: Input-Conditional Pattern Routing for Budgeted Long-Context Prefilling
论文提出RouteSparse方法，通过输入条件路由选择稀疏模式以解决长上下文预填充的高成本问题，提高了效率并减少了性能下降。
0 citationsRead paper
A Momentum-Based Variance-Reduced Algorithm for Federated Multiobjective Optimization
本文针对联邦多目标优化问题，提出了一种基于动量的方差减少算法，通过改进梯度估计器减少了随机更新的方差，提高了收敛速度。
0 citationsRead paper
DB SwinT: A Dual-Branch Swin Transformer Network for Road Extraction in Optical Remote Sensing Imagery
This work addresses the challenge of fragmented road structures and low extraction accuracy in optical remote sensing imagery caused by occlusions from trees, buildings, and other objects. To this end, the authors propose a dual-branch Swin Transformer network that integrates a U-Net–inspired multi-scale feature fusion strategy. The architecture employs separate local and global branches to recover fine details in occluded regions and preserve topological continuity of road networks, respectively. An Attention-based Feature Fusion (AFF) module is further introduced to adaptively integrate information from both branches. This design effectively balances local detail reconstruction with global semantic context modeling. Experimental results demonstrate state-of-the-art performance, achieving Intersection over Union (IoU) scores of 79.35% and 74.84% on the Massachusetts and DeepGlobe road datasets, respectively, significantly outperforming existing methods.
0 citationsRead paper
Recent publications
Latest Papers
Separating Stream Stability from Long-Term Recall in Language Models
本文区分了流式语言模型的稳定性与长期记忆问题，通过引入三个时间范围并提出ThreeH评估方法来解决这一区分问题。
0 citationsRead paper
Signed Rescue Routing: Harm-Aware Cascades for Efficient LLM Inference
为提高LLM推理效率，提出Signed Rescue Routing方法，通过预测大小模型纠错和误替事件差值来优化请求路由，优于传统基于不确定性的方法。
0 citationsRead paper
RouteSparse: Input-Conditional Pattern Routing for Budgeted Long-Context Prefilling
论文提出RouteSparse方法，通过输入条件路由选择稀疏模式以解决长上下文预填充的高成本问题，提高了效率并减少了性能下降。
0 citationsRead paper
A Momentum-Based Variance-Reduced Algorithm for Federated Multiobjective Optimization
本文针对联邦多目标优化问题，提出了一种基于动量的方差减少算法，通过改进梯度估计器减少了随机更新的方差，提高了收敛速度。
0 citationsRead paper
DB SwinT: A Dual-Branch Swin Transformer Network for Road Extraction in Optical Remote Sensing Imagery
This work addresses the challenge of fragmented road structures and low extraction accuracy in optical remote sensing imagery caused by occlusions from trees, buildings, and other objects. To this end, the authors propose a dual-branch Swin Transformer network that integrates a U-Net–inspired multi-scale feature fusion strategy. The architecture employs separate local and global branches to recover fine details in occluded regions and preserve topological continuity of road networks, respectively. An Attention-based Feature Fusion (AFF) module is further introduced to adaptively integrate information from both branches. This design effectively balances local detail reconstruction with global semantic context modeling. Experimental results demonstrate state-of-the-art performance, achieving Intersection over Union (IoU) scores of 79.35% and 74.84% on the Massachusetts and DeepGlobe road datasets, respectively, significantly outperforming existing methods.
0 citationsRead paper