Get started
Author

Weili Guan

PersonalAlign: Hierarchical Implicit Intent Alignment for Personalized GUI Agent with Long-Term User-Centric Records
2026 · Lyu, Yibo, Chen, Gongwei, et al. · arXiv (Cornell University) · 1
PDF
TaskBridge: Technical Report for SIGIR 2026 eCommerce Challenge
2026 · Fu, Zhiheng, Hu, Yupeng, et al. · arXiv (Cornell University)
PDF
CueMem: Cue-Guided Context Reconstruction for Long-Term Conversational Memory
2026 · Wang, Changjian, Li, Rongzhen, et al. · arXiv (Cornell University)
PDF
ADGNet: Asymmetric Dual-text Guided Network for Infrared Small Target Detection
2026 · Wang, Tongtong, Xu, Mingzhu, et al. · arXiv (Cornell University)
PDF
The First EgoCross Challenge at EgoVis 2026: Cross-Domain Egocentric Video Question Answering
2026 · Fu, Yuqian, Qian, Tianwen, et al. · arXiv (Cornell University)
PDF
EmAvatar: Multimodal Empathetic Response Generation via Conflict Resolution and Expressive Guidance
2026 · Chen, Xiaolin, Song, Xuemeng, et al. · arXiv (Cornell University)
PDF
Efficient Visual Pointing for Embodied AI:Agent-Driven Data Synthesis, Cross-Block Attention, and Iterative Correction
2026 · Hong, Zijian, Lv, Qi, et al. · arXiv (Cornell University)
PDF
Reusable Experiences: Latent Routing and Modular Composition in LLMs
2026 · Association for Computational Linguistics 2026, Guan, Weili, et al. · Underline Science Inc.
Resonating with RoPE: Spectral Quantization for High-Fidelity Key Cache Compression
2026 · Association for Computational Linguistics 2026, Guan, Weili, et al. · Underline Science Inc.
SAT: Balancing Reasoning Accuracy and Efficiency with Stepwise Adaptive Thinking
2026 · Association for Computational Linguistics 2026, Bai, Xuefeng, et al. · Underline Science Inc.
PersonalAlign: Hierarchical Implicit Intent Alignment for Personalized GUI Agent with Long-Term User-Centric Records
2026 · Association for Computational Linguistics 2026, Chen, Gongwei, et al. · Underline Science Inc.
TGV-KV: Text-Grounded KV Eviction for Vision-Language Models
2026 · Liu, Jizhihui, Han, Ruizi, et al. · arXiv (Cornell University)
PDF
TempRet: Temporal Enhancement and Two-Stage Reranking for CVPR 2026 EPIC-KITCHENS-100 Multi-Instance Retrieval Challenge
2026 · Li, Zixu, Hu, Yupeng, et al. · arXiv (Cornell University)
PDF
EgoAdapt: A Multi-Scene Egocentric Adaptation Method for CVPR 2026 HD-EPIC VQA Challenge
2026 · Chen, Zhiwei, Hu, Yupeng, et al. · arXiv (Cornell University)
PDF
EgoAction: Egocentric Action Composition with Reliability-Aware Temporal Fusion for the EPIC-KITCHENS Action Detection Challenge at CVPR 2026
2026 · Fu, Zhiheng, Li, Zixu, et al. · arXiv (Cornell University)
PDF
OmniEgo-R$^2$: A Routed Reasoning Framework for the 1st Cross-Domain EgoCross Challenge at CVPR 2026
2026 · Li, Zixu, Chen, Zhiwei, et al. · arXiv (Cornell University)
PDF
FashionLens: Toward Versatile Fashion Image Retrieval via Task-Adaptive Learning
2026 · Wen, Haokun, Song, Xuemeng, et al. · arXiv (Cornell University)
PDF
JFAA: Technical Report for the EPIC-KITCHENS-100 Action Anticipation Challenge at EgoVis 2026
2026 · Chu, Qiaohui, Zhang, Haoyu, et al. · arXiv (Cornell University)
PDF
PulseCol: Periodically Refreshed Column-Sparse Attention for Accelerating Diffusion Language Models
2026 · Lyu, Yanyi, Chen, Letian, et al. · arXiv (Cornell University)
PDF
VISTA: Technical Report for the Ego4D Short-Term Object Interaction Anticipation at EgoVis 2026
2026 · Chu, Qiaohui, Zhang, Haoyu, et al. · arXiv (Cornell University)
PDF
DASH: Fast Differentiable Architecture Search for Hybrid Attention in Minutes on a Single GPU
2026 · Chen, Weizhe, Zhang, Miao, et al. · arXiv (Cornell University)
PDF
OSGNet with MLLM Reranking @ Ego4D Episodic Memory Challenge 2026
2026 · Feng, Yisen, Qu, Leigang, et al. · arXiv (Cornell University)
PDF
Report of the 5th PVUW Challenge: Towards More Diverse Modalities in Pixel-Level Understanding
2026 · Liu, Chang, Ding, Henghui, et al. · arXiv (Cornell University)
PDF
SAT: Balancing Reasoning Accuracy and Efficiency with Stepwise Adaptive Thinking
2026 · Huang, Weiyang, Bai, Xuefeng, et al. · arXiv (Cornell University)
PDF
Advancing Complex Video Object Segmentation via Tracking-Enhanced Prompt: The 1st Winner for 5th PVUW MOSE Challenge
2026 · Zhang, Jinrong, Wu, Canyang, et al. · arXiv (Cornell University)
PDF
Works count: 29
Citation count: 1
H-index: 1
I10-index:
Year
Topic
Type