Hello! I am Kejing Xia (夏可敬), a first-year Ph.D. student in Computer Science at Georgia Tech, where I work in the EIC Lab on efficient LLMs. Prior to my Ph.D., I earned my B.Eng. in Communication Engineering (Artificial Intelligence Track) from Wuhan University, receiving multiple university-level scholarships and merit distinctions. Before that, I studied at the No.1 Middle School Affiliated to Central China Normal University (华中师大一附中).

You can view my CV here. (Updated in Sept. 2025)

Research Interest

• Efficient LLMs - Long-context modeling, training-free methods, and scalable architectures.
• 3D Vision - Neural radiance fields, event-based vision, and LiDAR-free urban scene reconstruction.

News

• 2025.09 - Paper D2GS: Dense Depth Regularization for LiDAR-free Urban Scene Reconstruction accepted at NeurIPS 2025.
• 2025.07 - Paper LAMB: A Training-Free Method to Enhance the Long-Context Understanding of SSMs accepted at ACL 2025.
• 2025.05 - Paper LongMamba: Enhancing Mamba’s Long-Context Capabilities accepted at ICLR 2025.
• 2024.06 - Paper A Spatio-temporal Event Transformer on Versatile Tasks for Human Behavior Analysis accepted at IJCAIW MiGA 2024.
• 2024.05 - Won National Second Prize and 5th Place (top 9%) in RoboCup China Open as team leader.
• 2023.11 - Won Province First Prize in China Undergraduate Mathematical Contest in Modeling.
• 2023.05 - Won National First Prize in Huazhong Cup Mathematical Modeling Challenge as team leader.

Publications

• D2GS: Dense Depth Regularization for LiDAR-free Urban Scene Reconstruction - NeurIPS 2025.
• LAMB: A Training-Free Method to Enhance the Long-Context Understanding of SSMs via Attention-Guided Token Filtering - ACL 2025.
• LongMamba: Enhancing Mamba’s Long-Context Capabilities via Training-Free Receptive Field Enlargement - ICLR 2025.
• BRS-E2NeRF: Event-Enhanced Neural Radiance Fields from Blurry Rolling Shutter Images - Submitted to Pattern Recognition.
• A Spatio-temporal Event Transformer on Versatile Tasks for Human Behavior Analysis - IJCAI-W 2024 (MiGA Workshop).

Research Experience

• EIC Lab, Georgia Tech (2024-Present) - Co-led projects on LongMamba and LAMB, proposing training-free approaches to extend context length in state-space models.
• Signal Processing Lab, Wuhan University (2023-2024) - Co-led BRS-E2NeRF, developing event-enhanced NeRFs to reconstruct sharp images from rolling shutter blur.
• Center for Machine Vision and Signal Analysis (CMVS), University of Oulu (2023-2024) - Led research on event-based human behavior analysis with spatio-temporal transformers, presented at IJCAI 2024 (MiGA Workshop).

Professional Experience

• Bosch Innovation Software Development Co., Ltd (2024-2025) - Project leader for D2GS, combining diffusion depth enhancement with 3D Gaussian models for LiDAR-free scene reconstruction.

Competition Experience

• RoboCup China Open (2024) - Captain, National First Prize.
• Student Innovation & Entrepreneurship Project (2023-2024) - National Prize for All-in-Focus Seeing Through Occlusions with Event and Frame.
• China Undergraduate Mathematical Contest in Modeling (2023) - Hubei Province First Prize.
• Huazhong Cup Mathematical Modeling Challenge (2023) - National First Prize.

Awards

• Wuhan University First-Class Academic Scholarship (2023-2024).
• “Luojia” Distinguished Exchange Student Scholarship (2023-2024).
• Merit Students, Wuhan University (2021-2022, 2023-2024).
• Outstanding Student (2022-2023).
• Multiple Merit and Outstanding Academic Scholarships (2021-2023).