13 papers
RayLift: Lifting Complementary Ray-Wise Evidence with 3D Geometry Priors for Semantic Scene Completion
Meng Wang, Hongxia Yu, Wenzhe He +4
Camera-based 3D semantic scene completion (SSC) provides comprehensive scene understanding for autonomous driving and robotics. However, existing methods often treat stereo depth e…
Exponential Separation of Quantum and Classical One-Way Numbers-on-Forehead Communication
Guangxu Yang, Jiapeng Zhang
Numbers-on-Forehead (NOF) communication model is a central model in communication complexity. As a restricted variant, one-way NOF model is of particular interest. Establishing str…
Self-Indexing KVCache: Predicting Sparse Attention from Compressed Keys
Xu Yang, Jiapeng Zhang, Dongyang Zhao +2
The KV cache in self-attention has emerged as a major bottleneck in long-context and large-batch inference for LLMs. Existing approaches often treat sparsity prediction and compres…
CoreSPECT: Enhancing Clustering Algorithms via an Interplay of Density and Geometry
Chandra Sekhar Mukherjee, Joonyoung Bae, Jiapeng Zhang
In this paper, we provide a novel perspective on the underlying structure of real-world data with ground-truth clusters via characterization of an abundantly observed yet often ove…
LiNeXt: Revisiting LiDAR Completion with Efficient Non-Diffusion Architectures
Wenzhe He, Xiaojun Chen, Ruiqi Wang +5
3D LiDAR scene completion from point clouds is a fundamental component of perception systems in autonomous vehicles. Previous methods have predominantly employed diffusion models f…
Enhancing Small-Scale Dataset Expansion with Triplet-Connection-based Sample Re-Weighting
Ting Xiang, Changjian Chen, Zhuo Tang +5
The performance of computer vision models in certain real-world applications, such as medical diagnosis, is often limited by the scarcity of available images. Expanding datasets us…