collaborators

11 papers

cs.AI2026

Allocation Before Ranking: Decoupled Token Compression for OmniLLMs

Zhenghui Guo, Yilin Yang, Yuanbin Man +5

Token compression in OmniLLMs is typically posed as a single saliency-ranking problem: score each multimodal token, keep the top-K. We argue this abstraction is mis-specified. The…

cs.DC2026

FLARE: A Dataflow-Aware and Scalable Hardware Architecture for Neural-Hybrid Scientific Lossy Compression

Wenqi Jia, Zhewen Hu, Baixi Sun +9

The paper introduces FLARE, a hardware architecture that integrates neural network‑based lossy compression with traditional scientific data processing to reduce memory traffic and…

cs.DC2026

Splaxel: Efficient Distributed Training of 3D Gaussian Splatting for Large-scale Scene Reconstruction via Pixel-level Communication

Wenqi Jia, Zhewen Hu, Ying Huang +10

3D Gaussian Splatting (3DGS) enables high-fidelity and real-time 3D scene reconstruction, but scaling training to large-scale scenes requires optimizing hundreds of millions of Gau…

cs.CV2026

Gaussians on a Diet: High-Quality Memory-Bounded 3D Gaussian Splatting Training

Yangming Zhang, Jian Xu, Chaojian Li +7

3D Gaussian Splatting (3DGS) has revolutionized novel view synthesis with high-quality rendering through continuous aggregations of millions of 3D Gaussian primitives. However, it…

cs.DC2026

FlashMem: Supporting Modern DNN Workloads on Mobile with GPU Memory Hierarchy Optimizations

Zhihao Shu, Md Musfiqur Rahman Sanim, Hangyu Zheng +4

The increasing size and complexity of modern deep neural networks (DNNs) pose significant challenges for on-device inference on mobile GPUs, with limited memory and computational r…

cs.LG2026

CoSA: Compressed Sensing-Based Adaptation of Large Language Models

Songtao Wei, Yi Li, Bohan Zhang +6

Parameter-Efficient Fine-Tuning (PEFT) has emerged as a practical paradigm for adapting large language models (LLMs) without updating all parameters. Most existing approaches, such…