activity
20242026
collaborators

7 papers

cs.RO2026

STEP: Warm-Started Visuomotor Policies with Spatiotemporal Consistency Prediction

Jinhao Li, Yuxuan Cong, Yingqiao Wang +5

Diffusion policies have recently emerged as a powerful paradigm for visuomotor control in robotic manipulation due to their ability to model the distribution of action sequences an…

cs.RO2026

ScoRe-Flow: Complete Distributional Control via Score-Based Reinforcement Learning for Flow Matching

Xiaotian Qiu, Lukai Chen, Jinhao Li +3

Flow Matching (FM) policies have emerged as an efficient backbone for robotic control, offering fast and expressive action generation that underpins recent large-scale embodied AI…

cs.CV2025

BalanceGS: Algorithm-System Co-design for Efficient 3D Gaussian Splatting Training on GPU

Junyi Wu, Jiaming Xu, Jinhao Li +4

3D Gaussian Splatting (3DGS) has emerged as a promising 3D reconstruction technique. The traditional 3DGS training pipeline follows three sequential steps: Gaussian densification,…

cs.AR2025

Large Language Model Inference Acceleration: A Comprehensive Hardware Perspective

Jinhao Li, Jiaming Xu, Shan Huang +9

Large Language Models (LLMs) have demonstrated remarkable capabilities across various fields, from natural language understanding to text generation. Compared to non-generative LLM…

cs.DC2025

SpecEE: Accelerating Large Language Model Inference with Speculative Early Exiting

Jiaming Xu, Jiayi Pan, Yongkang Zhou +5

Early exiting has recently emerged as a promising technique for accelerating large language models (LLMs) by effectively reducing the hardware computation and memory access. In thi…

cs.AR2024

SoftmAP: Software-Hardware Co-design for Integer-Only Softmax on Associative Processors

Mariam Rakka, Jinhao Li, Guohao Dai +3

Recent research efforts focus on reducing the computational and memory overheads of Large Language Models (LLMs) to make them feasible on resource-constrained devices. Despite adva…