6 papers
Not All Attention Heads Contribute to Critical Visual Token Selection: Head-Aware Pruning Matters More
Chaofang Ma, Lin Jiang, Carol Jingyi Li +4
Vision-Language Models (VLMs) have exhibited impressive performance across diverse visual scenarios. However, this success comes at the cost of explosive growth in visual tokens, w…
TherMapNet Attention-Guided Runtime Full-Chip Thermal Map Prediction from Performance Metrics
Qin Gu, Chaofang Ma, Mingyu Yang +4
Runtime thermal management of high-performance chips depends on fast and accurate full-chip thermal maps. Conventional simulators typically estimate power traces from performance m…
ThermoDSE: A Thermal-Aware and Comprehensive Design Space Exploration for Chiplet-Based DNN Accelerators
Jian Peng, Hanwei Fan, Jingbo Jiang +2
Chiplet-based DNN accelerators provide a scalable path to balance performance and yield for modern AI workloads. However, such systems face critical challenges in area and thermal…
VersaQ-3D: Architecture Support for Visual Geometry Grounded Transformers via Versatile Quantization
Yipu Zhang, Jintao Cheng, Xingyu Liu +8
3D reconstruction and view synthesis are fundamental to AR/VR, robotics, and digital twins. The Visual Geometry Grounded Transformer (VGGT) enables strong feed-forward 3D reconstru…
HERO: Hardware-Efficient RL-based Optimization Framework for NeRF Quantization
Yipu Zhang, Chaofang Ma, Jinming Ge +3
Neural Radiance Field (NeRF) has emerged as a promising 3D reconstruction method, delivering high-quality results for AR/VR applications. While quantization methods and hardware ac…
Uni-Render: A Unified Accelerator for Real-Time Rendering Across Diverse Neural Renderers
Chaojian Li, Sixu Li, Linrui Jiang +2
Recent advancements in neural rendering technologies and their supporting devices have paved the way for immersive 3D experiences, significantly transforming human interaction with…