9 papers
Physical AI: A Survey of Models, Learning, Systems, and Open Challenges
Bin Gao, Anuj Gautam, Aritra Bagchi +17
Physical AI aims to enable intelligent systems to perceive, reason, act, and learn through interaction with the physical world. Unlike purely digital intelligence, physical agents…
ActTune: Action-Aware Precision and GPU Operating-Point Adaptation for Energy-Efficient Vision-Language-Action Inference
Zou Qingyun, Bin Gao, Wenju Zhao +3
Vision-language-action (VLA) policies repeatedly invoke inference to control robots, making graphics processing unit (GPU) energy a recurring cost of task execution. Reducing energ…
ECO: Energy-Oriented Configuration Optimization for Attention FFN Disaggregated LLM Serving
Zou Qingyun, Bin Gao, Zhuobin Huang +3
Energy-efficient LLM serving requires minimizing serving GPU energy while meeting latency and throughput service-level objectives (SLOs). Attention--FFN disaggregation (AFD) enable…
SPLASH: Co-Designing Sparse Attention with High-Bandwidth Flash for Efficient Long-Context Inference
Aditya Anirudh Jonnalagadda, Agasthi Haputhanthri, Pranav Dangi +5
The key-value (KV) cache has become the dominant consumer of memory in large language model (LLM) serving systems as context lengths, concurrency, and request lifetimes grow. High-…
Para-Pipe: Exploiting Hierarchical Operator Parallelism of ML Computational Graphs on SoCs
Yujie Zhang, Huiying Lan, Ehsan Aghapour +5
As edge-based deep learning applications become more complex, optimizing performance on heterogeneous System-on-Chips (SoCs) presents unique challenges. Traditional pipelining tech…
LLM-based Hardware Development with Hierarchical IRs and End-to-End Multi-Agent Workflow
Chenyang Yin, Agasthi Haputhanthri, Aditya Anirudh Jonnalagadda +7
Large language models (LLMs) are increasingly used in software development, but their use in complex hardware design remains limited. This gap stems from both the scarcity of publi…
SAEM: Stage-Aware Expert Management for Memory-Efficient MoE Inference in Chain-of-Thought Reasoning
Yujie Zhang, Bin Gao, Tulika Mitra
Chain-of-thought (CoT) prompting improves LLM reasoning by decomposing complex problems into intermediate steps, but its sequential nature increases decoding latency and memory usa…
A Data-Driven Dynamic Execution Orchestration Architecture
Zhenyu Bai, Pranav Dangi, Rohan Juneja +4
Domain-specific accelerators deliver exceptional performance on their target workloads through fabrication-time orchestrated datapaths. However, such specialized architectures ofte…
Flip: Data-Centric Edge CGRA Accelerator
Dan Wu, Peng Chen, Thilini Kaushalya Bandara +2
Coarse-Grained Reconfigurable Arrays (CGRA) are promising edge accelerators due to the outstanding balance in flexibility, performance, and energy efficiency. Classic CGRAs statica…