12 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…
Articulate Intuition or Genuine Analysis? Benchmarking Epistemic Reliability in LLM-as-a-Judge Peer Reviews
Nuo Chen, Qian Wang, Qingyun Zou +1
When an LLM judge calls a peer review analytical and a human committee calls another review high quality, are they tracking the same thing? We argue they are not, and that the diff…
Is Agentic AI Ready for Real-World Hardware Engineering? A Deep Dive with Phoenix-bench
Qingyun Zou, Feng Yu, Hongshi Tan +2
We ask whether agentic AI systems built for software engineering transfer to realistic hardware engineering. Existing hardware LLM benchmarks isolate sub-tasks but none jointly req…
Reward-Weighted On-Policy Distillation with an Open Property-Equivalence Verifier for NL-to-SVA Generation
Qingyun Zou, Yingze Li, Tianen Liu +2
LLM-based generation of SystemVerilog Assertions (SVA) is often reported as nearing saturation, with the strongest specialized model reaching accuracy on NL2SVA-Human.…
HLS-Seek: QoR-Aware Code Generation for High-Level Synthesis via Proxy Comparative Reward Reinforcement Learning
Qingyun Zou, Feng Yu, Hongshi Tan +3
High-Level Synthesis (HLS) compiles algorithmic C/C++ descriptions into hardware, with Quality of Results (QoR)---latency and resource utilization---critically governed by pragma c…
Diversity Collapse in Multi-Agent LLM Systems: Structural Coupling and Collective Failure in Open-Ended Idea Generation
Nuo Chen, Yicheng Tong, Yuzhe Yang +5
Multi-agent systems (MAS) are increasingly used for open-ended idea generation, driven by the expectation that collective interaction will broaden the exploration diversity. Howeve…
MHRC-Bench: A Multilingual Hardware Repository-Level Code Completion benchmark
Qingyun Zou, Jiahao Cui, Nuo Chen +2
Large language models (LLMs) have achieved strong performance on code completion tasks in general-purpose programming languages. However, existing repository-level code completion…
Beyond Brainstorming: What Drives High-Quality Scientific Ideas? Lessons from Multi-Agent Collaboration
Nuo Chen, Yicheng Tong, Jiaying Wu +5
While AI agents show potential in scientific ideation, most existing frameworks rely on single-agent refinement, limiting creativity due to bounded knowledge and perspective. Inspi…
HLStrans: Dataset for C-to-HLS Hardware Code Synthesis
Qingyun Zou, Nuo Chen, Yao Chen +2
High-Level Synthesis (HLS) enables hardware design from C/C++ kernels but requires extensive transformations, such as restructuring code, inserting pragmas, adapting data types, an…
JudgeLRM: Large Reasoning Models as a Judge
Nuo Chen, Zhiyuan Hu, Qingyun Zou +4
Large Language Models (LLMs) are increasingly adopted as evaluators, offering a scalable alternative to human annotation. However, existing supervised fine-tuning (SFT) approaches…