59 citations · 59 across the 9 of their papers we have counts for
7 papers · 1 filter
Learning to Compute Is Not Learning to Retain or Reuse in Looped Transformers
Peilong Zhou, Hongtao Zhang, Yulong Huang +3
Looped transformers compute by applying one block repeatedly, so they can run for more loops than they were trained with. Recurrent reasoners are known to overthink: iterating past…
RTLCurator: Label-Efficient Data Curation for RTL Generation
Siyang Cai, Cangyuan Li, Wenjing Chang +4
Training large language models (LLMs) to write register-transfer level (RTL) requires large corpora of paired specifications and code, and such data is scarce enough that most publ…
CLOSER-Bench: Evaluating Budgeted Cross-Stage Design Closure for Hardware Agents
Peilong Zhou, Zhirong Chen, Cangyuan Li +4
Hardware engineering exposes coding agents to a form of long-horizon work that is difficult to capture with pass-at-k: progress is continuous, tool feedback is delayed and heteroge…
When Fuzzing Meets Understanding: LLM-Driven Semantic Test Generation for RTL Verification
Kun Wang, Cangyuan Li, Kaiyan Chang +3
The growing complexity of modern chips poses significant challenges to hardware verification. In recent years, coverage-guided fuzzing has emerged as a promising approach for impro…
Alpha-RTL: Test-Time Training for RTL Hardware Optimization
Peilong Zhou, Zhirong Chen, Cangyuan Li +4
Large language models (LLMs) have shown increasing promise in generating functionally correct register-transfer-level (RTL) hardware designs. Recent systems improve further through…
Wrong Code, Right Structure: Learning Netlist Representations from Imperfect LLM-Generated RTL
Siyang Cai, Cangyuan Li, Haoyu Gao +3
Learning effective netlist representations is fundamentally constrained by the scarcity of labeled datasets, as real designs are protected by Intellectual Property (IP) and costly…
TriMoE: Augmenting GPU with AMX-Enabled CPU and DIMM-NDP for High-Throughput MoE Inference via Offloading
Yudong Pan, Yintao He, Tianhua Han +7
To deploy large Mixture-of-Experts (MoE) models cost-effectively, offloading-based single-GPU heterogeneous inference is crucial. While GPU-CPU architectures that offload cold expe…