We have 7 of 73 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
This work applies MRT to power outage report generation for the Outage Data Initiative Nationwide (ODIN), transforming heterogeneous reports into standardized XML compliant with CIM IEC 61968-3.
Modern deep neural networks achieve strong performance, but their scale makes them costly and slow, especially on resource-constrained edge devices. Pruning and quantization address this, but rely on manual, expert choices and on algorithms that are hard to apply across architectures. Uniform settings also ignore how d...
Test-time scaling can improve large language model reasoning by generating and combining multiple candidate responses. In sampling-based methods, the inference budget is often described by the number of generated candidates, N. However, N tells us how many candidates are generated, not how they are executed. The same c...
This work proposes an autotuning framework that designs a machine learning-based ensemble LLVM Intermediate Representation ranker, Neural Configuration Scorer (NCS), which ranks the performance of IRs sampled by a transfer-learning-based autotuner, improving the efficiency of the tuning process by reducing tuning overh...
Adaptive test-time scaling with a lightweight fuzzy controller that maps interpretable signals, including estimated prompt complexity and model confidence, to a per-query sampling budget is proposed, suggesting that interpretable adaptive sampling is a practical direction for more efficient test-time reasoning in large...
VarRate is presented, a training-free KV codec that assigns each token a variable low-rank budget by its query salience, keeping every token at a nonzero rank, and is the strongest matched-memory compressor.
Empirical findings suggest that CudaPerf significantly outperforms strong baselines, including Qwen-3-32B and CUDA Agent by achieving up to 5X and 3.32X improvements in speedup, and 17%&7% improvements in correctness, respectively.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
