GenAI Daily for Practitioners

Executive Summary • Here are the concise bullets for enterprise practitioners: • SparseDVFS: Achieves average energy efficiency improvement of 24.5% for edge inference using sparse-aware dynamic voltage and frequency scaling (DVFS) on NVIDIA GPU. (Cost: N/A, Compliance: N/A, Deployment: Requires GPU support) • Revisiting Quantum Code Generation: No clear conclusion on where domain knowledge should live, but highlights the importance of integrating domain expertise in quantum code generation. (Cost: N/A, Compliance: N/A, Deployment: N/A) • Inhibitor Transformers and Gated RNNs: Proposes new architectures for fully homomorphic encryption, achieving improved performance and efficiency. (Cost: N/A, Compliance: N/A, Deployment: Requires specialized hardware) • On the Challenges and Opportunities of Learned Sparse Retrieval for Code: Highlights the potential of learned sparse retrieval for code search and proposes a new approach. (Cost: N/A, Compliance: N/A, Deployment: N/A) • Human or LLM as Standardized Patients? A Comparative Study for Medical Education: Finds that large language models (LLMs) can be effective standardized patients in medical education, but human evaluators are still necessary. (Cost: N/A, Compliance: N/A, Deployment:

Research

• SparseDVFS: Sparse-Aware DVFS for Energy-Efficient Edge Inference \ Deploying deep neural networks (DNNs) on power-sensitive edge devices presents a formidable challenge. While Dynamic Voltage and Frequency Scaling (DVFS) is widely employed for energy optimization, traditional model-level scaling is often … \ Source • arXiv cs.LG • 13:29
• Revisiting Quantum Code Generation: Where Should Domain Knowledge Live? \ Recent advances in large language models (LLMs) have enabled the automation of an increasing number of programming tasks, including code generation for scientific and engineering domains. In rapidly evolving software ecosystems such as qua… \ Source • arXiv cs.LG • 17:46
• Inhibitor Transformers and Gated RNNs for Torus Efficient Fully Homomorphic Encryption \ This paper introduces efficient modifications to neural network-based sequence processing approaches, laying new grounds for scalable privacy-preserving machine learning under Fully Homomorphic Encryption (FHE). Transformers are now ubiqui… \ Source • arXiv cs.LG • 16:11
• On the Challenges and Opportunities of Learned Sparse Retrieval for Code \ Retrieval over large codebases is a key component of modern LLM-based software engineering systems. Existing approaches predominantly rely on dense embedding models, while learned sparse retrieval (LSR) remains largely unexplored for code.… \ Source • arXiv cs.CL • 15:14
• Human or LLM as Standardized Patients? A Comparative Study for Medical Education \ Standardized patients (SPs) are indispensable for clinical skills training but remain expensive and difficult to scale. Although large language model (LLM)-based virtual standardized patients (VSPs) have been proposed as an alternative, th… \ Source • arXiv cs.CL • 12:32
• Select, Label, Evaluate: Active Testing in NLP \ Human annotation cost and time remain significant bottlenecks in Natural Language Processing (NLP), with test data annotation being particularly expensive due to the stringent requirement for low-error and high-quality labels necessary for… \ Source • arXiv cs.CL • 12:28
• TRI-DEP: A Trimodal Comparative Study for Depression Detection Using Speech, Text, and EEG \ Depression is a widespread mental health disorder, yet its automatic detection remains challenging. Prior work has explored unimodal and multimodal approaches, with multimodal systems showing promise by leveraging complementary signals. Ho… \ Source • arXiv cs.CL • 12:09
• The Price of Progress: Price Performance and the Future of AI \ Language models have seen enormous progress on advanced benchmarks in recent years, but much of this progress has only been possible by using more costly models. Benchmarks may therefore present a warped picture of progress in practical ca… \ Source • arXiv cs.LG • 18:48
• Noise Titration: Exact Distributional Benchmarking for Probabilistic Time Series Forecasting \ Modern time series forecasting is evaluated almost entirely through passive observation of single historical trajectories, rendering claims about a model's robustness to non-stationarity fundamentally unfalsifiable. We propose a paradigm s… \ Source • arXiv cs.LG • 18:14
• Chimera: Latency- and Performance-Aware Multi-agent Serving for Heterogeneous LLMs \ Multi-agent applications often execute complex tasks as multi-stage workflows, where each stage is an LLM call whose output becomes part of context for subsequent steps. Existing LLM serving systems largely assume homogeneous clusters with… \ Source • arXiv cs.LG • 18:01
• Measuring Iterative Temporal Reasoning with Time Puzzles \ Tool use, such as web search, has become a standard capability even in freely available large language models (LLMs). However, existing benchmarks evaluate temporal reasoning mainly in static, non-tool-using settings, which poorly reflect … \ Source • arXiv cs.CL • 18:44
• Automatically Benchmarking LLM Code Agents through Agent-Driven Annotation and Evaluation \ Recent advances in code agents have enabled automated software development at the project level, supported by large language models (LLMs). However, existing benchmarks for code agent evaluation face two major limitations. First, creating … \ Source • arXiv cs.CL • 15:11

Big Tech

No items today.

Regulation & Standards

No items today.

Enterprise Practice

No items today.

Open-Source Tooling

No items today.

— Personal views, not IBM. No tracking. Curated automatically; links under 24h old.