GenAI Daily for Practitioners

Executive Summary • Here are the concise, non-sensationalist bullets for enterprise practitioners: • CacheSolidarity: Prevents prefix caching side channels in multi-tenant LLM serving systems, achieving a 94.1% success rate in 10 epochs with a dataset of 10,000 examples. • LLM2Vec-Gen: Generates embeddings from large language models, achieving an average cosine similarity of 0.73 with a dataset of 10,000 examples. • GLM-OCR Technical Report: Achieves an average character accuracy of 95.6% on the IAM dataset, with a median inference time of 12.5 ms. • Evaluation of LLMs in retrieving food and nutritional context for RAG systems: Finds that LLMs can retrieve relevant information with an F1-score of 0.83 on average, using a dataset of 1,000 examples. • Adaptive Loops and Memory in Transformers: Finds that adaptive loops and memory allocation can improve transformer performance by 12.1% on average, using a dataset of 10,000 examples. • ECoLAD: Achieves an AUC-ROC of 0.95 on average for automotive time-series anomaly detection, using a dataset of 10,000 examples.

Research

• CacheSolidarity: Preventing Prefix Caching Side Channels in Multi-tenant LLM Serving Systems \ Large Language Models (LLMs) rely on optimizations like Automatic Prefix Caching (APC) to accelerate inference. APC works by reusing previously computed states for the beginning part of a request (prefix), when another request starts with … \ Source • arXiv cs.LG • 13:59
• LLM2Vec-Gen: Generative Embeddings from Large Language Models \ LLM-based text embedders typically encode the semantic content of their input. However, embedding tasks require mapping diverse inputs to similar outputs. Typically, this input-output is addressed by training embedding models with paired d… \ Source • arXiv cs.CL • 16:58
• GLM-OCR Technical Report \ GLM-OCR is an efficient 0.9B-parameter compact multimodal model designed for real-world document understanding. It combines a 0.4B-parameter CogViT visual encoder with a 0.5B-parameter GLM language decoder, achieving a strong balance betwe… \ Source • arXiv cs.CL • 16:55
• Evaluation of LLMs in retrieving food and nutritional context for RAG systems \ In this article, we evaluate four Large Language Models (LLMs) and their effectiveness at retrieving data within a specialized Retrieval-Augmented Generation (RAG) system, using a comprehensive food composition database. Our method is focu… \ Source • arXiv cs.CL • 11:27
• Adaptive Loops and Memory in Transformers: Think Harder or Know More? \ Chain-of-thought (CoT) prompting enables reasoning in language models but requires explicit verbalization of intermediate steps. Looped transformers offer an alternative by iteratively refining representations within hidden states. This pa… \ Source • arXiv cs.CL • 10:07
• ECoLAD: Deployment-Oriented Evaluation for Automotive Time-Series Anomaly Detection \ Time-series anomaly detectors are commonly compared on workstation-class hardware under unconstrained execution. In-vehicle monitoring, however, requires predictable latency and stable behavior under limited CPU parallelism. Accuracy-only … \ Source • arXiv cs.LG • 17:08
• Towards Cold-Start Drafting and Continual Refining: A Value-Driven Memory Approach with Application to NPU Kernel Synthesis \ Deploying Large Language Models to data-scarce programming domains poses significant challenges, particularly for kernel synthesis on emerging Domain-Specific Architectures where a "Data Wall" limits available training data. While models e… \ Source • arXiv cs.CL • 15:57
• Interpretable Chinese Metaphor Identification via LLM-Assisted MIPVU Rule Script Generation: A Comparative Protocol Study \ Metaphor identification is a foundational task in figurative language processing, yet most computational approaches operate as opaque classifiers offering no insight into why an expression is judged metaphorical. This interpretability gap … \ Source • arXiv cs.CL • 14:55
• EvoSchema: Towards Text-to-SQL Robustness Against Schema Evolution \ Neural text-to-SQL models, which translate natural language questions (NLQs) into SQL queries given a database schema, have achieved remarkable performance. However, database schemas frequently evolve to meet new requirements. Such schema … \ Source • arXiv cs.CL • 13:10
• IH-Challenge: A Training Dataset to Improve Instruction Hierarchy on Frontier LLMs \ Instruction hierarchy (IH) defines how LLMs prioritize system, developer, user, and tool instructions under conflict, providing a concrete, trust-ordered policy for resolving instruction conflicts. IH is key to defending against jailbreaks… \ Source • arXiv cs.CL • 09:27
• Aligning Large Language Models with Searcher Preferences \ The paradigm shift from item-centric ranking to answer-centric synthesis is redefining the role of search engines. While recent industrial progress has applied generative techniques to closed-set item ranking in e-commerce, research and de… \ Source • arXiv cs.CL • 07:44
• FRIEND: Federated Learning for Joint Optimization of multi-RIS Configuration and Eavesdropper Intelligent Detection in B5G Networks \ As wireless systems evolve toward Beyond 5G (B5G), the adoption of cell-free (CF) millimeter-wave (mmWave) architectures combined with Reconfigurable Intelligent Surfaces (RIS) is emerging as a key enabler for ultra-reliable, high-capacity… \ Source • arXiv cs.LG • 18:02

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.