GenAI Daily for Practitioners

Executive Summary • Here are the concise bullets: • SafetyALFRED: Evaluating Safety-Conscious Planning of Multimodal Large Language Models • + Develops a framework for evaluating safety in multimodal language models; uses a simulated environment to test for safety in planning tasks. • Are Large Language Models Economically Viable for Industry Deployment? • + Analyzes the costs of large language model training and deployment; estimates the costs of training a 1B-parameter model at $1.2M and deployment at $0.1M per year. • Enabling Vibration-Based Gesture Recognition on Everyday Furniture via Energy-Efficient FPGA Implementation of 1D Convolutional Networks • + Develops an energy-efficient FPGA implementation of 1D convolutional networks for vibration-based gesture recognition on everyday furniture.

Research

• SafetyALFRED: Evaluating Safety-Conscious Planning of Multimodal Large Language Models \ Multimodal Large Language Models are increasingly adopted as autonomous agents in interactive environments, yet their ability to proactively address safety hazards remains insufficient. We introduce SafetyALFRED, built upon the embodied ag… \ Source • arXiv cs.CL • 18:27
• Are Large Language Models Economically Viable for Industry Deployment? \ Generative AI-powered by Large Language Models (LLMs)-is increasingly deployed in industry across healthcare decision support, financial analytics, enterprise retrieval, and conversational automation, where reliability, efficiency, and cos… \ Source • arXiv cs.CL • 13:25
• Enabling Vibration-Based Gesture Recognition on Everyday Furniture via Energy-Efficient FPGA Implementation of 1D Convolutional Networks \ The growing demand for smart home interfaces has increased interest in non-intrusive sensing methods like vibration-based gesture recognition. While prior studies demonstrated feasibility, they often rely on complex preprocessing and large… \ Source • arXiv cs.LG • 12:45
• SitEmb-v1.5: Improved Context-Aware Dense Retrieval for Semantic Association and Long Story Comprehension \ Retrieval-augmented generation (RAG) over long documents typically involves splitting the text into smaller chunks, which serve as the basic units for retrieval. However, due to dependencies across the original document, contextual informa… \ Source • arXiv cs.CL • 14:01
• CounterRefine: Answer-Conditioned Counterevidence Retrieval for Inference-Time Knowledge Repair in Factual Question Answering \ In factual question answering, many errors are not failures of access but failures of commitment: the system retrieves relevant evidence, yet still settles on the wrong answer. We present CounterRefine, a lightweight inference-time repair … \ Source • arXiv cs.CL • 12:07
• MASS-RAG: Multi-Agent Synthesis Retrieval-Augmented Generation \ Large language models (LLMs) are widely used in retrieval-augmented generation (RAG) to incorporate external knowledge at inference time. However, when retrieved contexts are noisy, incomplete, or heterogeneous, a single generation process… \ Source • arXiv cs.CL • 11:31
• ShadowPEFT: Shadow Network for Parameter-Efficient Fine-Tuning \ Parameter-efficient fine-tuning (PEFT) reduces the training cost of full-parameter fine-tuning for large language models (LLMs) by training only a small set of task-specific parameters while freezing the pretrained backbone. However, exist… \ Source • arXiv cs.CL • 11:17
• Separating Geometry from Probability in the Analysis of Generalization \ The goal of machine learning is to find models that minimize prediction error on data that has not yet been seen. Its operational paradigm assumes access to a dataset $S$ and articulates a scheme for evaluating how well a given model perfo… \ Source • arXiv cs.LG • 17:13
• Cross-Family Speculative Decoding for Polish Language Models on Apple~Silicon: An Empirical Evaluation of Bielik~11B with UAG-Extended MLX-LM \ Speculative decoding accelerates LLM inference by using a small draft model to propose k candidate tokens for a target model to verify. While effective for same-tokenizer pairs on high-bandwidth GPUs, its applicability to cross-family pair… \ Source • arXiv cs.CL • 19:25
• Sessa: Selective State Space Attention \ Modern sequence modeling is dominated by two families: Transformers, whose self-attention can access arbitrary elements of the visible sequence, and structured state-space models, which propagate information through an explicit recurrent s… \ Source • arXiv cs.CL • 18:04
• Detecting Hallucinations in SpeechLLMs at Inference Time Using Attention Maps \ Hallucinations in Speech Large Language Models (SpeechLLMs) pose significant risks, yet existing detection methods typically rely on gold-standard outputs that are costly or impractical to obtain. Moreover, hallucination detection methods … \ Source • arXiv cs.CL • 17:18
• Hybrid Architectures for Language Models: Systematic Analysis and Design Insights \ Recent progress in large language models demonstrates that hybrid architectures--combining self-attention mechanisms with structured state space models like Mamba--can achieve a compelling balance between modeling quality and computational… \ Source • arXiv cs.CL • 15:16

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.