Interpretable machine learning for Large Language Models (LLMs) increasingly relies on sparse probing methods that identify small sets of neurons claimed to detect and causally influence behaviors such as factuality recall, safety alignment, and hallucination. These claims have important implications for model auditing...
Huseyin Cavus, Sebin Sabu, J. Spear et al.· 0 citations
Visual software often needs a decision over supplied alternatives rather than a generated explanation. We present PixelJev, a native-image decision interface that maps an image, a task instruction, and a runtime candidate set to a structured choice and candidate-conditioned probabilities using small open multimodal mod...
Xun-Lan Zhou, Xian-Liang Yang, Li Zhao· 1 citation
This paper proposes a training-free inference-stage enhancement termed Semantic-Sharpened Masked Language Modeling, which achieves performance comparable to knowledge-enhanced models without additional training or structural modifications, thereby improving the balance between overall accuracy and sense-level discrimin...
This work asks whether an implemented cross-lingual retrieval-augmented generation prototype can accept Somali symptom narratives, retrieve English medical-textbook evidence, and return a structured Somali response with explicit safety boundaries and page-level citations.
Hamza Abdiaziz Mohamed, Dalmar Abdullahi Mohamud, Zahra Abdullahi Mohamed et al.· Discover Artificial Intellig...· 0 citations
This work introduces a framework to evaluate the behavioral stability of LLM decision systems transforming IoT telemetry to semantic output, and argues behavioral stability in LLM-integrated IoT systems must be evaluated jointly with sensing reliability and regime structure.
J. A. D. López, Christopher Abou-Najm, Saksham Dawhan et al.· IEEE Internet of Things Jour...· 0 citations
Large language models (LLMs) have demonstrated significant potential in improving robotics applications through natural language processing capabilities. Matrix multiplication dominates the computational workload in these LLM-based robotics systems, and resistive random access memory (ReRAM) provides notable performanc...
Wen-Jing Xiao, Jianyu Wang, Dan Chen et al.· IEEE Transactions on Compute...· 0 citations
Video understanding is usually benchmarked on curated, single-actor, or professionally filmed clips, and a strong score there is routinely read as evidence a model is robust enough for deployment. Amateur team sport is a useful, largely untested place to check that assumption: over eight million students played a schoo...
Sai Varun Kodathala, Prashanth Pollishetty, J. Cargill· 0 citations
This paper presents a two-phase training framework that combines Supervised Fine-Tuning (SFT) and Group Relative Policy Optimization (GRPO) to enhance reasoning and IoT control capabilities in small language models. The proposed approach enables a reasoning-enhanced model to interpret real-time sensor data and control...
Ashish Prasad, Saurav Kumar· Zenodo (CERN European Organi...· 0 citations
The machine's PILOT argues that cooperation between open science platforms, among them the Global Open Science Cloud, the African Open Science Platform, and the European Open Science Cloud, is secured not in the description of content, which inference increasingly supplies, but in the act by which one holder offers goo...
Francis P. Crawley· Zenodo (CERN European Organi...· 0 citations
Abstract Neuromuscular system diseases may lead to severe paralysis and loss of language function. Patients cannot communicate normally with the outside world and are difficult to receive timely help. To address this issue, researchers have developed various alternative communication technologies, among which breathing...
