All AI stories, newest first.
A new study compares how different FHIR data serialization formats affect LLM performance in medication reconciliation tasks. The findings highlight significant differences in accuracy across serialization methods.
Researchers propose an explainable AML triage framework using LLMs to handle transaction alerts while mitigating hallucinations and ensuring compliance. The approach emphasizes evidence-constrained decision-making to improve auditability and governance.
Researchers propose EvoForest, a novel machine learning approach that evolves computational graphs instead of optimizing weights. This could revolutionize structured prediction problems where the key challenge is discovering what to compute, not just fitting parameters.
Researchers introduce DWTSumm, a Discrete Wavelet Transform (DWT)-based method to enhance LLM summarization of long, domain-specific documents. The approach decomposes text into global and local components, preserving structure and critical details.
DeepSeek has previewed its new V4 model, claiming it rivals US systems like Anthropic and OpenAI. The focus on coding could reshape the AI landscape, especially in technical applications.
DeepSeek-V4 introduces a one-million-token context window, making it the largest available. This breakthrough enables agents to process extensive documents and conversations with unprecedented context retention.
DeepSeek has previewed two new AI models, DeepSeek V4 and DeepSeek V4+, that outperform its previous V3.2 model and significantly close the gap with leading models. The improvements come from architectural enhancements that boost efficiency and performance.
Anthropic's AI assistant Claude can now integrate with popular personal apps, expanding beyond work-related tools. This move positions Claude as a more versatile AI assistant in daily life.
Researchers have developed an autonomous LLM agent that can independently formulate, test, and refine materials science theories. The agent successfully replicated established equations like the Hall-Petch equation and Paris law without human intervention.
Researchers developed AITP, an AI system that uses Multimodal Large Language Models to analyze traffic accidents and assign responsibility based on legal knowledge. This advancement could revolutionize accident investigations and insurance claims.
Researchers developed an AI model using LightGBM and multi-modal feature engineering to detect dosing errors in clinical trial narratives. The system achieved 92% accuracy by combining traditional NLP, semantic embeddings, and medical patterns.
An AI agent has autonomously designed a working RISC-V CPU core from scratch, demonstrating significant progress in AI's ability to tackle complex engineering tasks. The design was verified and fabricated, showing potential for accelerating hardware development.
Researchers introduce AFRILANGDICT, a dictionary of 194.7K entries to enable AI language tutoring in African languages. This work addresses the challenge of developing language-learning systems for languages with limited training resources.
A high school sophomore created a protocol to verify AI agent actions cryptographically. Microsoft integrated the code into their agent governance toolkit.
A new paper provides a comprehensive review of externalization techniques in LLM agents, focusing on memory and harness engineering. It highlights key advancements and challenges in the field.
Researchers propose TTKV, a temporal-tiered KV cache that prioritizes recent memories in LLMs, improving efficiency for long-context inference. This method mimics human memory systems, offering a more scalable solution than existing approaches.
Researchers introduce SAVOIR, a new method for training language agents in social intelligence using Shapley values. This approach improves reward attribution in multi-turn dialogues, addressing a key challenge in reinforcement learning.
A new study identifies specific neurons and attention heads in LLMs that encode harmful stereotypes. The research provides tools to locate and potentially mitigate biases in AI models. Researchers used a combination of contrastive neuron activation analysis and attention head tracking to pinpoint bias sources in GPT-2 Small and Llama 3.2.
A new study identifies reasoning structure as the root cause of safety risks in large reasoning models. Researchers propose AltTrain, a post-training method to alter reasoning paths for safer outputs.
Researchers propose a new method for evaluating LLMs that considers individual user preferences, moving beyond aggregate benchmarks. This approach uses ELO ratings to rank models based on personal context and needs.