Large Language Models

Google’s Gemini AI can answer your questions with 3D models and simulations

Google's latest upgrade for Gemini will allow the chatbot to generate interactive 3D models and simulations in response to your questions...

Moody’s Integrates AI Agents With Anthropic’s Claude

AI on the couch: Anthropic gives Claude 20 hours of psychiatry

[2603.04355] Efficient Refusal Ablation in LLM through Optimal Transport

Abstract page for arXiv paper 2603.04355: Efficient Refusal Ablation in LLM through Optimal Transport

[2603.04354] Out-of-distribution transfer of PDE foundation models to material dynamics under extreme loading

Abstract page for arXiv paper 2603.04354: Out-of-distribution transfer of PDE foundation models to material dynamics under extreme loading

[2603.03752] Confidence-Calibrated Small-Large Language Model Collaboration for Cost-Efficient Reasoning

Abstract page for arXiv paper 2603.03752: Confidence-Calibrated Small-Large Language Model Collaboration for Cost-Efficient Reasoning

[2603.04300] LUMINA: Foundation Models for Topology Transferable ACOPF

Abstract page for arXiv paper 2603.04300: LUMINA: Foundation Models for Topology Transferable ACOPF

[2603.03739] PROSPECT: Unified Streaming Vision-Language Navigation via Semantic--Spatial Fusion and Latent Predictive Representation

Abstract page for arXiv paper 2603.03739: PROSPECT: Unified Streaming Vision-Language Navigation via Semantic--Spatial Fusion and Latent ...

[2603.03727] Understanding Parents' Desires in Moderating Children's Interactions with GenAI Chatbots through LLM-Generated Probes

Abstract page for arXiv paper 2603.03727: Understanding Parents' Desires in Moderating Children's Interactions with GenAI Chatbots throug...

[2603.04276] Causality Elicitation from Large Language Models

Abstract page for arXiv paper 2603.04276: Causality Elicitation from Large Language Models

[2603.04142] A Multi-Agent Framework for Interpreting Multivariate Physiological Time Series

Abstract page for arXiv paper 2603.04142: A Multi-Agent Framework for Interpreting Multivariate Physiological Time Series

[2603.03681] EvoPrune: Early-Stage Visual Token Pruning for Efficient MLLMs

Abstract page for arXiv paper 2603.03681: EvoPrune: Early-Stage Visual Token Pruning for Efficient MLLMs

[2603.03677] MIND: Unified Inquiry and Diagnosis RL with Criteria Grounded Clinical Supports for Psychiatric Consultation

Abstract page for arXiv paper 2603.03677: MIND: Unified Inquiry and Diagnosis RL with Criteria Grounded Clinical Supports for Psychiatric...

[2603.04135] Unbiased Dynamic Pruning for Efficient Group-Based Policy Optimization

Abstract page for arXiv paper 2603.04135: Unbiased Dynamic Pruning for Efficient Group-Based Policy Optimization

[2603.03637] Image-based Prompt Injection: Hijacking Multimodal LLMs through Visually Embedded Adversarial Instructions

Abstract page for arXiv paper 2603.03637: Image-based Prompt Injection: Hijacking Multimodal LLMs through Visually Embedded Adversarial I...

[2603.03633] Goal-Driven Risk Assessment for LLM-Powered Systems: A Healthcare Case Study

Abstract page for arXiv paper 2603.03633: Goal-Driven Risk Assessment for LLM-Powered Systems: A Healthcare Case Study

[2603.04045] Inference-Time Toxicity Mitigation in Protein Language Models

Abstract page for arXiv paper 2603.04045: Inference-Time Toxicity Mitigation in Protein Language Models

[2603.03590] Social Norm Reasoning in Multimodal Language Models: An Evaluation

Abstract page for arXiv paper 2603.03590: Social Norm Reasoning in Multimodal Language Models: An Evaluation

[2603.03585] Belief-Sim: Towards Belief-Driven Simulation of Demographic Misinformation Susceptibility

Abstract page for arXiv paper 2603.03585: Belief-Sim: Towards Belief-Driven Simulation of Demographic Misinformation Susceptibility

[2603.04028] A Multi-Dimensional Quality Scoring Framework for Decentralized LLM Inference with Proof of Quality

Abstract page for arXiv paper 2603.04028: A Multi-Dimensional Quality Scoring Framework for Decentralized LLM Inference with Proof of Qua...

[2603.03555] Molt Dynamics: Emergent Social Phenomena in Autonomous AI Agent Populations

Abstract page for arXiv paper 2603.03555: Molt Dynamics: Emergent Social Phenomena in Autonomous AI Agent Populations

[2603.03543] Tucano 2 Cool: Better Open Source LLMs for Portuguese

Abstract page for arXiv paper 2603.03543: Tucano 2 Cool: Better Open Source LLMs for Portuguese

[2603.03541] RAG-X: Systematic Diagnosis of Retrieval-Augmented Generation for Medical Question Answering

Abstract page for arXiv paper 2603.03541: RAG-X: Systematic Diagnosis of Retrieval-Augmented Generation for Medical Question Answering