Skip to content

Research

Page 60 of 88

AI CFD Scientist: Toward Open-Ended Computational Fluid Dynamics Discovery with Physics-Aware AI Agents

research note

AI CFD Scientist: Toward Open-Ended Computational Fluid Dynamics Discovery with Physics-Aware AI Agents

·13 min read·Nithin Somasekharan, Rabi Pathak, Manushri Dhanakoti et al.

AI CFD Scientist addresses the gap between generic LLM-based AI-scientist frameworks (designed for software-only ML research) and the stricter validity requirements of computational fluid dynamics

researchllm-agentsscientific-discoveryautonomous-researchphysics-verification

Read note → Source paper ↗

BAMI: Training-Free Bias Mitigation in GUI Grounding

research note

BAMI: Training-Free Bias Mitigation in GUI Grounding

·13 min read·Borui Zhang, Bo Zhang, Bo Wang et al.

This paper attacks a specific failure mode in GUI grounding—the task of localizing a UI element given a screenshot and a natural-language instruction—by diagnosing *why* state-of-the-art multimodal…

researchgui-groundingtest-time-inferencemultimodal-llmvisual-ui-understanding

Read note → Source paper ↗

Cross-Modal Navigation with Multi-Agent Reinforcement Learning

research note

Cross-Modal Navigation with Multi-Agent Reinforcement Learning

·13 min read·Shuo Liu, Xinzichen Li, Christopher Amato

CRONA addresses the challenge of multi-modal embodied navigation by decomposing the problem across multiple specialized agents rather than forcing a single monolithic model to jointly align and rea…

researchmulti-agent-reinforcement-learningembodied-navigationmulti-modal-perceptiondecentralized-execution

Read note → Source paper ↗

Articles are CC BY 4.0 — feel free to quote with attribution