Quantifying the human visual exposome with vision l... | AI Research
Quantifying the human visual exposome with vision language models This research introduces a new way to understand how our daily visual surroundings influenc...
AI Research Papers
AI Research Papers
Keep up with the latest AI research papers, arXiv releases, and machine learning breakthroughs with plain-English explainers.
Recent Research Papers
Keep up with the latest AI research papers, arXiv releases, and machine learning breakthroughs with plain-English explainers.
Correct Is Not Enough: Training Reasoning Planners... | AI Research
The paper "Correct Is Not Enough: Training Reasoning Planners with Executor-Grounded Rewards" addresses a critical limitation in how we train large language...
Redefining AI Red Teaming in the Agentic Era: From... | AI Research
AI systems are increasingly being integrated into critical sectors like healthcare and finance, making the need for robust security testing—known as "red tea...
EvoLM: Self-Evolving Language Models through Co-Evo... | AI Research
EvoLM: Self-Evolving Language Models through Co-Evolved Discriminative Rubrics Current methods for improving language models after their initial training oft...
SymptomAI: Towards a Conversational AI Agent for Ev... | AI Research
SymptomAI: Towards a Conversational AI Agent for Everyday Symptom Assessment This paper introduces SymptomAI, a conversational AI system designed to conduct...
Contextual Multi-Objective Optimization: Rethinking... | AI Research
Contextual Multi-Objective Optimization: Rethinking Objectives in Frontier AI Systems explores why advanced AI models often struggle in open-ended, real-worl...
From Intent to Execution: Composing Agentic Workflo... | AI Research
From Intent to Execution: Composing Agentic Workflows with Agent Recommendation Creating Multi-Agent Systems (MAS)—where multiple AI agents work together to...
OpenSeeker-v2: Pushing the Limits of Search Agents... | AI Research
OpenSeeker-v2: Pushing the Limits of Search Agents with Informative and High-Difficulty Trajectories The development of high-performance "deep search" AI age...
QKVShare: Quantized KV-Cache Handoff for Multi-Agen... | AI Research
Multi-agent LLM systems running on edge devices face a significant bottleneck: when one agent passes its work to another, the system must either perform an e...
An Agent-Oriented Pluggable Experience-RAG Skill fo... | AI Research
An Agent-Oriented Pluggable Experience-RAG Skill for Experience-Driven Retrieval Strategy Orchestration Retrieval-augmented generation (RAG) systems typicall...