MIRA-AI-Lab

classroom

https://github.com/mira-ai-lab

Activity Feed Request to join this org

AI & ML interests

Multimodality, Inference (LLM Reasoning), Retrieval (Retrieval Augmented Generation), Agent/Action

Recent Activity

ZhitaoGao authored a paper 14 days ago

Visual-OPSD: Cross-Modal On-Policy Self-Distillation for Efficient Unified Multimodal Reasoning

ZhitaoGao authored a paper 14 days ago

Beyond Individual Intelligence: Surveying Collaboration, Failure Attribution, and Self-Evolution in LLM-based Multi-Agent Systems

ZhitaoGao authored a paper 14 days ago

$\textbf{AGT$^{AO}$}$: Robust and Stabilized LLM Unlearning via Adversarial Gating Training with Adaptive Orthogonality

View all activity

authored 3 papers 14 days ago

Visual-OPSD: Cross-Modal On-Policy Self-Distillation for Efficient Unified Multimodal Reasoning

Paper • 2606.18974 • Published Jun 17 • 3

Beyond Individual Intelligence: Surveying Collaboration, Failure Attribution, and Self-Evolution in LLM-based Multi-Agent Systems

Paper • 2605.14892 • Published May 14 • 51

$\textbf{AGT$^{AO}$}$: Robust and Stabilized LLM Unlearning via Adversarial Gating Training with Adaptive Orthogonality

Paper • 2602.01703 • Published Feb 2 • 2

authored 3 papers 3 months ago

AERO: Autonomous Evolutionary Reasoning Optimization via Endogenous Dual-Loop Feedback

Paper • 2602.03084 • Published Feb 3 • 1

Plan before Solving: Problem-Aware Strategy Routing for Mathematical Reasoning with LLMs

Paper • 2509.24377 • Published Sep 29, 2025

Beyond Individual Intelligence: Surveying Collaboration, Failure Attribution, and Self-Evolution in LLM-based Multi-Agent Systems

Paper • 2605.14892 • Published May 14 • 51

submitted a paper to Daily Papers 3 months ago

Beyond Individual Intelligence: Surveying Collaboration, Failure Attribution, and Self-Evolution in LLM-based Multi-Agent Systems

Paper • 2605.14892 • Published May 14 • 51

authored a paper 5 months ago

AERO: Autonomous Evolutionary Reasoning Optimization via Endogenous Dual-Loop Feedback

Paper • 2602.03084 • Published Feb 3 • 1

authored a paper about 1 year ago

Deliberation on Priors: Trustworthy Reasoning of Large Language Models on Knowledge Graphs

Paper • 2505.15210 • Published May 21, 2025 • 19

updated a collection about 1 year ago

Knowledge Graph

1 item • Updated May 22, 2025 • 1

updated a model over 1 year ago

reml-group/MAVEN

Updated Apr 3, 2025 • 9

updated a dataset over 1 year ago

reml-group/FortisAVQA

Viewer • Updated Apr 3, 2025 • 423k • 46

updated a model over 1 year ago

reml-group/MAVEN

Updated Apr 3, 2025 • 9

published a dataset over 1 year ago

reml-group/FortisAVQA

Viewer • Updated Apr 3, 2025 • 423k • 46

authored 2 papers over 1 year ago

FortisAVQA and MAVEN: a Benchmark Dataset and Debiasing Framework for Robust Multimodal Reasoning

Paper • 2504.00487 • Published Apr 1, 2025 • 18

Debate on Graph: a Flexible and Reliable Reasoning Framework for Large Language Models

Paper • 2409.03155 • Published Sep 5, 2024 • 2

published a model over 1 year ago

reml-group/MAVEN

Updated Apr 3, 2025 • 9

authored a paper over 1 year ago

Debate on Graph: a Flexible and Reliable Reasoning Framework for Large Language Models

Paper • 2409.03155 • Published Sep 5, 2024 • 2

authored 2 papers over 1 year ago

Robust Visual Question Answering: Datasets, Methods, and Future Challenges

Paper • 2307.11471 • Published Jul 21, 2023 • 1

Debate on Graph: a Flexible and Reliable Reasoning Framework for Large Language Models

Paper • 2409.03155 • Published Sep 5, 2024 • 2