Cover Image

LUMA-RAG: Lifelong Multimodal Agents with Provably Stable Streaming Alignment

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wandre, Rohan, Gajewar, Yash, Patel, Namrata, Dhalkari, Vivek
Format:	Preprint
Published:	2025
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

LUMA: A Benchmark Dataset for Learning from Uncertain and Multimodal Data
by: Bezirganyan, Grigor, et al.
Published: (2024)

ROSFD: Robust Online Streaming Fraud Detection with Resilience to Concept Drift in Data Streams
by: Yelleti, Vivek
Published: (2025)

Towards Provable Emergence of In-Context Reinforcement Learning
by: Wang, Jiuqi, et al.
Published: (2025)

Distribution-Free Robust Predict-Then-Optimize in Function Spaces
by: Patel, Yash, et al.
Published: (2026)

Direct Distributional Optimization for Provable Alignment of Diffusion Models
by: Kawata, Ryotaro, et al.
Published: (2025)

Inference via Interpolation: Contrastive Representations Provably Enable Planning and Inference
by: Eysenbach, Benjamin, et al.
Published: (2024)

Fast Lifelong Adaptive Inverse Reinforcement Learning from Demonstrations
by: Chen, Letian, et al.
Published: (2022)

Provably Convergent Primal-Dual DPO for Constrained LLM Alignment
by: Du, Yihan, et al.
Published: (2025)

Lifelong Safety Alignment for Language Models
by: Wang, Haoyu, et al.
Published: (2025)

Incremental Outlier Detection Modelling Using Streaming Analytics in Finance & Health Care
by: Yelleti, Vivek, et al.
Published: (2023)

Ward: Provable RAG Dataset Inference via LLM Watermarks
by: Jovanović, Nikola, et al.
Published: (2024)

Operator Learning for Schrödinger Equation: Unitarity, Error Bounds, and Time Generalization
by: Patel, Yash, et al.
Published: (2025)

Continuum Transformers Perform In-Context Learning by Operator Gradient Descent
by: Mishra, Abhiti, et al.
Published: (2025)

Controllable Video Generation with Provable Disentanglement
by: Shen, Yifan, et al.
Published: (2025)

One-Step Bellman Alignment Enables Provably Efficient Transfer in Online RL
by: Chen, Elynn, et al.
Published: (2026)

A Greedy PDE Router for Blending Neural Operators and Classical Methods
by: Rayan, Sahana, et al.
Published: (2025)

Lifelong Learning of Video Diffusion Models From a Single Video Stream
by: Yoo, Jason, et al.
Published: (2024)

AltGDmin: Alternating GD and Minimization for Partly-Decoupled (Federated) Optimization
by: Vaswani, Namrata
Published: (2025)

HybridRAG: Integrating Knowledge Graphs and Vector Retrieval Augmented Generation for Efficient Information Extraction
by: Sarmah, Bhaskarjit, et al.
Published: (2024)

OntoRAG: Enhancing Question-Answering through Automated Ontology Derivation from Unstructured Knowledge Bases
by: Tiwari, Yash, et al.
Published: (2025)

Skill-CMIB: Multimodal Agent Skill for Consistent Action via Conditional Multimodal Information Bottleneck
by: Huang, Zihan, et al.
Published: (2026)

Scalable Valuation of Human Feedback through Provably Robust Model Alignment
by: Fujisawa, Masahiro, et al.
Published: (2025)

VERSE: Virtual-Gradient Aware Streaming Lifelong Learning with Anytime Inference
by: Banerjee, Soumya, et al.
Published: (2023)

Conformal Prediction for Ensembles: Improving Efficiency via Score-Based Aggregation
by: Rivera, Eduardo Ochoa, et al.
Published: (2024)

More Edits, More Stable: Understanding the Lifelong Normalization in Sequential Model Editing
by: Ma, Xin, et al.
Published: (2026)

DSCA: Dynamic Subspace Concept Alignment for Lifelong VLM Editing
by: Das, Gyanendra, et al.
Published: (2026)

Decentralized and Lifelong-Adaptive Multi-Agent Collaborative Learning
by: Tang, Shuo, et al.
Published: (2024)

MimirRAG: A Multi-Agent RAG Framework for Financial Data Retrieval with Metadata Integration
by: Samuelsen, Magnus, et al.
Published: (2026)

Conditional Equivalence of DPO and RLHF: Implicit Assumption, Failure Modes, and Provable Alignment
by: Yang, Zhiqin, et al.
Published: (2026)

Privacy-Aware Lifelong Learning
by: Özdenizci, Ozan, et al.
Published: (2025)

Hybrid Preference Optimization for Alignment: Provably Faster Convergence Rates by Combining Offline Preferences with Online Exploration
by: Bose, Avinandan, et al.
Published: (2024)

Learning Equilibria from Data: Provably Efficient Multi-Agent Imitation Learning
by: Freihaut, Till, et al.
Published: (2025)

DynaSTy: A Framework for SpatioTemporal Node Attribute Prediction in Dynamic Graphs
by: Banerji, Namrata, et al.
Published: (2026)

Closing the Loop: A Control-Theoretic Framework for Provably Stable Time Series Forecasting with LLMs
by: Zhang, Xingyu, et al.
Published: (2026)

LeanAgent: Lifelong Learning for Formal Theorem Proving
by: Kumarappan, Adarsh, et al.
Published: (2024)

Leveraging RAG for Training-Free Alignment of LLMs
by: Halloran, John T.
Published: (2026)

Provably Mitigating Corruption, Overoptimization, and Verbosity Simultaneously in Offline and Online RLHF/DPO Alignment
by: Chen, Ziyi, et al.
Published: (2025)

Lifelong Reinforcement Learning via Neuromodulation
by: Lee, Sebastian, et al.
Published: (2024)

Lifelong Graph Learning for Graph Summarization
by: Frank, Jonatan, et al.
Published: (2024)

Provably-Stable Neural Network-Based Control of Nonlinear Systems
by: Li, Anran, et al.
Published: (2025)