Imagen de Portada

Multi-layer Cross-attention is Provably Optimal for Multi-modal In-context Learning

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Barnfield, Nicholas, Sen, Subhabrata, Sur, Pragya
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

High-dimensional Asymptotics of Langevin Dynamics in Spiked Matrix Models
por: Liang, Tengyuan, et al.
Publicado: (2022)

Optimal and Provable Calibration in High-Dimensional Binary Classification: Angular Calibration and Platt Scaling
por: Li, Yufan, et al.
Publicado: (2025)

Provable Multi-Party Reinforcement Learning with Diverse Human Feedback
por: Zhong, Huiying, et al.
Publicado: (2024)

Multi-modal Multi-kernel Graph Learning for Autism Prediction and Biomarker Discovery
por: Liu, Jin, et al.
Publicado: (2023)

MM-Path: Multi-modal, Multi-granularity Path Representation Learning -- Extended Version
por: Xu, Ronghui, et al.
Publicado: (2024)

Generic Multi-modal Representation Learning for Network Traffic Analysis
por: Gioacchini, Luca, et al.
Publicado: (2024)

Multi-objective Reinforcement Learning with Nonlinear Preferences: Provable Approximation for Maximizing Expected Scalarized Return
por: Peng, Nianli, et al.
Publicado: (2023)

Balance-aware Sequence Sampling Makes Multi-modal Learning Better
por: Guan, Zhi-Hao
Publicado: (2025)

Provably Efficient Reinforcement Learning for Adversarial Restless Multi-Armed Bandits with Unknown Transitions and Bandit Feedback
por: Xiong, Guojun, et al.
Publicado: (2024)

Compute-Optimal LLMs Provably Generalize Better With Scale
por: Finzi, Marc, et al.
Publicado: (2025)

Can Looped Transformers Learn to Implement Multi-step Gradient Descent for In-context Learning?
por: Gatmiry, Khashayar, et al.
Publicado: (2024)

CCPL: Cross-modal Contrastive Protein Learning
por: Zheng, Jiangbin, et al.
Publicado: (2023)

Safe RLHF-V: Safe Reinforcement Learning from Multi-modal Human Feedback
por: Ji, Jiaming, et al.
Publicado: (2025)

VoyagerVision: Investigating the Role of Multi-modal Information for Open-ended Learning Systems
por: Smyth, Ethan, et al.
Publicado: (2025)

Strongly Topology-preserving GNNs for Brain Graph Super-resolution
por: Singh, Pragya, et al.
Publicado: (2024)

LEMMA-RCA: A Large Multi-modal Multi-domain Dataset for Root Cause Analysis
por: Zheng, Lecheng, et al.
Publicado: (2024)

FedMobile: Enabling Knowledge Contribution-aware Multi-modal Federated Learning with Incomplete Modalities
por: Liu, Yi, et al.
Publicado: (2025)

FDRMFL:Multi-modal Federated Feature Extraction Model Based on Information Maximization and Contrastive Learning
por: Wu, Haozhe
Publicado: (2025)

Online Multi-modal Root Cause Identification in Microservice Systems
por: Zheng, Lecheng, et al.
Publicado: (2024)

M3-AD: Reflection-aware Multi-modal, Multi-category, and Multi-dimensional Benchmark and Framework for Industrial Anomaly Detection
por: Huang, Chao, et al.
Publicado: (2026)

Bypassing the Exponential Dependency: Looped Transformers Efficiently Learn In-context by Multi-step Gradient Descent
por: Chen, Bo, et al.
Publicado: (2024)

TSRBench: A Comprehensive Multi-task Multi-modal Time Series Reasoning Benchmark for Generalist Models
por: Yu, Fangxu, et al.
Publicado: (2026)

Cross-attentive Cohesive Subgraph Embedding to Mitigate Oversquashing in GNNs
por: Hossain, Tanvir, et al.
Publicado: (2026)

Triadic-OCD: Asynchronous Online Change Detection with Provable Robustness, Optimality, and Convergence
por: Huang, Yancheng, et al.
Publicado: (2024)

DistilCLIP-EEG: Enhancing Epileptic Seizure Detection Through Multi-modal Learning and Knowledge Distillation
por: Wang, Zexin, et al.
Publicado: (2025)

Multi-head Transformers Provably Learn Symbolic Multi-step Reasoning via Gradient Descent
por: Yang, Tong, et al.
Publicado: (2025)

Provable Last-Iterate Convergence for Multi-Objective Safe LLM Alignment via Optimistic Primal-Dual
por: Li, Yining, et al.
Publicado: (2026)

Unveiling Stochasticity: Universal Multi-modal Probabilistic Modeling for Traffic Forecasting
por: Xiong, Weijiang, et al.
Publicado: (2026)

Connector-S: A Survey of Connectors in Multi-modal Large Language Models
por: Zhu, Xun, et al.
Publicado: (2025)

Analyzing limits for in-context learning
por: Naim, Omar, et al.
Publicado: (2025)

Human-Inspired Multi-Level Reinforcement Learning
por: Wu, Mingkang, et al.
Publicado: (2025)

MOCHA: Multi-modal Objects-aware Cross-arcHitecture Alignment
por: Camuffo, Elena, et al.
Publicado: (2025)

CoPS: Empowering LLM Agents with Provable Cross-Task Experience Sharing
por: Yang, Chen, et al.
Publicado: (2024)

CALM: Consensus-Aware Localized Merging for Multi-Task Learning
por: Yan, Kunda, et al.
Publicado: (2025)

Autoregressive Enzyme Function Prediction with Multi-scale Multi-modality Fusion
por: Rong, Dingyi, et al.
Publicado: (2024)

Multi-level Conflict-Aware Network for Multi-modal Sentiment Analysis
por: Gao, Yubo, et al.
Publicado: (2025)

Efficient Multi-Task Reinforcement Learning with Cross-Task Policy Guidance
por: He, Jinmin, et al.
Publicado: (2025)

Internal Cross-layer Gradients for Extending Homogeneity to Heterogeneity in Federated Learning
por: Chan, Yun-Hin, et al.
Publicado: (2023)

Leveraging Foundational Models and Simple Fusion for Multi-modal Physiological Signal Analysis
por: Ghallab, Youssef, et al.
Publicado: (2025)

Multi-layer random features and the approximation power of neural networks
por: Takhanov, Rustem
Publicado: (2024)