Imagen de Portada

Robust Multimodal Safety via Conditional Decoding

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Kumar, Anurag, Peri, Raghuveer, Burnsky, Jon, Nelus, Alexandru, Paturi, Rohit, Vishnubhotla, Srikanth, Qi, Yanjun
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

SEAL: Speaker Error Correction using Acoustic-conditioned Large Language Models
por: Kumar, Anurag, et al.
Publicado: (2025)

AG-LSEC: Audio Grounded Lexical Speaker Error Correction
por: Paturi, Rohit, et al.
Publicado: (2024)

Speakers Unembedded: Embedding-free Approach to Long-form Neural Diarization
por: Li, Xiang, et al.
Publicado: (2024)

Dense and Diverse Goal Coverage in Multi Goal Reinforcement Learning
por: Singh, Sagalpreet, et al.
Publicado: (2025)

Speculative Safety-Aware Decoding
por: Wang, Xuekang, et al.
Publicado: (2025)

A Closer Look at Adversarial Suffix Learning for Jailbreaking LLMs: Augmented Adversarial Trigger Learning
por: Wang, Zhe, et al.
Publicado: (2025)

Learning from Label Proportions: Bootstrapping Supervised Learners via Belief Propagation
por: Havaldar, Shreyas, et al.
Publicado: (2023)

Cross-Session Decoding of Neural Spiking Data via Task-Conditioned Latent Alignment
por: Zhao, Canyang, et al.
Publicado: (2026)

Reinforcement Learning Based Escape Route Generation in Low Visibility Environments
por: Srikanth, Hari
Publicado: (2024)

Fairness under Covariate Shift: Improving Fairness-Accuracy tradeoff with few Unlabeled Test Samples
por: Havaldar, Shreyas, et al.
Publicado: (2023)

SinkRouter: Sink-Aware Routing for Efficient Long-Context Decoding in Large Language and Multimodal Models
por: Liu, Junnan, et al.
Publicado: (2026)

CARE: Decoding Time Safety Alignment via Rollback and Introspection Intervention
por: Hu, Xiaomeng, et al.
Publicado: (2025)

Improving Traffic Flow Predictions with SGCN-LSTM: A Hybrid Model for Spatial and Temporal Dependencies
por: Cismaru, Alexandru T.
Publicado: (2024)

Decoding the Multimodal Maze: A Systematic Review on the Adoption of Explainability in Multimodal Attention-based Models
por: Kibria, Md Raisul, et al.
Publicado: (2025)

MHARFedLLM: Multimodal Human Activity Recognition Using Federated Large Language Model
por: Bandyopadhyay, Asmit, et al.
Publicado: (2025)

Hardness-Aware Dynamic Curriculum Learning for Robust Multimodal Emotion Recognition with Missing Modalities
por: Liu, Rui, et al.
Publicado: (2025)

Breaking the Safety-Capability Tradeoff: Reinforcement Learning with Verifiable Rewards Maintains Safety Guardrails in LLMs
por: Cho, Dongkyu Derek, et al.
Publicado: (2025)

CoRe-Gen: Robust Spectrum-to-Structure Generation under Imperfect Fingerprint Conditions
por: Liu, Tianbo, et al.
Publicado: (2026)

Spectral Higher-Order Neural Networks
por: Peri, Gianluca, et al.
Publicado: (2026)

Multimodal Representation Learning Conditioned on Semantic Relations
por: Qiao, Yang, et al.
Publicado: (2025)

Robust Multi-Objective Controlled Decoding of Large Language Models
por: Son, Seongho, et al.
Publicado: (2025)

Fuzzy Rule based Intelligent Cardiovascular Disease Prediction using Complex Event Processing
por: Kumar, Shashi Shekhar, et al.
Publicado: (2024)

Constrained Decoding for Secure Code Generation
por: Fu, Yanjun, et al.
Publicado: (2024)

Online Learning under Haphazard Input Conditions: A Comprehensive Review and Analysis
por: Agarwal, Rohit, et al.
Publicado: (2024)

Unveiling the Potential of Robustness in Selecting Conditional Average Treatment Effect Estimators
por: Huang, Yiyan, et al.
Publicado: (2024)

XFMNet: Decoding Cross-Site and Nonstationary Water Patterns via Stepwise Multimodal Fusion for Long-Term Water Quality Forecasting
por: Wang, Ziqi, et al.
Publicado: (2025)

Robust Multimodal Representation Learning in Healthcare
por: Zhu, Xiaoguang, et al.
Publicado: (2026)

Towards Building a Robust Toxicity Predictor
por: Bespalov, Dmitriy, et al.
Publicado: (2024)

SCENT: Robust Spatiotemporal Learning for Continuous Scientific Data via Scalable Conditioned Neural Fields
por: Park, David Keetae, et al.
Publicado: (2025)

AI-CARE: Carbon-Aware Reporting Evaluation Metric for AI Models
por: Santosh, KC, et al.
Publicado: (2026)

Curriculum Learning for Safety Alignment
por: Kumar, Sandeep, et al.
Publicado: (2026)

Discrete State Diffusion Models: A Sample Complexity Perspective
por: Srikanth, Aadithya, et al.
Publicado: (2025)

Zero-knowledge LLM hallucination detection and mitigation through fine-grained cross-model consistency
por: Goel, Aman, et al.
Publicado: (2025)

Less is More for Improving Automatic Evaluation of Factual Consistency
por: Wang, Tong, et al.
Publicado: (2024)

Multimodal Federated Learning in Healthcare: a Review
por: Thrasher, Jacob, et al.
Publicado: (2023)

Faster Cascades via Speculative Decoding
por: Narasimhan, Harikrishna, et al.
Publicado: (2024)

AI Alignment via Incentives and Correction
por: Agarwal, Rohit, et al.
Publicado: (2026)

Neural Networks Decoded: Targeted and Robust Analysis of Neural Network Decisions via Causal Explanations and Reasoning
por: Diallo, Alec F., et al.
Publicado: (2024)

On Speculative Decoding for Multimodal Large Language Models
por: Gagrani, Mukul, et al.
Publicado: (2024)

Dissecting Chronos: Sparse Autoencoders Reveal Causal Feature Hierarchies in Time Series Foundation Models
por: Mishra, Anurag
Publicado: (2026)