Copertina

Provably Robust Adaptation for Language-Empowered Foundation Models

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Lai, Yuni, Xue, Xiaoyu, Shen, Linghui, Wu, Yulun, Li, Gaolei, Guo, Song, Zhou, Kai, Xiao, Bin
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

AuditVotes: A Framework Towards More Deployable Certified Robustness for Graph Neural Networks
di: Lai, Yuni, et al.
Pubblicazione: (2025)

Stealthy Dual-Trigger Backdoors: Attacking Prompt Tuning in LM-Empowered Graph Foundation Models
di: Xue, Xiaoyu, et al.
Pubblicazione: (2025)

Defense-as-a-Service: Black-box Shielding against Backdoored Graph Models
di: Yang, Xiao, et al.
Pubblicazione: (2024)

Toward Polymorphic Backdoor against Semantic Communication via Intensity-Based Poisoning
di: Yang, Xiao, et al.
Pubblicazione: (2026)

Multi-Grained Temporal-Spatial Graph Learning for Stable Traffic Flow Forecasting
di: Lin, Zhenan, et al.
Pubblicazione: (2025)

SFR-GNN: Simple and Fast Robust GNNs against Structural Attacks
di: Ai, Xing, et al.
Pubblicazione: (2024)

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

Provable Robust Saliency-based Explanations
di: Chen, Chao, et al.
Pubblicazione: (2022)

Estimating the Empowerment of Language Model Agents
di: Song, Jinyeop, et al.
Pubblicazione: (2025)

Synthetic Series-Symbol Data Generation for Time Series Foundation Models
di: Wang, Wenxuan, et al.
Pubblicazione: (2025)

Theoretical Foundation of Flow-Based Time Series Generation: Provable Approximation, Generalization, and Efficiency
di: Long, Jiangxuan, et al.
Pubblicazione: (2025)

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

Graph Neural Backdoor: Fundamentals, Methodologies, Applications, and Future Directions
di: Yang, Xiao, et al.
Pubblicazione: (2024)

Can LLMs Leverage Observational Data? Towards Data-Driven Causal Discovery with LLMs
di: Susanti, Yuni, et al.
Pubblicazione: (2025)

Spurious Feature Eraser: Stabilizing Test-Time Adaptation for Vision-Language Foundation Model
di: Ma, Huan, et al.
Pubblicazione: (2024)

Provable Robust Overfitting Mitigation in Wasserstein Distributionally Robust Optimization
di: Liu, Shuang, et al.
Pubblicazione: (2025)

Provably Robust Bayesian Counterfactual Explanations under Model Changes
di: Duell, Jamie, et al.
Pubblicazione: (2026)

Vision-Language Model Selection and Reuse for Downstream Adaptation
di: Tan, Hao-Zhe, et al.
Pubblicazione: (2025)

Transformers Provably Implement In-Context Reinforcement Learning with Policy Improvement
di: Liang, Haodong, et al.
Pubblicazione: (2026)

Mitigating Data Scarcity in Time Series Analysis: A Foundation Model with Series-Symbol Data Generation
di: Wang, Wenxuan, et al.
Pubblicazione: (2025)

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

Provable Benefits of In-Tool Learning for Large Language Models
di: Houliston, Sam, et al.
Pubblicazione: (2025)

Provable Training Data Identification for Large Language Models
di: Liu, Zhenlong, et al.
Pubblicazione: (2025)

Doubly Robust Alignment for Large Language Models
di: Xu, Erhan, et al.
Pubblicazione: (2025)

A Provable Expressiveness Hierarchy in Hybrid Linear-Full Attention
di: Ye, Xiaowei, et al.
Pubblicazione: (2026)

Quant-dLLM: Post-Training Extreme Low-Bit Quantization for Diffusion Large Language Models
di: Zhang, Tianao, et al.
Pubblicazione: (2025)

Empowering Time Series Analysis with Foundation Models: A Comprehensive Survey
di: Ye, Jiexia, et al.
Pubblicazione: (2024)

Foundations of Large Language Models
di: Xiao, Tong, et al.
Pubblicazione: (2025)

Learning from the Undesirable: Robust Adaptation of Language Models without Forgetting
di: Nam, Yunhun, et al.
Pubblicazione: (2025)

Large Connectome Model: An fMRI Foundation Model of Brain Connectomes Empowered by Brain-Environment Interaction in Multitask Learning Landscape
di: Wei, Ziquan, et al.
Pubblicazione: (2025)

Zero-shot Meta-learning for Tabular Prediction Tasks with Adversarially Pre-trained Transformer
di: Wu, Yulun, et al.
Pubblicazione: (2025)

Greedy Sampling Is Provably Efficient for RLHF
di: Wu, Di, et al.
Pubblicazione: (2025)

Fast Adaptation with Behavioral Foundation Models
di: Sikchi, Harshit, et al.
Pubblicazione: (2025)

Robust Tabular Foundation Models
di: Peroni, Matthew, et al.
Pubblicazione: (2025)

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

Provable Scaling Laws for the Test-Time Compute of Large Language Models
di: Chen, Yanxi, et al.
Pubblicazione: (2024)

Implicit Hypergraph Neural Networks: A Stable Framework for Higher-Order Relational Learning with Provable Guarantees
di: Li, Xiaoyu, et al.
Pubblicazione: (2025)

Provably Robust and Plausible Counterfactual Explanations for Neural Networks via Robust Optimisation
di: Jiang, Junqi, et al.
Pubblicazione: (2023)

Provable Failure of Language Models in Learning Majority Boolean Logic via Gradient Descent
di: Chen, Bo, et al.
Pubblicazione: (2025)

EdgeMoE: Empowering Sparse Large Language Models on Mobile Devices
di: Yi, Rongjie, et al.
Pubblicazione: (2023)