Copertina

Correction of Transformer-Based Models with Smoothing Pseudo-Projector

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autore principale:	Bulgakov, Vitaly
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Dimensionality Reduction in Sentence Transformer Vector Databases with Fast Fourier Transform
di: Bulgakov, Vitaly, et al.
Pubblicazione: (2024)

Optimization of Retrieval-Augmented Generation Context with Outlier Detection
di: Bulgakov, Vitaly
Pubblicazione: (2024)

Reasoning-Enhanced Rare-Event Prediction with Balanced Outcome Correction
di: Bulgakov, Vitaly, et al.
Pubblicazione: (2026)

Parameter Efficient Mamba Tuning via Projector-targeted Diagonal-centric Linear Transformation
di: Ham, Seokil, et al.
Pubblicazione: (2024)

Causes in neuron diagrams, and testing causal reasoning in Large Language Models. A glimpse of the future of philosophy?
di: Vervoort, Louis, et al.
Pubblicazione: (2025)

Semi-supervised CAPP Transformer Learning via Pseudo-labeling
di: Gross, Dennis, et al.
Pubblicazione: (2026)

DreamSmooth: Improving Model-based Reinforcement Learning via Reward Smoothing
di: Lee, Vint, et al.
Pubblicazione: (2023)

Anomaly Correction of Business Processes Using Transformer Autoencoder
di: Gong, Ziyou, et al.
Pubblicazione: (2024)

Cliqueformer: Model-Based Optimization with Structured Transformers
di: Kuba, Jakub Grudzien, et al.
Pubblicazione: (2024)

Calibrated Language Models and How to Find Them with Label Smoothing
di: Huang, Jerry, et al.
Pubblicazione: (2025)

Honeybee: Locality-enhanced Projector for Multimodal LLM
di: Cha, Junbum, et al.
Pubblicazione: (2023)

Memory Injections: Correcting Multi-Hop Reasoning Failures during Inference in Transformer-Based Language Models
di: Sakarvadia, Mansi, et al.
Pubblicazione: (2023)

Vanishing Contributions: A Unified Framework for Smooth and Iterative Model Compression
di: Nikiforos, Lorenzo, et al.
Pubblicazione: (2025)

SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks
di: Robey, Alexander, et al.
Pubblicazione: (2023)

ASER: Activation Smoothing and Error Reconstruction for Large Language Model Quantization
di: Zhao, Weibo, et al.
Pubblicazione: (2024)

Certified Robustness for Deep Equilibrium Models via Serialized Random Smoothing
di: Gao, Weizhi, et al.
Pubblicazione: (2024)

Bayesian Pseudo-Coresets via Contrastive Divergence
di: Tiwary, Piyush, et al.
Pubblicazione: (2023)

Regulating Model Reliance on Non-Robust Features by Smoothing Input Marginal Density
di: Yang, Peiyu, et al.
Pubblicazione: (2024)

Outlier-Efficient Hopfield Layers for Large Transformer-Based Models
di: Hu, Jerry Yao-Chieh, et al.
Pubblicazione: (2024)

Pool Me Wisely: On the Effect of Pooling in Transformer-Based Models
di: Ennadir, Sofiane, et al.
Pubblicazione: (2025)

Smooth Min-Max Monotonic Networks
di: Igel, Christian
Pubblicazione: (2023)

Posterior Label Smoothing for Node Classification
di: Heo, Jaeseung, et al.
Pubblicazione: (2024)

No-Regret Reinforcement Learning in Smooth MDPs
di: Maran, Davide, et al.
Pubblicazione: (2024)

Axiomatization of Gradient Smoothing in Neural Networks
di: Zhou, Linjiang, et al.
Pubblicazione: (2024)

How Smoothing is N-simplicial Attention?
di: Dussolle, Alexandre, et al.
Pubblicazione: (2025)

Uncertainty-Based Smooth Policy Regularisation for Reinforcement Learning with Few Demonstrations
di: Zhu, Yujie, et al.
Pubblicazione: (2025)

Neural Organ Transplantation (NOT): Checkpoint-Based Modular Adaptation for Transformer Models
di: Al-Zuraiqi, Ahmad
Pubblicazione: (2026)

Generalizing Few Data to Unseen Domains Flexibly Based on Label Smoothing Integrated with Distributionally Robust Optimization
di: Wang, Yangdi, et al.
Pubblicazione: (2024)

Accelerating Error Correction Code Transformers
di: Levy, Matan, et al.
Pubblicazione: (2024)

Soft Deterministic Policy Gradient with Gaussian Smoothing
di: Na, Hyunjun, et al.
Pubblicazione: (2026)

Variational Inference via Smoothed Particle Hydrodynamics
di: Huang, Yongchao
Pubblicazione: (2024)

Intriguing Properties of Input-dependent Randomized Smoothing
di: Súkeník, Peter, et al.
Pubblicazione: (2021)

Variational Learning Induces Adaptive Label Smoothing
di: Yang, Sin-Han, et al.
Pubblicazione: (2025)

Unveiling and Addressing Pseudo Forgetting in Large Language Models
di: Sun, Huashan, et al.
Pubblicazione: (2024)

Certifying Language Model Robustness with Fuzzed Randomized Smoothing: An Efficient Defense Against Backdoor Attacks
di: He, Bowei, et al.
Pubblicazione: (2025)

Calibration-Gated LLM Pseudo-Observations for Online Contextual Bandits
di: Pershin, Maksim, et al.
Pubblicazione: (2026)

Prototype Training with Dual Pseudo-Inverse and Optimized Hidden Activations
di: Tucci, Mauro
Pubblicazione: (2025)

Grid-Mapping Pseudo-Count Constraint for Offline Reinforcement Learning
di: Shen, Yi, et al.
Pubblicazione: (2024)

Reliable OOD Virtual Screening with Extrapolatory Pseudo-Label Matching
di: Qu, Yunni, et al.
Pubblicazione: (2024)

Transformer-Based Representation Learning for Robust Gene Expression Modeling and Cancer Prognosis
di: Jiang, Shuai, et al.
Pubblicazione: (2025)