Copertina

InfoSFT: Learn More and Forget Less with Information-Aware Token Weighting

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Sabbaghi, Mahdi, Pappas, George, Javanmard, Adel, Hassani, Hamed
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Robust Policy Optimization to Prevent Catastrophic Forgetting
di: Sabbaghi, Mahdi, et al.
Pubblicazione: (2026)

Explicitly Encoding Structural Symmetry is Key to Length Generalization in Arithmetic Tasks
di: Sabbaghi, Mahdi, et al.
Pubblicazione: (2024)

The curse of overparametrization in adversarial training: Precise analysis of robust generalization for random features regression
di: Hassani, Hamed, et al.
Pubblicazione: (2022)

Adversarial Reasoning at Jailbreaking Time
di: Sabbaghi, Mahdi, et al.
Pubblicazione: (2025)

Conformal Prediction with Learned Features
di: Kiyani, Shayan, et al.
Pubblicazione: (2024)

Length Optimization in Conformal Prediction
di: Kiyani, Shayan, et al.
Pubblicazione: (2024)

Temporal Difference Learning with Compressed Updates: Error-Feedback meets Reinforcement Learning
di: Mitra, Aritra, et al.
Pubblicazione: (2023)

Multi-Round Human-AI Collaboration with User-Specified Requirements
di: Noorani, Sima, et al.
Pubblicazione: (2026)

When to Trust the Cheap Check: Weak and Strong Verification for Reasoning
di: Kiyani, Shayan, et al.
Pubblicazione: (2026)

Decision Theoretic Foundations for Conformal Prediction: Optimal Uncertainty Quantification for Risk-Averse Agents
di: Kiyani, Shayan, et al.
Pubblicazione: (2025)

Conformal Prediction Beyond the Seen: A Missing Mass Perspective for Uncertainty Quantification in Generative Models
di: Noorani, Sima, et al.
Pubblicazione: (2025)

Robust Decision Making with Partially Calibrated Forecasts
di: Kiyani, Shayan, et al.
Pubblicazione: (2025)

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

Human-AI Collaborative Uncertainty Quantification
di: Noorani, Sima, et al.
Pubblicazione: (2025)

Federated Temporal Difference Learning with Linear Function Approximation under Environmental Heterogeneity
di: Wang, Han, et al.
Pubblicazione: (2023)

Learn More, Forget Less: A Gradient-Aware Data Selection Approach for LLM
di: Liu, Yibai, et al.
Pubblicazione: (2025)

Differentially Private Model-X Knockoffs via Johnson-Lindenstrauss Transform
di: Tao, Yuxuan, et al.
Pubblicazione: (2025)

Conformal Inference under High-Dimensional Covariate Shifts via Likelihood-Ratio Regularization
di: Joshi, Sunay, et al.
Pubblicazione: (2025)

Multi-Task Dynamic Pricing in Credit Market with Contextual Information
di: Javanmard, Adel, et al.
Pubblicazione: (2024)

Conformal Risk Minimization with Variance Reduction
di: Noorani, Sima, et al.
Pubblicazione: (2024)

Adversarial Training Should Be Cast as a Non-Zero-Sum Game
di: Robey, Alexander, et al.
Pubblicazione: (2023)

PriorBoost: An Adaptive Algorithm for Learning from Aggregate Responses
di: Javanmard, Adel, et al.
Pubblicazione: (2024)

Robust Feature Learning for Multi-Index Models in High Dimensions
di: Mousavi-Hosseini, Alireza, et al.
Pubblicazione: (2024)

Chordal Sparsity for Lipschitz Constant Estimation of Deep Neural Networks
di: Xue, Anton, et al.
Pubblicazione: (2022)

RL Fine-Tuning Heals OOD Forgetting in SFT
di: Jin, Hangzhan, et al.
Pubblicazione: (2025)

LoRA Learns Less and Forgets Less
di: Biderman, Dan, et al.
Pubblicazione: (2024)

Feature Learning in Linear-Width Two-Layer Networks: Two vs. One Step of Gradient Descent
di: Moniri, Behrad, et al.
Pubblicazione: (2026)

Provable Multi-Task Representation Learning by Two-Layer ReLU Neural Networks
di: Collins, Liam, et al.
Pubblicazione: (2023)

SLIM: Let LLM Learn More and Forget Less with Soft LoRA and Identity Mixture
di: Han, Jiayi, et al.
Pubblicazione: (2024)

Learning Rate Schedules in the Presence of Distribution Shift
di: Fahrbach, Matthew, et al.
Pubblicazione: (2023)

Optimistic Rates for Learning from Label Proportions
di: Li, Gene, et al.
Pubblicazione: (2024)

Theoretical Perspectives on Data Quality and Synergistic Effects in Pre- and Post-Training Reasoning Models
di: Javanmard, Adel, et al.
Pubblicazione: (2026)

Understanding the Role of Training Data in Test-Time Scaling
di: Javanmard, Adel, et al.
Pubblicazione: (2025)

Rethinking Tokenization for Clinical Time Series: When Less is More
di: Attrach, Rafi Al, et al.
Pubblicazione: (2025)

Forget Less, Retain More: A Lightweight Regularizer for Rehearsal-Based Continual Learning
di: Alssum, Lama, et al.
Pubblicazione: (2025)

Continual Learning: Less Forgetting, More OOD Generalization via Adaptive Contrastive Replay
di: Rezaei, Hossein, et al.
Pubblicazione: (2024)

Jailbreaking Black Box Large Language Models in Twenty Queries
di: Chao, Patrick, et al.
Pubblicazione: (2023)

Forget Less, Generalize More: Unifying Temporal and Structural Adaptation for Dynamic Graphs
di: Chang, Qian, et al.
Pubblicazione: (2026)

On the Mechanisms of Weak-to-Strong Generalization: A Theoretical Perspective
di: Moniri, Behrad, et al.
Pubblicazione: (2025)

Chameleons do not Forget: Prompt-Based Online Continual Learning for Next Activity Prediction
di: Hassani, Marwan, et al.
Pubblicazione: (2026)