:: Library Catalog

Imagen de Portada

Guardado en:

Detalles Bibliográficos
Autores principales:	Liu, Chenruo, Dong, Yijun, Shen, Yiqiu, Lei, Qi
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning
Acceso en línea:	https://arxiv.org/abs/2602.10014
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Does Weak-to-strong Generalization Happen under Spurious Correlations?
por: Liu, Chenruo, et al.
Publicado: (2025)

Superclass-Guided Representation Disentanglement for Spurious Correlation Mitigation
por: Liu, Chenruo, et al.
Publicado: (2025)

Bridging Distribution Shift and AI Safety: Conceptual and Methodological Synergies
por: Liu, Chenruo, et al.
Publicado: (2025)

Teaching by Failure: Counter-Example-Driven Curricula for Transformer Self-Improvement
por: Vejendla, Harshil
Publicado: (2025)

The Unreasonable Effectiveness of Easy Training Data for Hard Tasks
por: Hase, Peter, et al.
Publicado: (2024)

Language Models Do Hard Arithmetic Tasks Easily and Hardly Do Easy Arithmetic Tasks
por: Gambardella, Andrew, et al.
Publicado: (2024)

When does Chain-of-Thought Help: A Markovian Perspective
por: Wang, Zihan, et al.
Publicado: (2026)

Self-Improving Transformers Overcome Easy-to-Hard and Length Generalization Challenges
por: Lee, Nayoung, et al.
Publicado: (2025)

Easy-to-Hard Generalization: Scalable Alignment Beyond Human Supervision
por: Sun, Zhiqing, et al.
Publicado: (2024)

Curriculum Reinforcement Learning from Easy to Hard Tasks Improves LLM Reasoning
por: Parashar, Shubham, et al.
Publicado: (2025)

WIST: Web-Grounded Iterative Self-Play Tree for Domain-Targeted Reasoning Improvement
por: Li, Fangyuan, et al.
Publicado: (2026)

Bootstrapping Task Spaces for Self-Improvement
por: Jiang, Minqi, et al.
Publicado: (2025)

Learning Compositional Functions with Transformers from Easy-to-Hard Data
por: Wang, Zixuan, et al.
Publicado: (2025)

Multi-Agent Imitation Learning: Value is Easy, Regret is Hard
por: Tang, Jingwu, et al.
Publicado: (2024)

Sparsity via Hyperpriors: A Theoretical and Algorithmic Study under Empirical Bayes Framework
por: Li, Zhitao, et al.
Publicado: (2025)

Sketchy Moment Matching: Toward Fast and Provable Data Selection for Finetuning
por: Dong, Yijun, et al.
Publicado: (2024)

Compress the Easy, Explore the Hard: Difficulty-Aware Entropy Regularization for Efficient LLM Reasoning
por: Luo, Qin-Wen, et al.
Publicado: (2026)

MetaLint: Easy-to-Hard Generalization for Code Linting
por: Naik, Atharva, et al.
Publicado: (2025)

More Consistent Accuracy PINN via Alternating Easy-Hard Training
por: Gao, Zhaoqian, et al.
Publicado: (2025)

Dissecting Sample Hardness: A Fine-Grained Analysis of Hardness Characterization Methods for Data-Centric AI
por: Seedat, Nabeel, et al.
Publicado: (2024)

The Easy Path to Robustness: Coreset Selection using Sample Hardness
por: Ramesh, Pranav, et al.
Publicado: (2025)

Frustratingly Easy Task-aware Pruning for Large Language Models
por: Tian, Yuanhe, et al.
Publicado: (2025)

Sample-Centric Multi-Task Learning for Detection and Segmentation of Industrial Surface Defects
por: Dong, Hang-Cheng, et al.
Publicado: (2025)

EH-MAM: Easy-to-Hard Masked Acoustic Modeling for Self-Supervised Speech Representation Learning
por: Seth, Ashish, et al.
Publicado: (2024)

Towards Initialization-Agnostic Clustering with Iterative Adaptive Resonance Theory
por: Qu, Xiaozheng, et al.
Publicado: (2025)

SC2Arena and StarEvolve: Benchmark and Self-Improvement Framework for LLMs in Complex Decision-Making Tasks
por: Shen, Pengbo, et al.
Publicado: (2025)

Probabilistic Iterative Hard Thresholding for Sparse Learning
por: Bergamaschi, Matteo, et al.
Publicado: (2024)

Normalized Iterative Hard Thresholding for Tensor Recovery
por: Li, Li, et al.
Publicado: (2025)

Easy Adaptation: An Efficient Task-Specific Knowledge Injection Method for Large Models in Resource-Constrained Environments
por: Chen, Dong, et al.
Publicado: (2025)

EasyTime: Time Series Forecasting Made Easy
por: Qiu, Xiangfei, et al.
Publicado: (2024)

Discrepancies are Virtue: Weak-to-Strong Generalization through Lens of Intrinsic Dimension
por: Dong, Yijun, et al.
Publicado: (2025)

Thermodynamics of Reinforcement Learning Curricula
por: Adamczyk, Jacob, et al.
Publicado: (2026)

Easy to Learn, Yet Hard to Forget: Towards Robust Unlearning Under Bias
por: Kwon, JuneHyoung, et al.
Publicado: (2026)

Enhancing Sample Selection Against Label Noise by Cutting Mislabeled Easy Examples
por: Yuan, Suqin, et al.
Publicado: (2025)

Easy2Hard-Bench: Standardized Difficulty Labels for Profiling LLM Performance and Generalization
por: Ding, Mucong, et al.
Publicado: (2024)

Detecting is Easy, Adapting is Hard: Local Expert Growth for Visual Model-Based Reinforcement Learning under Distribution Shift
por: Zhao, Haiyang
Publicado: (2026)

Bottom-Up Synthesis of Knowledge-Grounded Task-Oriented Dialogues with Iteratively Self-Refined Prompts
por: Qian, Kun, et al.
Publicado: (2025)

Reward-Free Curricula for Training Robust World Models
por: Rigter, Marc, et al.
Publicado: (2023)

HEDN: A Hard-Easy Dual Network with Source Reliability Assessment for Cross-Subject EEG Emotion Recognition
por: Wang, Qiang, et al.
Publicado: (2025)

Easy Samples Are All You Need: Self-Evolving LLMs via Data-Efficient Reinforcement Learning
por: Yu, Zhiyin, et al.
Publicado: (2026)