:: Library Catalog

Cover Image

Saved in:

Bibliographic Details
Main Authors:	Liu, Chenruo, Dong, Yijun, Shen, Yiqiu, Lei, Qi
Format:	Preprint
Published:	2026
Subjects:	Machine Learning
Online Access:	https://arxiv.org/abs/2602.10014
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

Thermodynamics of Reinforcement Learning Curricula
by: Adamczyk, Jacob, et al.
Published: (2026)

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

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

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

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

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

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

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

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