CURE: Critical-Token-Guided Re-Concatenation for Entropy-Collapse Prevention

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Li, Qingbin, Xue, Rongkun, Wang, Jie, Zhou, Ming, Li, Zhi, Ji, Xiaofeng, Wang, Yongqi, Liu, Miao, Yang, Zheming, Qiu, Minghui, Yang, Jing
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

From Atoms to Chains: Divergence-Guided Reasoning Curriculum for Unlabeled LLM Domain Adaptation
by: Wang, Yongqi, et al.
Published: (2026)

GThinker: Towards General Multimodal Reasoning via Cue-Guided Rethinking
by: Zhan, Yufei, et al.
Published: (2025)

Not All Negative Samples Are Equal: LLMs Learn Better from Plausible Reasoning
by: Di, Zixiang, et al.
Published: (2026)

Reinforced MLLM: A Survey on RL-Based Reasoning in Multimodal Large Language Models
by: Zhou, Guanghao, et al.
Published: (2025)

Enhancing Pretrained Model-based Continual Representation Learning via Guided Random Projection
by: Li, Ruilin, et al.
Published: (2026)

Logo-VGR: Visual Grounded Reasoning for Open-world Logo Recognition
by: Liang, Zichen, et al.
Published: (2025)

ALTER: Asymmetric LoRA for Token-Entropy-Guided Unlearning of LLMs
by: Chen, Xunlei, et al.
Published: (2026)

Understanding and Preventing Entropy Collapse in RLVR with On-Policy Entropy Flow Optimization
by: Xu, Huimin, et al.
Published: (2026)

Window Token Concatenation for Efficient Visual Large Language Models
by: Li, Yifan, et al.
Published: (2025)

EntropyPrune: Matrix Entropy Guided Visual Token Pruning for Multimodal Large Language Models
by: Wang, Yahong, et al.
Published: (2026)

ThinkDrive: Chain-of-Thought Guided Progressive Reinforcement Learning Fine-Tuning for Autonomous Driving
by: Zhao, Chang, et al.
Published: (2026)

KILL OR CURE?
Published: (1998)

A Novel Beam Tracking Approach for Preventing Beam Collapse
by: Zong, Xiaocun, et al.
Published: (2025)

Caterpillar: A Pure-MLP Architecture with Shifted-Pillars-Concatenation
by: Sun, Jin, et al.
Published: (2023)

CURE-OOD: Benchmarking Out-of-Distribution Detection for Survival Prediction
by: Zhao, Wenjie, et al.
Published: (2026)

Geometric construction of Schur algebras
by: Luo, Li, et al.
Published: (2024)

Valley: Video Assistant with Large Language model Enhanced abilitY
by: Luo, Ruipu, et al.
Published: (2023)

Mimic Human Cognition, Master Multi-Image Reasoning: A Meta-Action Framework for Enhanced Visual Understanding
by: Yin, Jianghao, et al.
Published: (2026)

Jointly Complementary&Competitive Influence Maximization with Concurrent Ally-Boosting and Rival-Preventing
by: Shi, Qihao, et al.
Published: (2023)

Layer as Puzzle Pieces: Compressing Large Language Models through Layer Concatenation
by: Wang, Fei, et al.
Published: (2025)

DEPRESSION: THE TALKING CURE
by: PEPPER, TARA
Published: (2004)

HEALing Entropy Collapse: Enhancing Exploration in Few-Shot RLVR via Hybrid-Domain Entropy Dynamics Alignment
by: Liu, Zhanyu, et al.
Published: (2026)

Entropy-Guided Token Dropout: Training Autoregressive Language Models with Limited Domain Data
by: Wang, Jiapeng, et al.
Published: (2025)

RFPPO: Motion Dynamic RRT based Fluid Field - PPO for Dynamic TF/TA Routing Planning
by: Xue, Rongkun, et al.
Published: (2024)

TokenSkip: Controllable Chain-of-Thought Compression in LLMs
by: Xia, Heming, et al.
Published: (2025)

GTR: Guided Thought Reinforcement Prevents Thought Collapse in RL-based VLM Agent Training
by: Wei, Tong, et al.
Published: (2025)

Token Compensator: Altering Inference Cost of Vision Transformer without Re-Tuning
by: Jie, Shibo, et al.
Published: (2024)

ReAct Meets ActRe: When Language Agents Enjoy Training Data Autonomy
by: Yang, Zonghan, et al.
Published: (2024)

CURE:Circuit-Aware Unlearning for LLM-based Recommendation
by: Chen, Ziheng, et al.
Published: (2026)

Renormalization-group Perspective on Gravitational Critical Collapse
by: Yang, Huan, et al.
Published: (2022)

MLIC++: Linear Complexity Multi-Reference Entropy Modeling for Learned Image Compression
by: Jiang, Wei, et al.
Published: (2023)

MLICv2: Enhanced Multi-Reference Entropy Modeling for Learned Image Compression
by: Jiang, Wei, et al.
Published: (2025)

Magic Tokens: Select Diverse Tokens for Multi-modal Object Re-Identification
by: Zhang, Pingping, et al.
Published: (2024)

ERPO: Token-Level Entropy-Regulated Policy Optimization for Large Reasoning Models
by: Yu, Song, et al.
Published: (2026)

LaDi-RL: Latent Diffusion Reasoning Prevents Entropy Collapse in Reinforcement Learning
by: Kang, Haoqiang, et al.
Published: (2026)

ByteGen: A Tokenizer-Free Generative Model for Orderbook Events in Byte Space
by: Li, Yang, et al.
Published: (2025)

Dynamic Inter-Class Confusion-Aware Encoder for Audio-Visual Fusion in Human Activity Recognition
by: Cong, Kaixuan, et al.
Published: (2025)

Entropy-Guided Dynamic Tokens for Graph-LLM Alignment in Molecular Understanding
by: Jing, Zihao, et al.
Published: (2026)

EARN: Efficient Inference Acceleration for LLM-based Generative Recommendation by Register Tokens
by: Yang, Chaoqun, et al.
Published: (2025)

TO CURE E TO CARE IN SITUAZIONI DI FINE VITA: LA PROPORZIONALITÀ E LE CURE PALLIATIVE
by: Elena Colombetti
Published: (2009)