Image de couverture de livre

Entropy-Adaptive Fine-Tuning: Resolving Confident Conflicts to Mitigate Forgetting

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Diao, Muxi, Yang, Lele, Gong, Wuxuan, Zhang, Yutong, Yan, Zhonghao, Han, Yufei, Liang, Kongming, Xu, Weiran, Ma, Zhanyu
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning Artificial Intelligence Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

MedReasoner: Reinforcement Learning Drives Reasoning Grounding from Clinical Thought to Pixel-Level Precision
par: Yan, Zhonghao, et autres
Publié: (2025)

DriveRX: A Vision-Language Reasoning Model for Cross-Task Autonomous Driving
par: Diao, Muxi, et autres
Publié: (2025)

From Simple to Professional: A Combinatorial Controllable Image Captioning Agent
par: Wang, Xinran, et autres
Publié: (2024)

Hepato-LLaVA: An Expert MLLM with Sparse Topo-Pack Attention for Hepatocellular Pathology Analysis on Whole Slide Images
par: Yang, Yuxuan, et autres
Publié: (2026)

DetailVerifyBench: A Benchmark for Dense Hallucination Localization in Long Image Captions
par: Wang, Xinran, et autres
Publié: (2026)

Harnessing Caption Detailness for Data-Efficient Text-to-Image Generation
par: Wang, Xinran, et autres
Publié: (2025)

Toward Generalizable Forgery Detection and Reasoning
par: Gao, Yueying, et autres
Publié: (2025)

PGP-SAM: Prototype-Guided Prompt Learning for Efficient Few-Shot Medical Image Segmentation
par: Yan, Zhonghao, et autres
Publié: (2025)

CineTechBench: A Benchmark for Cinematographic Technique Understanding and Generation
par: Wang, Xinran, et autres
Publié: (2025)

Multi-Perspective Consistency Enhances Confidence Estimation in Large Language Models
par: Wang, Pei, et autres
Publié: (2024)

RO-Bench: Large-scale robustness evaluation of MLLMs with text-driven counterfactual videos
par: Yang, Zixi, et autres
Publié: (2025)

AutoRed: A Free-form Adversarial Prompt Generation Framework for Automated Red Teaming
par: Diao, Muxi, et autres
Publié: (2025)

Mitigating Catastrophic Forgetting with Adaptive Transformer Block Expansion in Federated Fine-Tuning
par: Huo, Yujia, et autres
Publié: (2025)

Vulnerability-Aware Alignment: Mitigating Uneven Forgetting in Harmful Fine-Tuning
par: Chen, Liang, et autres
Publié: (2025)

Upweighting Easy Samples in Fine-Tuning Mitigates Forgetting
par: Sanyal, Sunny, et autres
Publié: (2025)

Seeing Through the Rain: Resolving High-Frequency Conflicts in Deraining and Super-Resolution via Diffusion Guidance
par: Li, Wenjie, et autres
Publié: (2025)

Benchmarking Segmentation Models with Mask-Preserved Attribute Editing
par: Yin, Zijin, et autres
Publié: (2024)

Reinforcement Fine-Tuning Naturally Mitigates Forgetting in Continual Post-Training
par: Lai, Song, et autres
Publié: (2025)

FairHuman: Boosting Hand and Face Quality in Human Image Generation with Minimum Potential Delay Fairness in Diffusion Models
par: Wang, Yuxuan, et autres
Publié: (2025)

SEAS: Self-Evolving Adversarial Safety Optimization for Large Language Models
par: Diao, Muxi, et autres
Publié: (2024)

Stable Adaptive Thinking via Advantage Shaping and Length-Aware Gradient Regulation
par: Xu, Zihang, et autres
Publié: (2026)

CURLoRA: Stable LLM Continual Fine-Tuning and Catastrophic Forgetting Mitigation
par: Fawi, Muhammad
Publié: (2024)

MoFO: Momentum-Filtered Optimizer for Mitigating Forgetting in LLM Fine-Tuning
par: Chen, Yupeng, et autres
Publié: (2024)

Improved Supervised Fine-Tuning for Large Language Models to Mitigate Catastrophic Forgetting
par: Ding, Fei, et autres
Publié: (2025)

Mitigating Forgetting in LLM Fine-Tuning via Low-Perplexity Token Learning
par: Wu, Chao-Chung, et autres
Publié: (2025)

Fine-Tuning Without Forgetting via Loss-Adaptive Learning Rates
par: Prashant, Parjanya Prajakta, et autres
Publié: (2026)

Meet Dynamic Individual Preferences: Resolving Conflicting Human Value with Paired Fine-Tuning
par: Wang, Shanyong, et autres
Publié: (2026)

DolphCoder: Echo-Locating Code Large Language Models with Diverse and Multi-Objective Instruction Tuning
par: Wang, Yejie, et autres
Publié: (2024)

A Spark Optimizer for Adaptive, Fine-Grained Parameter Tuning
par: Lyu, Chenghao, et autres
Publié: (2024)

Discerning and Resolving Knowledge Conflicts through Adaptive Decoding with Contextual Information-Entropy Constraint
par: Yuan, Xiaowei, et autres
Publié: (2024)

From Parameters to Prompts: Understanding and Mitigating the Factuality Gap between Fine-Tuned LLMs
par: Gong, Xuan, et autres
Publié: (2025)

RAFT: Data Refinement and Adaptive Distillation for Domain Fine-Tuning with Alleviated Forgetting
par: Li, Yuduo, et autres
Publié: (2026)

Efficient Face Super-Resolution via Wavelet-based Feature Enhancement Network
par: Li, Wenjie, et autres
Publié: (2024)

Evaluating Attribute Comprehension in Large Vision-Language Models
par: Zhang, Haiwen, et autres
Publié: (2024)

Benchmarking Semantic Segmentation Models via Appearance and Geometry Attribute Editing
par: Yin, Zijin, et autres
Publié: (2026)

CoCoA: Confidence and Context-Aware Adaptive Decoding for Resolving Knowledge Conflicts in Large Language Models
par: Khandelwal, Anant, et autres
Publié: (2025)

Policy Gradient with Adaptive Entropy Annealing for Continual Fine-Tuning
par: Zhang, Yaqian, et autres
Publié: (2026)

A Sensitivity-Driven Expert Allocation Method in LoRA-MoE for Efficient Fine-Tuning
par: Xu, Junzhou, et autres
Publié: (2025)

The Blind Spot of Adaptation: Quantifying and Mitigating Forgetting in Fine-tuned Driving Models
par: Mao, Runhao, et autres
Publié: (2026)

Polyp-E: Benchmarking the Robustness of Deep Segmentation Models via Polyp Editing
par: Wei, Runpu, et autres
Publié: (2024)