Cover Image

LifeAlign: Lifelong Alignment for Large Language Models with Memory-Augmented Focalized Preference Optimization

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Li, Junsong, Zhou, Jie, Zhan, Bihao, Yang, Yutao, Pan, Qianjun, Chen, Shilian, Huai, Tianyu, Li, Xin, Chen, Qin, He, Liang
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Black-box Model Merging for Language-Model-as-a-Service with Massive Model Repositories
by: Chen, Shilian, et al.
Published: (2025)

Forget What's Sensitive, Remember What Matters: Token-Level Differential Privacy in Memory Sculpting for Continual Learning
by: Zhan, Bihao, et al.
Published: (2025)

AutoSkill: Experience-Driven Lifelong Learning via Skill Self-Evolution
by: Yang, Yutao, et al.
Published: (2026)

Reinforced Interactive Continual Learning via Real-time Noisy Human Feedback
by: Yang, Yutao, et al.
Published: (2025)

Teaching LLMs for Step-Level Automatic Math Correction via Reinforcement Learning
by: Li, Junsong, et al.
Published: (2025)

PsychAgent: An Experience-Driven Lifelong Learning Agent for Self-Evolving Psychological Counselor
by: Yang, Yutao, et al.
Published: (2026)

Building Self-Evolving Agents via Experience-Driven Lifelong Learning: A Framework and Benchmark
by: Cai, Yuxuan, et al.
Published: (2025)

A Survey of Slow Thinking-based Reasoning LLMs using Reinforced Learning and Inference-time Scaling Law
by: Pan, Qianjun, et al.
Published: (2025)

Teaching Your Models to Understand Code via Focal Preference Alignment
by: Wu, Jie, et al.
Published: (2025)

PsychEval: A Multi-Session and Multi-Therapy Benchmark for High-Realism AI Psychological Counselor
by: Pan, Qianjun, et al.
Published: (2026)

Can Heterogeneous Language Models Be Fused?
by: Chen, Shilian, et al.
Published: (2026)

Ask Only When Needed: Proactive Retrieval from Memory and Skills for Experience-Driven Lifelong Agents
by: Cai, Yuxuan, et al.
Published: (2026)

Lifelong Safety Alignment for Language Models
by: Wang, Haoyu, et al.
Published: (2025)

FocalOrder: Focal Preference Optimization for Reading Order Detection
by: Liu, Fuyuan, et al.
Published: (2026)

Recent Advances of Foundation Language Models-based Continual Learning: A Survey
by: Yang, Yutao, et al.
Published: (2024)

CROP: Expert-Aligned Image Cropping via Compositional Reasoning and Optimizing Preference
by: Dong, Zhitong, et al.
Published: (2026)

Task-Core Memory Management and Consolidation for Long-term Continual Learning
by: Huai, Tianyu, et al.
Published: (2025)

CriterAlign: Criterion-Centric Rationale Alignment for Code Preference Judging
by: Li, Zhenyu, et al.
Published: (2026)

Re-Align: Aligning Vision Language Models via Retrieval-Augmented Direct Preference Optimization
by: Xing, Shuo, et al.
Published: (2025)

Efficient Excited-State Calculations for Molecules Based on Contextual Subspace Method and Symmetry Optimizations
by: Yao, Qianjun, et al.
Published: (2025)

Follow-Your-Preference: Towards Preference-Aligned Image Inpainting
by: Shen, Yutao, et al.
Published: (2025)

Oracle Noise: Faster Semantic Spherical Alignment for Interpretable Latent Optimization
by: Li, Haosen, et al.
Published: (2026)

Bridging the Gap Between Preference Alignment and Machine Unlearning
by: Feng, Xiaohua, et al.
Published: (2025)

Understand What LLM Needs: Dual Preference Alignment for Retrieval-Augmented Generation
by: Dong, Guanting, et al.
Published: (2024)

Aligning CodeLLMs with Direct Preference Optimization
by: Miao, Yibo, et al.
Published: (2024)

AlignCap: Aligning Speech Emotion Captioning to Human Preferences
by: Liang, Ziqi, et al.
Published: (2024)

OVAL: Open-Vocabulary Augmented Memory Model for Lifelong Object Goal Navigation
by: Pei, Jiahua, et al.
Published: (2026)

Self-Augmented Preference Optimization: Off-Policy Paradigms for Language Model Alignment
by: Yin, Yueqin, et al.
Published: (2024)

FocalPO: Enhancing Preference Optimizing by Focusing on Correct Preference Rankings
by: Liu, Tong, et al.
Published: (2025)

BPO: Towards Balanced Preference Optimization between Knowledge Breadth and Depth in Alignment
by: Wang, Sizhe, et al.
Published: (2024)

AVC-DPO: Aligned Video Captioning via Direct Preference Optimization
by: Tang, Jiyang, et al.
Published: (2025)

Aligning MLLM Benchmark With Human Preferences via Structural Equation Modeling
by: Xiong, Shengwu., et al.
Published: (2025)

SpeechAlign: Aligning Speech Generation to Human Preferences
by: Zhang, Dong, et al.
Published: (2024)

GainRAG: Preference Alignment in Retrieval-Augmented Generation through Gain Signal Synthesis
by: Jiang, Yi, et al.
Published: (2025)

Towards Aligning Personalized Conversational Recommendation Agents with Users' Privacy Preferences
by: Zhang, Shuning, et al.
Published: (2025)

TextAlign: Preference Alignment for Text Rendering with Hierarchical Rewards
by: Cui, Mingxuan, et al.
Published: (2026)

Unsupervised Equivalent Contrastive Learning for Radio Signal Recognition
by: Zheng, Shilian, et al.
Published: (2026)

Preference Ranking Optimization for Human Alignment
by: Song, Feifan, et al.
Published: (2023)

CL-MoE: Enhancing Multimodal Large Language Model with Dual Momentum Mixture-of-Experts for Continual Visual Question Answering
by: Huai, Tianyu, et al.
Published: (2025)

HPS: Hard Preference Sampling for Human Preference Alignment
by: Zou, Xiandong, et al.
Published: (2025)