Cover Image

Black-box Model Merging for Language-Model-as-a-Service with Massive Model Repositories

Fuente: arXiv

Saved in:

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

Similar Items

LifeAlign: Lifelong Alignment for Large Language Models with Memory-Augmented Focalized Preference Optimization
by: Li, Junsong, 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)

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)

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

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

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

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

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

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

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

TypeScript Repository Indexing for Code Agent Retrieval
by: Pu, Junsong, et al.
Published: (2026)

Knowledge Editing on Black-box Large Language Models
by: Song, Xiaoshuai, et al.
Published: (2024)

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)

MergePrint: Merge-Resistant Fingerprints for Robust Black-box Ownership Verification of Large Language Models
by: Yamabe, Shojiro, et al.
Published: (2024)

Defense-as-a-Service: Black-box Shielding against Backdoored Graph Models
by: Yang, Xiao, et al.
Published: (2024)

Privacy-preserving Universal Adversarial Defense for Black-box Models
by: Li, Qiao, et al.
Published: (2024)

From Black-box to Causal-box: Towards Building More Interpretable Models
by: Hwang, Inwoo, et al.
Published: (2025)

CLMTracing: Black-box User-level Watermarking for Code Language Model Tracing
by: Zhang, Boyu, et al.
Published: (2025)

BLADE: Enhancing Black-box Large Language Models with Small Domain-Specific Models
by: Li, Haitao, et al.
Published: (2024)

Performance-lossless Black-box Model Watermarking
by: Zhao, Na, et al.
Published: (2023)

CMM-Math: A Chinese Multimodal Math Dataset To Evaluate and Enhance the Mathematics Reasoning of Large Multimodal Models
by: Liu, Wentao, et al.
Published: (2024)

Mathematical Language Models: A Survey
by: Liu, Wentao, et al.
Published: (2023)

MAP: Low-compute Model Merging with Amortized Pareto Fronts via Quadratic Approximation
by: Li, Lu, et al.
Published: (2024)

MergeNet: Knowledge Migration across Heterogeneous Models, Tasks, and Modalities
by: Li, Kunxi, et al.
Published: (2024)

Do Not Merge My Model! Safeguarding Open-Source LLMs Against Unauthorized Model Merging
by: Li, Qinfeng, et al.
Published: (2025)

Weight Scope Alignment: A Frustratingly Easy Method for Model Merging
by: Xu, Yichu, et al.
Published: (2024)

MIRAGE: Misleading Retrieval-Augmented Generation via Black-box and Query-agnostic Poisoning Attacks
by: Chen, Tailun, 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)

MIN-Merging: Merge the Important Neurons for Model Merging
by: Liang, Yunfei
Published: (2025)

AutoMerge: Search-Based Model Merging Framework for Effective Model Reuse
by: Lu, You, et al.
Published: (2026)

Rapid Parameter Estimation for Merging Massive Black Hole Binaries Using Continuous Normalizing Flows
by: Liang, Bo, et al.
Published: (2024)

Model Merging in the Essential Subspace
by: Li, Longhua, et al.
Published: (2026)

Reading Between the Lines: Towards Reliable Black-box LLM Fingerprinting via Zeroth-order Gradient Estimation
by: Shao, Shuo, et al.
Published: (2025)

Serving Innovation: Exploring Patent Agency Service Networks in China
by: Junsong Wang, et al.
Published: (2024)

Leveraging Black-box Models to Assess Feature Importance in Unconditional Distribution
by: Zhou, Jing, et al.
Published: (2024)

NSmark: Null Space Based Black-box Watermarking Defense Framework for Language Models
by: Zhao, Haodong, et al.
Published: (2024)

White-box Membership Inference Attacks against Diffusion Models
by: Pang, Yan, et al.
Published: (2023)

DREAM: Domain-agnostic Reverse Engineering Attributes of Black-box Model
by: Li, Rongqing, et al.
Published: (2024)

DiaHalu: A Dialogue-level Hallucination Evaluation Benchmark for Large Language Models
by: Chen, Kedi, et al.
Published: (2024)