Home Knowledge Base Collaborative and Efficient Fine

Collaborative and Efficient Fine

No mentions found

This entity hasn't been tracked yet, or Iris is still building its knowledge base.

Related Articles from SNS

Collaborative and Efficient Fine-tuning: Leveraging Task Similarity

arXiv:2602.07218v2 Announce Type: replace Abstract: Adaptability has been regarded as a central feature in the foundation models, enabling them to effectively acclimate to unseen downstream tasks. Parameter-efficient fine-tuning methods such as celebrated LoRA facilitate efficient adaptation of large foundation models using labeled, high-quality and generally scarce task data. To mitigate data scarcity in fine-tuning of foundation models, we propose to leverage task similarity across...

arXiv CS 8d ago

DECA: Decentralizing Block-Wise Adam for Efficient LLM Full-Parameter Fine-Tuning on Non-IID Data

arXiv:2606.03209v1 Announce Type: new Abstract: Fine-tuning large language models (LLMs) in privacy-sensitive and resource-constrained environments remains challenging. Since training data are often distributed across multiple clients, decentralized fine-tuning offers a natural paradigm for collaborative adaptation without a central server. However, enabling full-parameter fine-tuning (FPFT) in this decentralized setting is difficult: FPFT provides strong adaptation capacity but incurs...

arXiv CS 7d ago

Understanding-Enhanced Model Collaboration for Long-Tailed Egocentric Mistake Detection

new Abstract: In this report, we address the problem of determining whether a user performs an action incorrectly from egocentric video data. To this end, we propose an Understanding-Enhanced Model Collaboration Method (UE-MCM) that combines efficient coarse-grained video understanding with accurate fine-grained action reasoning. Specifically, UE-MCM contains a small model branch and a large model branch.

arXiv CS 8d ago

Maris: A Formally Verifiable Privacy Policy Enforcement Paradigm for Multi-Agent Collaboration Systems

Announce Type: replace Abstract: Multi-agent collaboration systems (MACS), powered by large language models (LLMs), solve complex problems efficiently by leveraging each agent's specialization and communication between agents. However, the inherent exchange of information between agents and their interaction with external environments, such as LLM, tools, and users, inevitably introduces significant risks of sensitive data leakage, including vulnerabilities to attacks such as eavesdropping...

arXiv CS 1d ago

Maris: A Formally Verifiable Privacy Policy Enforcement Paradigm for Multi-Agent Collaboration Systems

arXiv:2505.04799v4 Announce Type: replace Abstract: Multi-agent collaboration systems (MACS), powered by large language models (LLMs), solve complex problems efficiently by leveraging each agent's specialization and communication between agents. However, the inherent exchange of information between agents and their interaction with external environments, such as LLM, tools, and users, inevitably introduces significant risks of sensitive data leakage, including vulnerabilities to attacks such...

arXiv CS 8d ago

Expert Merging in Sparse Mixture of Experts with Nash Bargaining

arXiv:2510.16138v2 Announce Type: replace Abstract: Existing expert merging strategies for Sparse Mixture of Experts (SMoE) typically rely on input-dependent or input-independent averaging of expert parameters, but often lack a principled weighting mechanism. In this work, we reinterpret expert merging through the lens of game theory, revealing cooperative and competitive dynamics among experts. Based on this perspective, we introduce Nash Merging of Experts (NAMEx), a novel framework that...

arXiv CS 9d ago

AlignFed: Alignment-Aware Asynchronous Federated Fine-Tuning for Large Language Models in Heterogeneous Edge Environments

arXiv:2606.08197v1 Announce Type: new Abstract: Large Language Models (LLMs) have significantly propelled the advancement of edge intelligence and have been widely deployed across various scenarios, including autonomous driving, industrial inspection, and personalized IoT services. However, the collaborative adaptation of LLMs on edge devices continues to face formidable challenges due to strict data privacy constraints, highly heterogeneous computing and communication resources, and the...

arXiv CS 1d ago

Federated Large Language Models: Current Progress and Future Directions

arXiv:2409.15723v3 Announce Type: replace Abstract: Large Language Models have achieved impressive performance across diverse applications, yet their training typically depends on centralized data collection, raising serious privacy and governance concerns. Federated Learning offers a decentralized alternative by enabling multiple clients to collaboratively train shared models without exposing raw local data. However, integrating FL with LLMs introduces new challenges, including data...

arXiv CS 1d ago

The future of agriculture

The future of agriculture Lisa Lock Scientific Editor Andrew Zinin Lead Editor It's a mild early spring morning at the historic Cottonwood Field Station in western South Dakota, and a herd of 150 Angus steers are scheduled to move to a new pasture rotation. Moving cattle can be tricky and often requires some extra help, electrical fencing and quite a bit of time. But today, there are no extra ranchers, no gates swinging open and no temporary fences in place.

Phys.org 8d ago

FFR: Forward-Forward Learning for Regression

arXiv:2606.03927v1 Announce Type: new Abstract: The Forward-Forward (FF) algorithm offers a computationally efficient and biologically plausible alternative to backpropagation (BP) by training neural networks through purely local, layer-wise optimization. However, FF is inherently designed for classification via contrastive positive-negative sample pairs, and extending it to regression poses fundamental challenges: continuous target space lack natural "opposites" for contrastive learning,...

arXiv CS 7d ago