arXiv Machine Learning July 7, 2026 By Wei Zhang, Lin Tang, Ming Zhao, Yuxuan Wang

Co-Adaptive Multi-Task LoRA: Transfer-Aware, Label-Free Control of Domain Participation

Read the original on arXiv Machine Learning →

arXiv:2607. 03522v1 Announce Type: new Abstract: Fine-tuning a single low-rank adapter on many domains at once is multi-task learning: the domains must be co-learned, and how they share the adapter decides whether they help or hurt one another.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

fine-tuning

arXiv Machine Learning

Jun 18

PACT: Preserving Anchored Cores in Task-vectors for Model Merging

arXiv:2606. 18627v1 Announce Type: new Abstract: Model merging has emerged as a training-free alternative to multi-task learning, aiming to combine multiple task-specific fine-tuned models into a single multi-task model.

By Ningyuan Shi, Zhipeng Zhou, Hao Wang, Chunyan Miao, Peilin Zhao

fine-tuning benchmarks

arXiv Machine Learning

Aug 10

Training-free Task Classification for Multi-Task Model Merging

arXiv:2606. 22589v2 Announce Type: replace Abstract: Ever since the advent of foundation models and the pre-training-finetuning paradigm, there have been numerous efforts to merge multiple task-specific experts into a single multi-task model.

By Jungyong Son, Jinwook Jung, Sungyong Baik

computer-vision nlp fine-tuning benchmarks

arXiv AI

Jun 4

SUSD: Structured Unsupervised Skill Discovery through State Factorization

arXiv:2602. 01619v2 Announce Type: replace-cross Abstract: Unsupervised Skill Discovery (USD) aims to autonomously learn a diverse set of skills without relying on extrinsic rewards.

By Seyed Mohammad Hadi Hosseini, Mahdieh Soleymani Baghshah

agents reinforcement-learning

arXiv AI

Jul 21

Capacity and Redundancy Trade-offs in Multi-Task Learning

arXiv:2607. 16554v1 Announce Type: cross Abstract: In multi-task learning (MTL) negative transfer is often considered as an optimization artifact, but it can also be viewed as a consequence of limited shared capacity and weak task redundancy.

By Asif Khan

fine-tuning

arXiv AI

Jul 20

PASs-MoE: Mitigating Misaligned Co-drift among Router and Experts via Pathway Activation Subspaces for Continual Learning

arXiv:2601. 13020v2 Announce Type: replace-cross Abstract: Continual instruction tuning (CIT) requires multimodal large language models (MLLMs) to adapt to a stream of tasks without forgetting prior capabilities.

By Zhiyan Hou, Haiyun Guo, Haokai Ma, Yandu Sun, Yonghui Yang, Jinqiao Wang

llms fine-tuning multimodal benchmarks

arXiv Machine Learning

Aug 11

Control-Diverse Reinforcement Fine-Tuning: Decoupling the Shared Control Bottleneck of RL Post-Training

arXiv:2608. 08224v1 Announce Type: new Abstract: Reinforcement learning post-training unlocks complex reasoning in LLMs.

By Binwen Tan, Jingchao Wang, Dengzhe Hou, Lingyu Jiang, Zeyuan Wu, Yunhan Shen, Fangzhou Lin, Kazunori Yamada, Atsushi Koike

llms reinforcement-learning fine-tuning efficiency benchmarks safety

Related stories

PACT: Preserving Anchored Cores in Task-vectors for Model Merging

Training-free Task Classification for Multi-Task Model Merging

SUSD: Structured Unsupervised Skill Discovery through State Factorization

Capacity and Redundancy Trade-offs in Multi-Task Learning

PASs-MoE: Mitigating Misaligned Co-drift among Router and Experts via Pathway Activation Subspaces for Continual Learning

Control-Diverse Reinforcement Fine-Tuning: Decoupling the Shared Control Bottleneck of RL Post-Training