activity
20242026
most citedConcrete Subspace Learning based Interference Elimination for Multi-task Model Fusion

1 citations · 1 across the 1 of their papers we have counts for

collaborators

10 papers

cs.LG20261 cited

Concrete Subspace Learning based Interference Elimination for Multi-task Model Fusion

Anke Tang, Xianglin Luo, Li Shen +5

Merging models fine-tuned from a common, extensively pre-trained large model but specialized for different tasks has been demonstrated as a cheap and scalable strategy to construct…

cs.LG2026

A Unified Generalization Framework for Model Merging: Trade-offs, Non-Linearity, and Scaling Laws

Qinglun Li, Anke Tang, Miao Zhang +3

Model merging efficiently aggregates capabilities from multiple fine-tuned models into a single one, operating purely in parameter space without original data or expensive re-compu…

cs.CL2026

Mix Data or Merge Models? Balancing the Helpfulness, Honesty, and Harmlessness of Large Language Model via Model Merging

Jinluan Yang, Dingnan Jin, Anke Tang +10

Achieving balanced alignment of large language models (LLMs) in terms of Helpfulness, Honesty, and Harmlessness (3H optimization) constitutes a cornerstone of responsible AI. Exist…

cs.LG2025

FusionBench: A Unified Library and Comprehensive Benchmark for Deep Model Fusion

Anke Tang, Li Shen, Yong Luo +5

Deep model fusion is an emerging technique that unifies the predictions or parameters of several deep neural networks into a single better-performing model in a cost-effective and…

physics.med-ph2025

Unsupervised deep learning model for fast energy layer pre-selection of delivery-efficient proton arc therapy plan optimization of nasopharyngeal carcinoma

Bohan Yang, Gang Liu, Yang Zhong +7

Proton arc therapy (PAT) is an emerging and promising modality in radiotherapy, offering improved dose distribution and treatment robustness over intensity-modulated proton therapy…

cs.LG2025

Modeling Multi-Task Model Merging as Adaptive Projective Gradient Descent

Yongxian Wei, Anke Tang, Li Shen +3

Merging multiple expert models offers a promising approach for performing multi-task learning without accessing their original data. Existing methods attempt to alleviate task conf…