9 papers
Exploring Heterogeneous Model Merging Approach for Complex Knowledge Transfer
Jiahe Fan, Si Chen, Yinghao Hou +4
Specialized models encode task-oriented behavior, but transferring that behavior to a general language model usually requires training, distillation, or representation alignment. W…
Understanding Knowledge Transfer Mechanism in Heterogeneous MLLM Fusion: A Simple Linear Approach
Yinghao Hou, Jiahe Fan, Yuanhao Pu +2
Training-free fusion of heterogeneous multimodal large language models (MLLMs) provides a direct route for cross-scale capability transfer, yet improvements in aggregate performanc…
Training-Free Knowledge Transfer Across Model Scales through Activation-Guided Pruning
Jiahe Fan, Si Chen, Yinghao Hou +2
Heterogeneous model fusion seeks to combine models that differ in tasks, initializations, architectures, or scales. We study an underexplored cross-scale setting: improving a small…
Rethinking Heterogeneous LLM Merging: A Weighted Model Averaging Perspective
Jiahe Fan, Yinghao Hou, Si Chen +3
Can large language models with substantially different parameter spaces be merged by direct weighted averaging, without training or semantic alignment? Existing heterogeneous fusio…
Optimization-Free Topological Sort for Causal Discovery via the Schur Complement of Score Jacobians
Rui Wu, Hong Xie
Continuous causal discovery typically couples representation learning with structural optimization via non-convex acyclicity penalties, which subjects solvers to local optima and r…
Model Specific Task Similarity for Vision Language Model Selection via Layer Conductance
Wei Yang, Hong Xie, Tao Tan +3
While open sourced Vision-Language Models (VLMs) have proliferated, selecting the optimal pretrained model for a specific downstream task remains challenging. Exhaustive evaluation…
Demystifying Design Choices of Reinforcement Fine-tuning: A Batched Contextual Bandit Learning Perspective
Hong Xie, Xiao Hu, Tao Tan +5
The reinforcement fine-tuning area is undergoing an explosion papers largely on optimizing design choices. Though performance gains are often claimed, inconsistent conclusions also…
Rethinking Reinforcement fine-tuning of LLMs: A Multi-armed Bandit Learning Perspective
Xiao Hu, Hong Xie, Tao Tan +2
A large number of heuristics have been proposed to optimize the reinforcement fine-tuning of LLMs. However, inconsistent claims are made from time to time, making this area elusive…
Multiple-play Stochastic Bandits with Prioritized Arm Capacity Sharing
Hong Xie, Haoran Gu, Yanying Huang +2
This paper proposes a variant of multiple-play stochastic bandits tailored to resource allocation problems arising from LLM applications, edge intelligence, etc. The model is compo…