paper-with-me

Papers

H-OPD: Confidence Aware Heterogeneous Multi-Teacher Multimodal On-policy Distillation

2026-07-01 · Qixiang Yin, Huanjin Yao, Yuchen Cai, Jianghao Chen, Ziyi Wang, Min Yang, Fei Su, Zhicheng Zhao arxiv

On-policy distillation (OPD) has recently emerged as an effective post-training paradigm by providing supervision on student-generated trajectories. However, existing OPD methods for multimodal reasoning usually rely on a static teacher routing, assigning each sample to a single teacher based on modality or task type. This ignores that visual grounding and abstract reasoning may dominate different decoding steps, making a single teacher insufficient for the full trajectory. To this end, H-OPD is proposed as a confidence-aware heterogeneous multi-teacher OPD framework for multimodal reasoning. By verifying the complementarity of heterogeneous teachers in the same reasoning process, H-OPD replaces task or sample level teacher routing with token-level teacher arbitration along the shared student trajectory. H-OPD employs vision-to-language description transfer to enable text-only teachers to access key visual semantics, and uses a confidence-aware arbitration mechanism to dynamically combine vision-language teacher and text-only teachers at each token. Extensive evaluations over 11 widely-used reasoning benchmarks showcase the superior performance of our method.

📄 PDF Abstract BibTeX arXiv:2607.02592

Code (0)

등록된 구현이 없습니다.

Tasks

Multimodal ReasoningVisual Grounding

Similar Papers 제목 키워드 기반

Teaching Sarcasm: Few-Shot Multimodal Sarcasm Detection via Distillation to a Parameter-Efficient Student

2025-10-29 · Soumyadeep Jana, Sanasam Ranbir Singh arxiv

Multimodal sarcasm detection is challenging, especially in low-resource settings where subtle image-text contradictions are hard to learn due to scarce annotated data, which hinders the model's performance. Parameter-eff…

parameter-efficient fine-tuningSarcasm Detection

CPFD: Confidence-aware Privileged Feature Distillation for Short Video Classification

2024-10-03 · Jinghao Shi, Xiang Shen, Kaili Zhao, Xuedong Wang 외

Dense features, customized for different business scenarios, are essential in short video classification. However, their complexity, specific adaptation requirements, and high computational costs make them resource-inten…

Video Classification

MURAL: Multimodal Uncertainty-aware Recommendation via Adaptive edge Learning

2026-09-04 · Ahmad Mousavi, Majid Alikhani, Yeon-Chang Lee, Roberto Corizzo 외 arxiv

Multimodal Graph Neural Networks have become standard for recommendation by augmenting sparse interaction data with content features. Yet current architectures face two bottlenecks: structural rigidity, from a reliance o…

Multimodal Recommendation

A Confidence-Aware Multimodal Fusion Framework for Industrial Human-Robot Collaboration

2026-09-09 · Xinyu Liu, Qiqi Dong, Boya Jia, Yi Zhang 외 arxiv

A confidence-aware multimodal fusion framework (CAMF) is proposed to realize reliable human intention prediction for industrial human-robot collaboration. This framework fuses four heterogeneous modalities including obje…

Uncertainty-Aware Dual-Student Knowledge Distillation for Efficient Image Classification

2025-11-24 · Aakash Gore, Anoushka Dey, Aryan Mishra arxiv

Knowledge distillation has emerged as a powerful technique for model compression, enabling the transfer of knowledge from large teacher networks to compact student models. However, traditional knowledge distillation meth…

Knowledge DistillationImage ClassificationModel Compression