paper-with-me

홈 › Papers

MoPD: Mixture-of-Prompts Distillation for Vision-Language Models

2024-12-26 · Yang Chen, Shuai Fu, Yu Zhang

Soft prompt learning methods are effective for adapting vision-language models (VLMs) to downstream tasks. Nevertheless, empirical evidence reveals a tendency of existing methods that they overfit seen classes and exhibit degraded performance on unseen classes. This limitation is due to the inherent bias in the training data towards the seen classes. To address this issue, we propose a novel soft prompt learning method, named Mixture-of-Prompts Distillation (MoPD), which can effectively transfer useful knowledge from hard prompts manually hand-crafted (a.k.a. teacher prompts) to the learnable soft prompt (a.k.a. student prompt), thereby enhancing the generalization ability of soft prompts on unseen classes. Moreover, the proposed MoPD method utilizes a gating network that learns to select hard prompts used for prompt distillation. Extensive experiments demonstrate that the proposed MoPD method outperforms state-of-the-art baselines especially on on unseen classes.

📄 PDF Abstract BibTeX arXiv:2412.19087

Code (0)

등록된 구현이 없습니다.

Tasks

Prompt Learning

Similar Papers 제목 키워드 기반

D^3-MOPD: Adaptive Dynamic Domain ScheDuling for Efficient Multi-Teacher Distillation

2026-08-25 · Zechen Sun, Zhiwei Zhang, Fei Zhao, Juntao Li 외 hf

Multi-teacher on-policy distillation (MOPD) distills several domain-expert teachers into a single student by minimizing per-domain reverse-KL divergence on the student's own rollouts. Existing approaches typically fix th…

Counteraction-Aware Multi-Teacher On-Policy Distillation for General Capability Recovery with Domain Preservation

2026-05-26 · Tianlei Chen, Jiao Ou, Ziyuan Liu, Ruiming Tang 외 arxiv

Domain specialization can improve LLM behavior in vertical domains, but often weakens the general capabilities inherited from the original model. Recent Multi-Teacher On-Policy Distillation (MOPD) pipelines recover model…

Multi-Rollout On-Policy Distillation via Peer Successes and Failures

2026-05-12 · Weichen Yu, Xiaomin Li, Yizhou Zhao, Xiaoze Liu 외 arxiv

Large language models are often post-trained with sparse verifier rewards, which indicate whether a sampled trajectory succeeds but provide limited guidance about where reasoning succeeds or fails. On-policy distillation…

Mathematical ReasoningQuestion Answering

Nemotron 3 Ultra: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning

2026-06-12 · NVIDIA, :, Aaron Blakeman, Aaron Thomas 외 arxiv

We introduce Nemotron 3 Ultra, a 550 billion total and 55 billion active parameter Mixture-of-Experts Hybrid Mamba-Attention language model. We pre-trained Nemotron 3 Ultra on 20 trillion text tokens, then extended the c…

Reinforcement Learning

MOPD: Multi-Teacher On-Policy Distillation for Capability Integration in LLM Post-Training

2026-06-29 · Wenhan Ma, Jianyu Wei, Liang Zhao, Hailin Zhang 외 hf

Modern large language models (LLMs) rely on reinforcement learning during post-training to push specific capabilities, yet integrating multiple capabilities into one model remains hard. Existing methods, such as Off-Poli…

Reinforcement Learning