5 citations · 13 across the 16 of their papers we have counts for
16 papers
Parallel In-context Learning for Large Vision Language Models
Shin'ya Yamaguchi, Daiki Chijiwa, Tamao Sakao +1
Large vision-language models (LVLMs) employ multi-modal in-context learning (MM-ICL) to adapt to new tasks by leveraging demonstration examples. While increasing the number of demo…
The Strong Lottery Ticket Hypothesis for Multi-Head Attention Mechanisms
Hikari Otsuka, Daiki Chijiwa, Yasuyuki Okoshi +3
The strong lottery ticket hypothesis (SLTH) conjectures that high-performing subnetworks, called strong lottery tickets (SLTs), are hidden in randomly initialized neural networks.…
Lossless Vocabulary Reduction for Auto-Regressive Language Models
Daiki Chijiwa, Taku Hasegawa, Kyosuke Nishida +4
Tokenization -- the process of decomposing a given text into a sequence of subwords called tokens -- is one of the key components in the development of language models. Particularl…
Do We Really Need Permutations? Impact of Model Width on Linear Mode Connectivity
Akira Ito, Masanori Yamada, Daiki Chijiwa +1
Recently, Ainsworth et al. empirically demonstrated that, given two independently trained models, applying a parameter permutation that preserves the input-output behavior allows t…
Rationale-Enhanced Decoding for Multi-modal Chain-of-Thought
Shin'ya Yamaguchi, Kosuke Nishida, Daiki Chijiwa
Large vision-language models (LVLMs) have demonstrated remarkable capabilities by integrating pre-trained vision encoders with large language models (LLMs). Similar to single-modal…
Post-pre-training for Modality Alignment in Vision-Language Foundation Models
Shin'ya Yamaguchi, Dewei Feng, Sekitoshi Kanai +2
Contrastive language image pre-training (CLIP) is an essential component of building modern vision-language foundation models. While CLIP demonstrates remarkable zero-shot performa…
Portable Reward Tuning: Towards Reusable Fine-Tuning across Different Pretrained Models
Daiki Chijiwa, Taku Hasegawa, Kyosuke Nishida +2
While foundation models have been exploited for various expert tasks through fine-tuning, any foundation model will become outdated due to its old knowledge or limited capability.…
Zero-shot Concept Bottleneck Models
Shin'ya Yamaguchi, Kosuke Nishida, Daiki Chijiwa +1
Concept bottleneck models (CBMs) are inherently interpretable and intervenable neural network models, which explain their final label prediction by the intermediate prediction of h…
Adaptive Random Feature Regularization on Fine-tuning Deep Neural Networks
Shin'ya Yamaguchi, Sekitoshi Kanai, Kazuki Adachi +1
While fine-tuning is a de facto standard method for training deep neural networks, it still suffers from overfitting when using small target datasets. Previous methods improve fine…
Partially Frozen Random Networks Contain Compact Strong Lottery Tickets
Hikari Otsuka, Daiki Chijiwa, Ángel López García-Arias +6
Randomly initialized dense networks contain subnetworks that achieve high accuracy without weight learning--strong lottery tickets (SLTs). Recently, Gadhikar et al. (2023) demonstr…
Regularizing Neural Networks with Meta-Learning Generative Models
Shin'ya Yamaguchi, Daiki Chijiwa, Sekitoshi Kanai +2
This paper investigates methods for improving generative data augmentation for deep learning. Generative data augmentation leverages the synthetic samples produced by generative mo…
Toward Data Efficient Model Merging between Different Datasets without Performance Degradation
Masanori Yamada, Tomoya Yamashita, Shin'ya Yamaguchi +1
Model merging is attracting attention as a novel method for creating a new model by combining the weights of different trained models. While previous studies reported that model me…
Transferring Learning Trajectories of Neural Networks
Daiki Chijiwa
Training deep neural networks (DNNs) is computationally expensive, which is problematic especially when performing duplicated or similar training runs in model ensemble or fine-tun…
Meta-ticket: Finding optimal subnetworks for few-shot learning within randomly initialized neural networks
Daiki Chijiwa, Shin'ya Yamaguchi, Atsutoshi Kumagai +1
Few-shot learning for neural networks (NNs) is an important problem that aims to train NNs with a few data. The main challenge is how to avoid overfitting since over-parameterized…
Transfer Learning with Pre-trained Conditional Generative Models
Shin'ya Yamaguchi, Sekitoshi Kanai, Atsutoshi Kumagai +2
Transfer learning is crucial in training deep neural networks on new target tasks. Current transfer learning methods always assume at least one of (i) source and target task label…
Pruning Randomly Initialized Neural Networks with Iterative Randomization
Daiki Chijiwa, Shin'ya Yamaguchi, Yasutoshi Ida +2
Pruning the weights of randomly initialized neural networks plays an important role in the context of lottery ticket hypothesis. Ramanujan et al. (2020) empirically showed that onl…