1 citations · 2 across the 11 of their papers we have counts for
12 papers
FlexComp: One Model for Every Ratio in Context Compression
Kaiyan Zhao, Zhongtao Miao, Akiko Aizawa +1
Soft context compression condenses a context into a few memory tokens that a frozen LLM consumes in place of the raw text, but existing compressors fix the compression ratio at tra…
CNeo-Bench: Diagnosing Large Language Models on Chinese Neologisms
Kaiyan Zhao, Zhongtao Miao, Zheyong Xie +2
Chinese neologisms exploit diverse and unique linguistic mechanisms, such as phonetic substitution (e.g., 886 for ``bye-bye'') and visual character decomposition that are rare in o…
RegMix-D: Dynamic Data Mixing via Proxy Training Trajectories
Kaiyan Zhao, Zhongtao Miao, Akiko Aizawa +1
Data mixture selection is critical for Large Language Model pretraining. Existing methods such as RegMix select a single static mixture by fitting a regression model on small-scale…
GRC: Unifying Reasoning-Driven Generation, Retrieval and Compression
Zhongtao Miao, Qiyu Wu, Yoshimasa Tsuruoka
Text embedding and generative tasks are usually trained separately based on large language models (LLMs) nowadays. This causes a large amount of training cost and deployment effort…
NeoAMT: Neologism-Aware Agentic Machine Translation with Reinforcement Learning
Zhongtao Miao, Kaiyan Zhao, Masaaki Nagata +1
Neologism-aware machine translation aims to translate source sentences containing neologisms into target languages. This field remains underexplored compared with general machine t…
Improving Multimodal Contrastive Learning of Sentence Embeddings with Object-Phrase Alignment
Kaiyan Zhao, Zhongtao Miao, Yoshimasa Tsuruoka
Multimodal sentence embedding models typically leverage image-caption pairs in addition to textual data during training. However, such pairs often contain noise, including redundan…
Direct Quantized Training of Language Models with Stochastic Rounding
Kaiyan Zhao, Tsuguchika Tabaru, Kenichi Kobayashi +3
Although recent quantized Large Language Models (LLMs), such as BitNet, have paved the way for significant reduction in memory usage during deployment with binary or ternary weight…
M2M-Gen: A Multimodal Framework for Automated Background Music Generation in Japanese Manga Using Large Language Models
Megha Sharma, Muhammad Taimoor Haseeb, Gus Xia +1
This paper introduces M2M Gen, a multi modal framework for generating background music tailored to Japanese manga. The key challenges in this task are the lack of an available data…
Cross-Domain Policy Transfer by Representation Alignment via Multi-Domain Behavioral Cloning
Hayato Watahiki, Ryo Iwase, Ryosuke Unno +1
Transferring learned skills across diverse situations remains a fundamental challenge for autonomous agents, particularly when agents are not allowed to interact with an exact targ…
Improving Arithmetic Reasoning Ability of Large Language Models through Relation Tuples, Verification and Dynamic Feedback
Zhongtao Miao, Kaiyan Zhao, Yoshimasa Tsuruoka
Current representations used in reasoning steps of large language models can mostly be categorized into two main types: (1) natural language, which is difficult to verify; and (2)…
Word Alignment as Preference for Machine Translation
Qiyu Wu, Masaaki Nagata, Zhongtao Miao +1
The problem of hallucination and omission, a long-standing problem in machine translation (MT), is more pronounced when a large language model (LLM) is used in MT because an LLM it…
Enhancing Cross-lingual Sentence Embedding for Low-resource Languages with Word Alignment
Zhongtao Miao, Qiyu Wu, Kaiyan Zhao +2
The field of cross-lingual sentence embeddings has recently experienced significant advancements, but research concerning low-resource languages has lagged due to the scarcity of p…