19 papers
FLOMSS: Generative Music Source Separation by Flow Matching
Shuyang Cui, Zhi Zhong, Keisuke Toyama +10
Music source separation (MSS) has been conventionally addressed by discriminative methods. Recently, flow matching has emerged as a strong generative paradigm for modeling complex…
MLLMCLIP: Feature-Level Distillation of MLLM for Robust Vision-Language Representations
Jongsuk Kim, Qiyu Wu, Zhuoyuan Mao +3
Pretrained vision-language models such as CLIP excel at zero-shot recognition but often fail at compositionality, particularly attribute-object and relational structures. Recent st…
Searching Videos as Trees: Self-Correcting Agents for Grounded Long Video QA
Ce Zhang, Ziyang Wang, Yulu Pan +6
Grounded long-video question answering (Grounded LVQA) requires answering a question about a long video while localizing the short evidence interval that supports the answer. Recen…
Embodied-R1.5: Evolving Physical Intelligence via Embodied Foundation Models
Yifu Yuan, Yaoting Huang, Xianze Yao +20
We introduce Embodied-R1.5, a unified Embodied Foundation Model (EFM) that integrates comprehensive embodied reasoning capabilities, spanning embodied cognition, task planning, cor…
Mixture of Probes: Learning from Privileged Modalities in Multimodal LLMs Through Probing
Dominick Reilly, Qiyu Wu, Hiromi Wakaki +2
Multimodal Large Language Models (MLLMs) are typically designed under the assumption that all modalities available during training will also be accessible at inference. However, ma…
DynaVieW: Schema-Guided World Modeling for Understanding Hierarchical Visual Dynamics
Silin Gao, Hao Zhao, Zeming Chen +8
Multimodal LLMs struggle to systematically model the temporal evolution of visual scenes in videos or multi-image sequences. Such inputs require models to predict or simulate multi…
Break-the-Beat! Controllable MIDI-to-Drum Audio Synthesis
Shuyang Cui, Zhi Zhong, Qiyu Wu +9
Current methods for creating drum loop audio in digital music production, such as using one-shot samples or resampling, often demand non-trivial efforts of creators. While recent g…
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…
MusTBench: Benchmarking and Advancing Temporal Grounding in Music LLMs
Daeyong Kwon, Qiyu Wu, Shinobu Kuriya +6
Recent Large Audio-Language Models (LALMs) have demonstrated promising abilities in understanding musical content. However, whether their responses are grounded in the correct temp…
LLM2Fx-Tools: Tool Calling For Music Post-Production
Seungheon Doh, Junghyun Koo, Marco A. Martínez-Ramírez +5
This paper introduces LLM2Fx-Tools, a multimodal tool-calling framework that generates executable sequences of audio effects (Fx-chain) for music post-production. LLM2Fx-Tools uses…
Mining the Gold: Student-AI Chat Logs as Rich Sources for Automated Knowledge Gap Detection
Quanzhi Fu, Qiyu Wu, Dan Williams
With the significant increase in enrollment in computing-related programs over the past 20 years, lecture sizes have grown correspondingly. In large lectures, instructors face chal…
Remedy-R: Generative Reasoning for Machine Translation Evaluation without Error Annotations
Shaomu Tan, Ryosuke Mitani, Ritvik Choudhary +3
Over the years, automatic MT metrics have hillclimbed benchmarks and presented strong and sometimes human-level agreement with human ratings. Yet they remain black-box, offering li…
MCA: Modality Composition Awareness for Robust Composed Multimodal Retrieval
Qiyu Wu, Shuyang Cui, Satoshi Hayakawa +3
Multimodal retrieval, which seeks to retrieve relevant content across modalities such as text or image, supports applications from AI search to contents production. Despite the suc…
VIRTUE: Visual-Interactive Text-Image Universal Embedder
Wei-Yao Wang, Kazuya Tateishi, Qiyu Wu +2
Multimodal representation learning models have demonstrated successful operation across complex tasks, and the integration of vision-language models (VLMs) has further enabled embe…
From Chaos to Order: The Atomic Reasoner Framework for Fine-grained Reasoning in Large Language Models
Jinyi Liu, Yan Zheng, Rong Cheng +8
Recent advances in large language models (LLMs) have shown remarkable progress, yet their capacity for logical ``slow-thinking'' reasoning persists as a critical research frontier.…
Cross-Modal Learning for Music-to-Music-Video Description Generation
Zhuoyuan Mao, Mengjie Zhao, Qiyu Wu +4
Music-to-music-video generation is a challenging task due to the intrinsic differences between the music and video modalities. The advent of powerful text-to-video diffusion models…
DeepResonance: Enhancing Multimodal Music Understanding via Music-centric Multi-way Instruction Tuning
Zhuoyuan Mao, Mengjie Zhao, Qiyu Wu +2
Recent advancements in music large language models (LLMs) have significantly improved music understanding tasks, which involve the model's ability to analyze and interpret various…
Beyond Simple Sum of Delayed Rewards: Non-Markovian Reward Modeling for Reinforcement Learning
Yuting Tang, Xin-Qiang Cai, Jing-Cheng Pang +3
Reinforcement Learning (RL) empowers agents to acquire various skills by learning from reward signals. Unfortunately, designing high-quality instance-level rewards often demands si…
TLMCM Network for Medical Image Hierarchical Multi-Label Classification
Meng Wu, Siyan Luo, Qiyu Wu +1
Medical Image Hierarchical Multi-Label Classification (MI-HMC) is of paramount importance in modern healthcare, presenting two significant challenges: data imbalance and \textit{hi…