7 papers
Summary of DCASE 2026 Task 5: Audio-Dependent Question Answering
Haolin He, Renhe Sun, Zheqi Dai +16
DCASE~2026 Task~5 introduces Audio-Dependent Question Answering (ADQA), which tests whether large audio-language models answer from the audio rather than from textual priors. An Au…
ROAD: Adaptive Data Mixing for Offline-to-Online Reinforcement Learning via Bi-Level Optimization
Letian Yang, Xu Liu, Yiqiang Lu +3
Offline-to-online reinforcement learning harnesses the stability of offline pretraining and the flexibility of online fine-tuning. A key challenge lies in the non-stationary distri…
OmniZip: Audio-Guided Dynamic Token Compression for Fast Omnimodal Large Language Models
Keda Tao, Kele Shao, Bohan Yu +3
Omnimodal large language models (OmniLLMs) have attracted increasing research attention of late towards unified audio-video understanding. However, the high computational cost of p…
ST-GDance++: A Scalable Spatial-Temporal Diffusion for Long-Duration Group Choreography
Jing Xu, Weiqiang Wang, Cunjian Chen +2
Group dance generation from music requires synchronizing multiple dancers while maintaining spatial coordination, making it highly relevant to applications such as film production,…
Measuring Audio's Impact on Correctness: Audio-Contribution-Aware Post-Training of Large Audio Language Models
Haolin He, Xingjian Du, Renhe Sun +16
Large Audio Language Models (LALMs) represent an important frontier in multimodal AI, addressing diverse audio tasks. Recently, post-training of LALMs has received increasing atten…
Active Perception Agent for Omnimodal Audio-Video Understanding
Keda Tao, Wenjie Du, Bohan Yu +3
Omnimodal large language models have made significant strides in unifying audio and visual modalities; however, they often face challenges in fine-grained cross-modal understanding…