6 papers
oHC: Orthogonal Hyper-Connections on SO(4) via Quaternions
Haoqiang Guo, Xuyi Chen, Bo Ke +5
Hyper-Connections (HC) replace the single residual stream of a Transformer with parallel ones, mixing them at every layer with a learned residual matrix. Leaving t…
CodecCap: High-Fidelity Codec-Inspired Residual Modeling for Dense Video Captioning
Zihan Lin, Songhe Deng, Shuwei He +6
Existing video captioning methods struggle to balance visual fidelity and redundancy: holistic captions are compact but lose fine-grained evidence, whereas segment-wise captions im…
Eureka-Audio: Triggering Audio Intelligence in Compact Language Models
Dan Zhang, Yishu Lei, Jing Hu +10
We present Eureka-Audio, a compact yet high-performance audio language model that achieves competitive performance against models that are 4 to 18 times larger across a broad range…
CORD: Bridging the Audio-Text Reasoning Gap via Weighted On-policy Cross-modal Distillation
Jing Hu, Danxiang Zhu, Xianlong Luo +9
Large Audio Language Models (LALMs) have garnered significant research interest. Despite being built upon text-based large language models (LLMs), LALMs frequently exhibit a degrad…
MoE Adapter for Large Audio Language Models: Sparsity, Disentanglement, and Gradient-Conflict-Free
Yishu Lei, Shuwei He, Jing Hu +9
Extending the input modality of Large Language Models~(LLMs) to the audio domain is essential for achieving comprehensive multimodal perception. However, it is well-known that acou…
MatryoshkaThinking: Recursive Test-Time Scaling Enables Efficient Reasoning
Hongwei Chen, Yishu Lei, Dan Zhang +10
Test-time scaling has emerged as a promising paradigm in language modeling, wherein additional computational resources are allocated during inference to enhance model performance.…