Summary of Dm-codec: Distilling Multimodal Representations For Speech Tokenization, by Md Mubtasim Ahasan et al.
DM-Codec: Distilling Multimodal Representations for Speech Tokenizationby Md Mubtasim Ahasan, Md Fahim, Tasnim Mohiuddin, A…
DM-Codec: Distilling Multimodal Representations for Speech Tokenizationby Md Mubtasim Ahasan, Md Fahim, Tasnim Mohiuddin, A…
Conformity in Large Language Modelsby Xiaochen Zhu, Caiqi Zhang, Tom Stafford, Nigel Collier, Andreas VlachosFirst…
Efficient Diffusion as Low Light Enhancerby Guanzhou Lan, Qianli Ma, Yuqi Yang, Zhigang Wang, Dong…
Dual-Model Distillation for Efficient Action Classification with Hybrid Edge-Cloud Solutionby Timothy Wei, Hsien Xin Peng,…
LOBG:Less Overfitting for Better Generalization in Vision-Language Modelby Chenhao Ding, Xinyuan Gao, Songlin Dong, Yuhang…
ControLRM: Fast and Controllable 3D Generation via Large Reconstruction Modelby Hongbin Xu, Weitao Chen, Zhipeng…
T2V-Turbo-v2: Enhancing Video Generation Model Post-Training through Data, Reward, and Conditional Guidance Designby Jiachen Li,…
Accelerating Diffusion Models with One-to-Many Knowledge Distillationby Linfeng Zhang, Kaisheng MaFirst submitted to arxiv on:…
SyllableLM: Learning Coarse Semantic Units for Speech Language Modelsby Alan Baade, Puyuan Peng, David HarwathFirst…
Learning from Committee: Reasoning Distillation from a Mixture of Teachers with Peer-Reviewby Zhuochun Li, Yuelyu…