Deep Learning
Kangaroo: Lossless Self-Speculative Decoding for Accelerating LLMs via Double Early Exiting Fangcheng Liu Yehui Tang Zhenhua Liu Y unsheng Ni Duyu Tang Kai Han, Yunhe Wang
To bridge the representation gap between the sub-network and the full model, we train a lightweight and efficient adapter module on top of the sub-network.
A Versatile Diffusion Transformer with Mixture of Noise Levels for Audiovisual Generation
Instead of the standard fixed diffusion timestep, we propose applying variable diffusion timesteps across the temporal dimension and across modalities of the inputs.
AsEP: Benchmarking Deep Learning Methods for Antibody-specific Epitope Prediction Chu'nan Liu Structural Molecular Biology University College London United Kindom Lilian Denzler
Our empirical findings suggest that epitope prediction benefits from combining sequential features provided by language models with geometrical information from graph representations.
Evaluating Neural Theorem-Provers on the Putnam Mathematical Competition
Automating mathematical reasoning is a longstanding goal in artificial intelligence (Newell et al., 1957). A prominent line of work on the problem (Li et al., 2024) uses neural models to direct
