Deep Learning
Amortized Bayesian Experimental Design for Decision-Making
For example, in personalized medical diagnostics, a model is built based on historical data to facilitate an optimal treatment for a new patient (Bica et al., 2021).
DiffTORI: Differentiable Trajectory Optimization for Deep Reinforcement and Imitation Learning Weikang Wan
This paper introduces DiffTORI, which utilizes Diff erentiable T rajectory O ptimization as the policy representation to generate actions for deep R einforcement and I mitation learning. Trajectory optimization is a powerful and widely used algorithm in control, parameterized by a cost and a dynamics function.
Adaptive Layer Sparsity for Large Language Models via Activation Correlation Assessment Wei Li
Large Language Models (LLMs) have revolutionized the field of natural language processing with their impressive capabilities.
Modeling Million-byte Sequences with Multiscale Transformers Lili Y u Dániel Simig Colin Flaherty Armen Aghajanyan Luke Zettlemoyer Mike Lewis Meta AI
Sequences of millions of bytes are ubiquitous; for example, music, image, or video files typically consist of multiple megabytes.
DeBaRA: Denoising-Based3DRoomArrangement Generation
Weargue that the most critical component of a scene synthesis system is to accurately establish thesizeandpositionofvarious objects within arestricted area.
T2I-CompBench: A Comprehensive Benchmark for Open-world Compositional Text-to-image Generation
We introduce a new approach, Generative mOdel finetun-ing with Reward-driven Sample selection (GORS), to boost the compositional text-to-image generation abilities of pretrained text-to-image models.
