Technology
Debiasing Conditional Stochastic Optimization Lie He
The sample-averaged gradient of the CSO objective is biased due to its nested structure, and therefore requires a high sample complexity for convergence. We introduce a general stochastic extrapolation technique that effectively reduces the bias.
VirtualScanning: Unsupervised Non-line-of-sight ImagingfromIrregularlyUndersampledTransients
Inatypical activeconfocal NLOS imaging system, as depicted in Figure 1, alaser source and adetector are both focused on the same point onarelay surface.
CQM: Curriculum Reinforcement Learning with a Quantized World Model
Recent curriculum Reinforcement Learning (RL) has shown notable progress in solving complex tasks by proposing sequences of surrogate tasks. However, the previous approaches often face challenges when they generate curriculum goals in a high-dimensional space.
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 Dรกniel 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.
Bridging Geometric States via Geometric Diffusion Bridge Shengjie Luo
In this work, we introduce the Geometric Diffusion Bridge (GDB), a novel generative modeling framework that accurately bridges initial and target geometric states.