Search Results
BigO(Bench) -- Can LLMs Generate Code with Controlled Time and Space Complexity?
We introduce BigO(Bench), a novel coding benchmark designed to evaluate the capabilities of generative language models in understanding and generating code with specified time and space complexities.
Space-time 2D Gaussian Splatting for Accurate Surface Reconstruction under Complex Dynamic Scenes
To tackle the dynamic contents and the occlusions in complex scenes, we present a space-time 2D Gaussian Splatting approach.
Recovering complex ecological dynamics from time series using state-space universal dynamic equations
Ecological systems often exhibit complex nonlinear dynamics like oscillations, chaos, and regime shifts.
Magnitude-squared coherence: A powerful tool for disentangling Doppler planet discoveries from stellar activity
High RV-H$\alpha$ coherence at the frequency of GJ 3998 b, and high RV-S index coherence at the frequency of GJ 3998 c, indicate that the planets may actually be stellar signals.
Earth and Planetary Astrophysics Instrumentation and Methods for Astrophysics Solar and Stellar Astrophysics
Mega: Moving Average Equipped Gated Attention
The design choices in the Transformer attention mechanism, including weak inductive bias and quadratic computational complexity, have limited its application for modeling long sequences.
Ranked #1 on
ListOps
on ListOps
Progressive Neural Architecture Search
We propose a new method for learning the structure of convolutional neural networks (CNNs) that is more efficient than recent state-of-the-art methods based on reinforcement learning and evolutionary algorithms.
Ranked #1 on
Image Classification
on ImageNet
(Operations per network pass metric)
Neighborhood Attention Transformer
We present Neighborhood Attention (NA), the first efficient and scalable sliding-window attention mechanism for vision.
Ranked #123 on
Semantic Segmentation
on ADE20K
Rethinking Attention with Performers
We introduce Performers, Transformer architectures which can estimate regular (softmax) full-rank-attention Transformers with provable accuracy, but using only linear (as opposed to quadratic) space and time complexity, without relying on any priors such as sparsity or low-rankness.
Ranked #9 on
D4RL
on D4RL
Chefs' Random Tables: Non-Trigonometric Random Features
We introduce chefs' random tables (CRTs), a new class of non-trigonometric random features (RFs) to approximate Gaussian and softmax kernels.
High-Resolution Image Synthesis with Latent Diffusion Models
By decomposing the image formation process into a sequential application of denoising autoencoders, diffusion models (DMs) achieve state-of-the-art synthesis results on image data and beyond.
Ranked #2 on
Layout-to-Image Generation
on LayoutBench
