@_akhaliq

–

18 September 2024 17h56

Hacker News of AI research papers built with o1-preview/mini in @Gradio
, added instructions on how to submit a paper

Fine-Tuning Image-Conditional Diffusion Models for Depth Estimation

By

–

18 September 2024 4h55

Fine-Tuning Image-Conditional Diffusion Models is Easier than You Think discuss: https://
huggingface.co/papers/2409.11
355
… Recent work showed that large diffusion models can be reused as highly precise monocular depth estimators by casting depth estimation as an image-conditional image

EzAudio: Efficient Diffusion Transformer for Text-to-Audio Generation

By

–

18 September 2024 4h47

EzAudio Enhancing Text-to-Audio Generation with Efficient Diffusion Transformer discuss: https://
huggingface.co/papers/2409.10
819
… demo: https://
huggingface.co/spaces/OpenSou
nd/EzAudio
… Latent diffusion models have shown promising results in text-to-audio (T2A) generation tasks, yet previous models have encountered

SplatFields: Neural Gaussian Splats for 3D and 4D Reconstruction

By

–

18 September 2024 4h24

SplatFields Neural Gaussian Splats for Sparse 3D and 4D Reconstruction discuss: https://
huggingface.co/papers/2409.11
211
… Digitizing 3D static scenes and 4D dynamic events from multi-view images has long been a challenge in computer vision and graphics. Recently, 3D Gaussian Splatting (3DGS)

Agile Continuous Jumping for Quadrupedal Robots in Discontinuous Terrains

By

–

18 September 2024 4h19

Agile Continuous Jumping in Discontinuous Terrains

discuss: https://t.co/2beMBjQUTQ

We focus on agile, continuous, and terrain-adaptive jumping of quadrupedal robots in discontinuous terrains such as stairs and stepping stones. Unlike single-step jumping, continuous jumping… pic.twitter.com/JN91iUktNh
— AK (@_akhaliq) 18 septembre 2024

Agile Continuous Jumping in Discontinuous Terrains discuss: https://
huggingface.co/papers/2409.10
923
… We focus on agile, continuous, and terrain-adaptive jumping of quadrupedal robots in discontinuous terrains such as stairs and stepping stones. Unlike single-step jumping, continuous jumping

Exploring Agency Limits in Agent-Based Modeling Systems

By

–

18 September 2024 4h13

On the limits of agency in agent-based models discuss: https://
huggingface.co/papers/2409.10
568
… Agent-based modeling (ABM) seeks to understand the behavior of complex systems by simulating a collection of agents that act and interact within an environment. Their practical utility requires

OSV: Single Step Generation for High-Quality Image to Video

By

–

18 September 2024 4h00

OSV One Step is Enough for High-Quality Image to Generation discuss: https://
huggingface.co/papers/2409.11
367
… diffusion models have shown great potential in generating high-quality videos, making them an increasingly popular focus. However, their inherent iterative nature leads to

Kolmogorov-Arnold Transformer: Revolutionary MLP Alternative for Deep Learning

By

–

18 September 2024 3h26

Kolmogorov-Arnold Transformer discuss: https://
huggingface.co/papers/2409.10
594
… Transformers stand as the cornerstone of mordern deep learning. Traditionally, these models rely on multi-layer perceptron (MLP) layers to mix the information between channels. In this paper, we introduce the