Trending Research
DINO-X: A Unified Vision Model for Open-World Object Detection and Understanding
DINO-X employs the same Transformer-based encoder-decoder architecture as Grounding DINO 1. 5 to pursue an object-level representation for open-world object understanding.
3D Convex Splatting: Radiance Field Rendering with 3D Smooth Convexes
convexsplatting/convex-splatting
•
•
Our results highlight the potential of 3D Convex Splatting to become the new standard for high-quality scene reconstruction and novel view synthesis.
DROID-Splat: Combining end-to-end SLAM with 3D Gaussian Splatting
Recent progress in scene synthesis makes standalone SLAM systems purely based on optimizing hyperprimitives with a Rendering objective possible.
SwitchLight: Co-design of Physics-driven Architecture and Pre-training Framework for Human Portrait Relighting
lllyasviel/ic-light
•
•
CVPR 2024
We introduce a co-designed approach for human portrait relighting that combines a physics-guided architecture with a pre-training framework.
Cautious Optimizers: Improving Training with One Line of Code
In this work, we propose a \textbf{single-line modification in Pytorch} to any momentum-based optimizer, which we rename Cautious Optimizer, e. g. C-AdamW and C-Lion.
FlipSketch: Flipping Static Drawings to Text-Guided Sketch Animations
Sketch animations offer a powerful medium for visual storytelling, from simple flip-book doodles to professional studio productions.
MossFormer: Pushing the Performance Limit of Monaural Speech Separation using Gated Single-Head Transformer with Convolution-Augmented Joint Self-Attentions
modelscope/ClearerVoice-Studio
•
•
To effectively solve the indirect elemental interactions across chunks in the dual-path architecture, MossFormer employs a joint local and global self-attention architecture that simultaneously performs a full-computation self-attention on local chunks and a linearised low-cost self-attention over the full sequence.
Ranked #1 on
Speech Separation
on WSJ0-2mix-16k
(using extra training data)
MARS: Unleashing the Power of Variance Reduction for Training Large Models
AGI-Arena/MARS
•
•
Despite the development of numerous variance reduction algorithms in the past decade aimed at accelerating stochastic optimization in both convex and nonconvex settings, variance reduction has not found widespread success in training deep neural networks or large language models.
Unpacking DPO and PPO: Disentangling Best Practices for Learning from Preference Feedback
High-quality preference data leads to improvements of up to 8% in instruction following and truthfulness.
Streaming Deep Reinforcement Learning Finally Works
mohmdelsayed/streaming-drl
•
•
This paper introduces the stream-x algorithms, the first class of deep RL algorithms to overcome stream barrier for both prediction and control and match sample efficiency of batch RL.
