Trending Research
The AdEMAMix Optimizer: Better, Faster, Older
nanowell/AdEMAMix-Optimizer-Pytorch
•
•
This work questions the use of a single EMA to accumulate past gradients and empirically demonstrates how this choice can be sub-optimal: a single EMA cannot simultaneously give a high weight to the immediate past, and a non-negligible weight to older gradients.
Dynamic Gaussian Marbles for Novel View Synthesis of Casual Monocular Videos
coltonstearns/dynamic-gaussian-marbles
•
•
We evaluate on the Nvidia Dynamic Scenes dataset and the DyCheck iPhone dataset, and show that Gaussian Marbles significantly outperforms other Gaussian baselines in quality, and is on-par with non-Gaussian representations, all while maintaining the efficiency, compositionality, editability, and tracking benefits of Gaussians.
Text2SQL is Not Enough: Unifying AI and Databases with TAG
Such systems would allow users to leverage the powerful reasoning and knowledge capabilities of language models (LMs) alongside the scalable computational power of data management systems.
Radiative Gaussian Splatting for Efficient X-ray Novel View Synthesis
X-ray is widely applied for transmission imaging due to its stronger penetration than natural light.
Agent Workflow Memory
Despite the potential of language model-based agents to solve real-world tasks such as web navigation, current methods still struggle with long-horizon tasks with complex action trajectories.
Self-Harmonized Chain of Thought
Chain-of-Thought (CoT) prompting reveals that large language models are capable of performing complex reasoning via intermediate steps.
MAD-ICP: It Is All About Matching Data -- Robust and Informed LiDAR Odometry
Most of these systems implicitly rely on assumptions about the operating environment, the sensor used, and motion pattern.
LinFusion: 1 GPU, 1 Minute, 16K Image
We find that the distilled model, termed LinFusion, achieves performance on par with or superior to the original SD after only modest training, while significantly reducing time and memory complexity.
WavTokenizer: an Efficient Acoustic Discrete Codec Tokenizer for Audio Language Modeling
Despite the reduced number of tokens, WavTokenizer achieves state-of-the-art reconstruction quality with outstanding UTMOS scores and inherently contains richer semantic information.
Frequency-aware Feature Fusion for Dense Image Prediction
The offset generator refines large inconsistent features and thin boundaries by replacing inconsistent features with more consistent ones through resampling, while the AHPF generator enhances high-frequency detailed boundary information lost during downsampling.
