Trending Research
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)
Gaze-LLE: Gaze Target Estimation via Large-Scale Learned Encoders
fkryan/gazelle
•
•
We address the problem of gaze target estimation, which aims to predict where a person is looking in a scene.
Segment Any Text: A Universal Approach for Robust, Efficient and Adaptable Sentence Segmentation
facebookresearch/large_concept_model
•
•
We introduce a new model - Segment any Text (SaT) - to solve this problem.
StableAnimator: High-Quality Identity-Preserving Human Image Animation
Francis-Rings/StableAnimator
•
•
During inference, we propose a novel Hamilton-Jacobi-Bellman (HJB) equation-based optimization to further enhance the face quality.
SynCamMaster: Synchronizing Multi-Camera Video Generation from Diverse Viewpoints
Recent advancements in video diffusion models have shown exceptional abilities in simulating real-world dynamics and maintaining 3D consistency.
Learning Flow Fields in Attention for Controllable Person Image Generation
franciszzj/leffa
•
•
Additionally, we show that our loss is model-agnostic and can be used to improve the performance of other diffusion models.
Neural Localizer Fields for Continuous 3D Human Pose and Shape Estimation
isarandi/nlf
•
•
With the explosive growth of available training data, single-image 3D human modeling is ahead of a transition to a data-centric paradigm.
Video Seal: Open and Efficient Video Watermarking
facebookresearch/videoseal
•
•
To reduce these gaps, this paper introduces Video Seal, a comprehensive framework for neural video watermarking and a competitive open-sourced model.
HunyuanVideo: A Systematic Framework For Large Video Generative Models
In this report, we introduce HunyuanVideo, an innovative open-source video foundation model that demonstrates performance in video generation comparable to, or even surpassing, that of leading closed-source models.
LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods
Finally, we provide a detailed analysis of the limitations of LLM judges and discuss potential future directions.
