Trending Research
DeMo: Decoupled Momentum Optimization
bloc97/demo
•
•
Training large neural networks typically requires sharing gradients between accelerators through specialized high-speed interconnects.
Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving
Compared to the baseline method, Mooncake can achieve up to a 525% increase in throughput in certain simulated scenarios while adhering to SLOs.
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)
Auto-RAG: Autonomous Retrieval-Augmented Generation for Large Language Models
ictnlp/auto-rag
•
•
Iterative retrieval refers to the process in which the model continuously queries the retriever during generation to enhance the relevance of the retrieved knowledge, thereby improving the performance of Retrieval-Augmented Generation (RAG).
Identity-Preserving Text-to-Video Generation by Frequency Decomposition
We propose a hierarchical training strategy to leverage frequency information for identity preservation, transforming a vanilla pre-trained video generation model into an IPT2V model.
ShowUI: One Vision-Language-Action Model for GUI Visual Agent
showlab/showui
•
•
In this work, we develop a vision-language-action model in digital world, namely ShowUI, which features the following innovations: (i) UI-Guided Visual Token Selection to reduce computational costs by formulating screenshots as an UI connected graph, adaptively identifying their redundant relationship and serve as the criteria for token selection during self-attention blocks; (ii) Interleaved Vision-Language-Action Streaming that flexibly unifies diverse needs within GUI tasks, enabling effective management of visual-action history in navigation or pairing multi-turn query-action sequences per screenshot to enhance training efficiency; (iii) Small-scale High-quality GUI Instruction-following Datasets by careful data curation and employing a resampling strategy to address significant data type imbalances.
EchoMimicV2: Towards Striking, Simplified, and Semi-Body Human Animation
Recent work on human animation usually involves audio, pose, or movement maps conditions, thereby achieves vivid animation quality.
Star Attention: Efficient LLM Inference over Long Sequences
Inference with Transformer-based Large Language Models (LLMs) on long sequences is both costly and slow due to the quadratic complexity of the self-attention mechanism.
OminiControl: Minimal and Universal Control for Diffusion Transformer
In this paper, we introduce OminiControl, a highly versatile and parameter-efficient framework that integrates image conditions into pre-trained Diffusion Transformer (DiT) models.
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.
