Trending Research
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.
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.
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)
Multi-Programming Language Sandbox for LLMs
We introduce MPLSandbox, an out-of-the-box multi-programming language sandbox designed to provide unified and comprehensive feedback from compiler and analysis tools for Large Language Models (LLMs).
LightRAG: Simple and Fast Retrieval-Augmented Generation
Retrieval-Augmented Generation (RAG) systems enhance large language models (LLMs) by integrating external knowledge sources, enabling more accurate and contextually relevant responses tailored to user needs.
LLaVA-CoT: Let Vision Language Models Reason Step-by-Step
Large language models have demonstrated substantial advancements in reasoning capabilities, particularly through inference-time scaling, as illustrated by models such as OpenAI's o1.
JoyVASA: Portrait and Animal Image Animation with Diffusion-Based Audio-Driven Facial Dynamics and Head Motion Generation
jdh-algo/JoyVASA
•
•
Specifically, in the first stage, we introduce a decoupled facial representation framework that separates dynamic facial expressions from static 3D facial representations.
Tora: Trajectory-oriented Diffusion Transformer for Video Generation
alibaba/Tora
•
•
The TE encodes arbitrary trajectories into hierarchical spacetime motion patches with a 3D video compression network.
Multimodal Autoregressive Pre-training of Large Vision Encoders
apple/ml-aim
•
•
We introduce a novel method for pre-training of large-scale vision encoders.
Ranked #1 on
Image Classification
on iNaturalist
MagicPIG: LSH Sampling for Efficient LLM Generation
MagicPIG stores the LSH hash tables and runs the attention computation on the CPU, which allows it to serve longer contexts and larger batch sizes with high approximation accuracy.
