Trending Research
Implementation Matters in Deep Policy Gradients: A Case Study on PPO and TRPO
We study the roots of algorithmic progress in deep policy gradient algorithms through a case study on two popular algorithms: Proximal Policy Optimization (PPO) and Trust Region Policy Optimization (TRPO).
4D Panoptic Scene Graph Generation
jingkang50/psg4d
•
•
NeurIPS 2023
To facilitate research in this new area, we build a richly annotated PSG-4D dataset consisting of 3K RGB-D videos with a total of 1M frames, each of which is labeled with 4D panoptic segmentation masks as well as fine-grained, dynamic scene graphs.
TensorIR: An Abstraction for Automatic Tensorized Program Optimization
mlc-ai/web-llm
•
•
Finally, we build an end-to-end framework on top of our abstraction to automatically optimize deep learning models for given tensor computation primitives.
Lumina-T2X: Transforming Text into Any Modality, Resolution, and Duration via Flow-based Large Diffusion Transformers
Sora unveils the potential of scaling Diffusion Transformer for generating photorealistic images and videos at arbitrary resolutions, aspect ratios, and durations, yet it still lacks sufficient implementation details.
MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies
openbmb/minicpm
•
•
For data scaling, we introduce a Warmup-Stable-Decay (WSD) learning rate scheduler (LRS), conducive to continuous training and domain adaptation.
HMT: Hierarchical Memory Transformer for Long Context Language Processing
With an additional 0. 5% - 2% of parameters, HMT can easily plug in and augment future LLMs to handle long context effectively.
emotion2vec: Self-Supervised Pre-Training for Speech Emotion Representation
alibaba-damo-academy/FunASR
•
•
To the best of our knowledge, emotion2vec is the first universal representation model in various emotion-related tasks, filling a gap in the field.
Actions Speak Louder than Words: Trillion-Parameter Sequential Transducers for Generative Recommendations
facebookresearch/generative-recommenders
•
•
Large-scale recommendation systems are characterized by their reliance on high cardinality, heterogeneous features and the need to handle tens of billions of user actions on a daily basis.
Ranked #1 on
Recommendation Systems
on Amazon-Book
(HR@10 metric)
PuLID: Pure and Lightning ID Customization via Contrastive Alignment
We propose Pure and Lightning ID customization (PuLID), a novel tuning-free ID customization method for text-to-image generation.
Vidur: A Large-Scale Simulation Framework For LLM Inference
Vidur models the performance of LLM operators using a combination of experimental profiling and predictive modeling, and evaluates the end-to-end inference performance for different workloads by estimating several metrics of interest such as latency and throughput.
