Trending Research
Unfolding the Headline: Iterative Self-Questioning for News Retrieval and Timeline Summarization
In the fast-changing realm of information, the capacity to construct coherent timelines from extensive event-related content has become increasingly significant and challenging.
REINFORCE++: A Simple and Efficient Approach for Aligning Large Language Models
Reinforcement Learning from Human Feedback (RLHF) has emerged as a critical approach for aligning large language models with human preferences, witnessing rapid algorithmic evolution through methods such as Proximal Policy Optimization (PPO), Direct Preference Optimization (DPO), REINFORCE Leave One-Out (RLOO), ReMax, and Group Relative Policy Optimization (GRPO).
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).
Infinity: Scaling Bitwise AutoRegressive Modeling for High-Resolution Image Synthesis
We present Infinity, a Bitwise Visual AutoRegressive Modeling capable of generating high-resolution, photorealistic images following language instruction.
PLAPT: Protein-Ligand Binding Affinity Prediction Using Pretrained Transformers
trrt-good/WELP-PLAPT
•
•
bioRxiv 2024
Understanding protein-ligand binding affinity is crucial for drug discovery, enabling the identification of promising drug candidates efficiently.
Ranked #1 on
Protein-Ligand Affinity Prediction
on PDBbind
SWE-Fixer: Training Open-Source LLMs for Effective and Efficient GitHub Issue Resolution
The retrieval module employs BM25 along with a lightweight LLM model to achieve coarse-to-fine file retrieval.
Reconstruction vs. Generation: Taming Optimization Dilemma in Latent Diffusion Models
The integrated system achieves state-of-the-art (SOTA) performance on ImageNet 256x256 generation with an FID score of 1. 35 while demonstrating remarkable training efficiency by reaching an FID score of 2. 11 in just 64 epochs--representing an over 21 times convergence speedup compared to the original DiT.
Ranked #1 on
Image Generation
on ImageNet 256x256
The Tabular Foundation Model TabPFN Outperforms Specialized Time Series Forecasting Models Based on Simple Features
Foundation models have become popular in forecasting due to their ability to make accurate predictions, even with minimal fine-tuning on specific datasets.
SHMT: Self-supervised Hierarchical Makeup Transfer via Latent Diffusion Models
To address these issues, we propose a novel Self-supervised Hierarchical Makeup Transfer (SHMT) method via latent diffusion models.
ROLO-SLAM: Rotation-Optimized LiDAR-Only SLAM in Uneven Terrain with Ground Vehicle
sdwyc/rolo
•
•
In this article, a LiDAR-based SLAM method is presented to improve the accuracy of pose estimations for ground vehicles in rough terrains, which is termed Rotation-Optimized LiDAR-Only (ROLO) SLAM.
