A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
Hieu Tran, Zonghai Yao, Junda Wang, et al.
RARE enhances LLM reasoning accuracy and factual integrity by integrating retrieval-augmented actions into Monte Carlo Tree Search, enabling open-source models to rival GPT-4.
Unknown
This paper presents methods, metrics, and comparisons for uncertainty quantification in scientific machine learning, along with an open-source Python library.
Unknown
OpenMoE is an early effort to train and release fully open Mixture-of-Experts (MoE) based large language models to help the open-source community understand MoE LLMs.
Andrey Shutkin, Denis Parkhomenko, Ivan Kirillov, et al.
KVAE introduces a family of tokenizers for audio, image, and video that match or surpass frontier open-source tokenizers in reconstruction and generation quality.
Unknown
This paper presents Open-Sora Plan, an open-source large video generation model, with careful design and practical experience to inspire future video generation research.
Unknown
A systematic review of controllable video generation, covering methods, open-source models, and future directions.
Unknown
Scalecua scales open-source computer use agents by introducing cross-platform data collection and training, releasing data, models, and code to advance research.
Qiying Yu, Zheng Zhang, Ruofei Zhu, et al.
DAPO is an open-source large-scale LLM reinforcement learning system with a novel algorithm achieving 50 points on AIME 2024 using Qwen2.5-32B, releasing training code and data.
Unknown
OpenICL is an open-source framework that provides a modular and flexible interface for in-context learning research and practice.
Unknown
This paper evaluates closed- and open-source VLMs as planners, showing that spatially grounded long-horizon planning remains a major unsolved challenge.
Yihao Chen, Shi Chang, Khaled Chawa, et al.
MindForge automates creation of source-free software engineering training environments from open-source programs, enabling small models to match frontier performance on whole-life-cycle tasks.
Unknown
OpenThoughts creates open-source datasets for training reasoning models, leading to the OpenThinker models.