SuperAPI AI Directory
Partner with us中文AI newsFavorites

AI developer platforms

3,641 results · Page 89 of 102

R1-Onevision

AI developer platforms

R1-Onevision is a multimodal reasoning large model designed to solve complex visual reasoning tasks. It was developed by a team at Zhejiang University and can seamlessly integrate visual and textual data, excelling in fields such as mathematics, science, deep image understanding, and logical reasoning. The project converts images into formal textual representations through a cross-modal reasoning pipeline, thereby enabling precise language-based reasoning. The model is fine-tuned based on Qwen2.5-VL, and the accompanying dataset, benchmark, SFT weights, RL weights, and demo have been released.

Read more

RAGEN

AI developer platforms

RAGEN is an open-source reinforcement learning framework for training reasoning LLM agents, based on the StarPO algorithm and supporting multi-turn trajectory-level reinforcement learning. It provides 10 built-in environments (such as Sokoban, FrozenLake, WebShop, DeepCoder, SearchQA, etc.) and a Gym-compatible interface, making it easy to add custom environments. The RAGEN-2 version further introduces SNR-Adaptive Filtering, a lightweight trajectory filtering method based on reward variance, as well as reasoning collapse diagnostics (detecting template collapse through conditional entropy and mutual information proxy metrics), helping to understand and fix hidden failure modes in agent reinforcement learning (such as Echo Trap and reasoning collapse). The framework supports two optimization methods, PPO and GRPO, and includes tools such as a diagnostics dashboard and training metrics guide.

Read more

RAGEN

AI developer platforms

RAGEN is a reinforcement learning framework for training reasoning LLM agents, supporting multi-turn reinforcement learning based on the StarPO algorithm. It provides trajectory-level and turn-level training, 10 built-in environments, and a Gym-compatible interface, making it easy to add custom environments. RAGEN-2 further introduces SNR adaptive filtering based on reward variance and reasoning collapse diagnostic metrics to mitigate issues such as template collapse and improve training stability.

Read more