SuperAPI AI Directory
Partner中文AI newsFavorites

All AI tools

35,738 results · Page 355 of 993

R1-Multimodal-Journey

AI developer platforms

R1-Multimodal-Journey (also known as MM-Eureka V0) is an open-source project exploring reinforcement learning (RL) for multimodal large models, aiming to apply R1-style reinforcement learning similar to DeepSeek-R1 to vision-language models (VLMs) and verify its effectiveness on more challenging problems such as geometry. The project is built on Open-R1-Multimodal, integrates open-source achievements such as vLLM, Open-R1, and trl, and adopts the technologies and base models of DeepSeek-R1 and Qwen2.5-VL. Its core improvements include: support for vLLM-accelerated training, which is 5-6 times faster than OpenR1-MM on 8 H100s; fixing some bugs in Open-R1-Multimodal (such as the get_per_token_logps function); and upgrading transformers to 4.49.0.dev0 to support Qwen2.5_VL. The experiment used 20,000 samples from geo170k and found that even a small 3B model under the instruct setting can exhibit an "aha moment" within the first 10 training steps. The project also found that VLMs struggle to show a length growth curve like LLMs, but performance still improves; compared with SFT, R1-style RL is based only on answer correctness rewards, yet exhibits higher data efficiency. The project's latest progress has been migrated to MM-Eureka, and more capabilities, models, and data are also open-sourced in that repository.

Read more

R1-Omni

Other AI tools

R1-Omni is the industry's first project to apply Reinforcement Learning with Verifiable Rewards (RLVR) to a full-modal large language model, focusing on the emotion recognition task, aiming to validate the potential of combining RLVR with full-modal models. The project is built on the open-source Omni model HumanOmni-0.5B, and has open-sourced the base model, the cold-start model EMER-SFT, the MAFW-DFEW-SFT model fine-tuned directly on the MAFW and DFEW training sets, and the final model R1-Omni. Research shows that compared with supervised fine-tuning (SFT), RLVR significantly improves performance on the emotion recognition task and enhances reasoning ability, understanding ability, and generalization ability, especially outstanding in out-of-distribution scenarios. The project has been reported by People's Daily and Bloomberg.

Read more

RadioNewsAI

AI audio

RadioNewsAI is an AI audio generation tool for scenarios such as radio stations and podcasts, capable of quickly turning ideas into audio content ready for broadcast. It can automatically generate news broadcasts, weather reports, local traffic updates, and radio and podcast advertisements, with support for selecting voices, building complete audio sequences, and adding background music. It is officially said to be trusted by radio stations worldwide, helping users produce high-quality broadcast content more efficiently. Pricing starts at $19 per month, billed by the duration of all AI-generated audio; each plan includes a certain number of minutes and optional additional usage-based billing. News, weather, traffic, and advertising production tools are included in all plans.

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

Railway

Other AI tools

Railway is a full-stack cloud platform for deploying web apps, servers, databases, and more, with autoscaling, monitoring, and security features. It can connect to a code repository and automatically complete configuration, and provides instant previews, private network connectivity, public endpoints, SSL, and load balancing. Railway also provides logs, metrics, traces, custom alerts, unlimited environments, automatic previews for every PR, and one-click rollbacks. The platform is aimed at software teams that need to simplify deployment and operations, helping users scale from a single instance to a global deployment.

Read more