ActIO-UI-7B-RLVR is a 7-billion-parameter visual language model released by Uniphore, specifically designed for computer interface automation tasks. It is based on Qwen2.5-VL-7B-Instruct and optimized through supervised fine-tuning and reinforcement learning with verifiable rewards. It performs excellently in tasks such as GUI navigation, element positioning, and interaction planning, and has achieved the leading level among open-source 7B models in the WARC-Bench benchmark test.

MultimodalTransformersEnglish

Nanbeige 4-3B-Thinking-2511 is the latest enhanced version of the Nanbeige series. Through advanced distillation technology and reinforcement learning optimization, it achieves powerful reasoning ability within a compact 3B parameter scale. This model has achieved state-of-the-art (SOTA) results among models with less than 32B parameters in benchmark tests such as Arena-Hard-V2 and BFCL-V4.

Natural Language ProcessingTransformersMultiple Languages

OpenMMReasoner is a fully transparent two-stage multimodal reasoning solution that covers supervised fine-tuning (SFT) and reinforcement learning (RL). By carefully constructing high-quality datasets, this solution surpasses powerful baseline models in multiple multimodal reasoning benchmark tests, laying a solid empirical foundation for future large-scale multimodal reasoning research.

MultimodalTransformers

Olmo 3 is a series of language models developed by the Allen Institute for AI, including two scales of 7B and 32B, with two variants: instructional and reflective. This model performs excellently in long-chain thinking and can effectively improve the performance of reasoning tasks such as mathematics and coding. It adopts a multi-stage training method, including supervised fine-tuning, direct preference optimization, and reinforcement learning with verifiable rewards.

Natural Language ProcessingTransformersEnglish

WavJEPA is an audio foundation model based on the waveform joint embedding prediction architecture. It uses advanced semantic representation learning to address the deficiencies in speech unit or token-level representation learning. It significantly outperforms the state-of-the-art time-domain audio foundation models in many downstream benchmark tasks while requiring significantly less computational resources.

Audio ProcessingTransformers

PokeeResearch - 7B is a 7 - billion - parameter in - depth research agent model developed by Pokee AI. It combines Reinforcement Learning from AI Feedback (RLAIF) and a powerful reasoning framework, enabling reliable, aligned, and scalable research - level reasoning in tool - enhanced large language models. It is suitable for complex multi - step research workflows.

Natural Language ProcessingTransformersEnglish

OLGA is an online reinforcement learning positioning agent built on Qwen3-VL-30B-A3B-Instruct, using a mixture-of-experts model with 3.3 billion active parameters. It is trained through a new data recipe that combines existing datasets, new data collection, automatic filtering, and online reinforcement learning, achieving advanced positioning performance among open-source models.

MultimodalTransformersEnglish

G²RPO is a novel reinforcement learning framework specifically designed for preference alignment in flow models, significantly improving the generation quality through a granular reward evaluation mechanism.

MultimodalDiffusers

Apriel-1.5-15b-Thinker is a multimodal reasoning model in the ServiceNow Apriel SLM series, with 15 billion parameters. It can compete with models 10 times its size in text and image reasoning tasks. This model achieves excellent reasoning ability through a mid-term training scheme and can reach SOTA performance without image SFT training or reinforcement learning.

MultimodalTransformers

QuestA is an innovative framework that enhances the reasoning ability of large language models through a question-enhanced approach. It integrates partial solutions during the reinforcement learning training process, significantly improving the model's performance on complex tasks such as mathematical reasoning, especially achieving optimal results on small-parameter models.

Natural Language ProcessingTransformers

MiMo Audio is an audio language model developed by Xiaomi, which demonstrates strong few-shot learning ability through large-scale pre-training. This model breaks through the limitations of traditional models that rely on fine-tuning for specific tasks and performs excellently in tasks such as speech intelligence and audio understanding, reaching an advanced level among open-source models.

Audio ProcessingSafetensors

MiMo Audio is an audio language model based on large-scale pre-training, achieving SOTA performance among open-source models in speech intelligence and audio understanding benchmark tests. This model demonstrates strong few-shot learning ability and can generalize to tasks not included in the training data, supporting various audio tasks such as speech conversion, style transfer, and speech editing.

Audio ProcessingSafetensors

DeepSeek-GRM-16B is a generative reward model based on Self-Principled Critique Tuning (SPCT), which can generate a transparent 'Principle → Critique → Score' evaluation process for query-responses and can be used in tasks such as reinforcement learning, evaluation, and data collection of large language models.

Natural Language ProcessingTransformersMultiple Languages

DINOv3 is a series of general visual foundation models developed by Meta AI. Without fine-tuning, it can outperform specialized state-of-the-art models in a wide range of visual tasks. This model uses self-supervised learning to generate high-quality dense features and performs excellently in various tasks such as image classification, segmentation, and depth estimation.

Computer VisionTransformersEnglish

DINOv3 is a series of general-purpose visual foundation models that can outperform specialized state-of-the-art models on a wide range of visual tasks without fine-tuning. The model uses self-supervised learning to generate high-quality dense features and performs excellently in various visual tasks, significantly surpassing previous self-supervised and weakly supervised foundation models.

Computer VisionTransformersEnglish

DINOv3 is a series of general visual foundation models that can outperform specialized state-of-the-art techniques in a wide range of visual tasks without fine-tuning. The model generates high-quality dense features through self-supervised learning and performs excellently in various visual tasks, significantly surpassing previous self-supervised and weakly supervised foundation models.

Computer VisionTransformersEnglish

GLM-4.1V-9B-Thinking is an open-source model developed based on the Vision-Language Model (VLM), aiming to explore the upper limit of the reasoning ability of vision-language models. By introducing the 'thinking paradigm' and reinforcement learning, it significantly improves the model's ability and reaches the leading level among VLMs with 10B parameters.

MultimodalTransformersMultiple Languages

GLM-4.1V-9B-Thinking is an open-source vision-language model based on the GLM-4-9B-0414 base model, specifically designed to explore the upper limit of the reasoning ability of vision-language models. It introduces the 'thinking paradigm' and uses reinforcement learning to significantly enhance its capabilities, performing excellently among VLMs with 10B parameters and rivaling or even surpassing models with larger parameters in multiple benchmark tasks.

MultimodalTransformersMultiple Languages

The Deep Ignorance Model Suite is a collection of 18 large language models with 6.9 billion parameters each. It aims to study methods of preventing models from learning unsafe technical capabilities (such as CBRN-related capabilities) by filtering pretrained data. This suite demonstrates that filtering data can effectively avoid the learning of bad knowledge while maintaining general performance and having anti-tampering capabilities.

Natural Language ProcessingTransformersEnglish

AReaL is an asynchronous reinforcement learning training system developed by Ant Group, designed specifically for large inference models, supporting fast training and cutting-edge performance.

Natural Language ProcessingTransformers