124 stories tagged Models · page 4 of 6
Allen Institute for AI released OlmoEarth v1.1, a suite of AI models designed to analyze satellite images. These models help track environmental changes, like deforestation and urban growth, more efficiently than before.
Hugging Face has launched the Ettin Reranker Family, a new set of open-source tools to improve search result accuracy. These models help prioritize the most relevant information in search queries, making it easier to find what you need.
NVIDIA has fine-tuned its Cosmos Predict 2.5 model to generate realistic robot videos. This advancement could revolutionize robot training and simulation.
Scientists discovered that AI models trained for reasoning don't just think longer—they actually move differently in their internal processes. This changes how we understand and improve AI problem-solving. The study found that longer chains of thought don't necessarily mean better reasoning, but rather a different internal path. This could lead to more efficient and effective AI models in the future.
Researchers developed PROMETHEUS, an AI system that organizes causal claims from text into navigable maps. This could help scientists and policymakers make better decisions by understanding complex relationships in data.
Researchers introduced a new framework called CHAL for AI debates. It focuses on areas where truth is uncertain, helping AI models refine their reasoning through structured discussions. This could make AI more useful in real-world, ambiguous situations.
Researchers have developed a system called LatentRouter that can choose the best AI model for a specific image-based question before it even answers. This could make AI assistants much more efficient and accurate for visual tasks.
Researchers tested 33 advanced AI models on their ability to gauge their own knowledge across different subjects. They found that AI models are more confident in applied and professional knowledge than in other areas, which could affect how we use them in real-world applications.
A new AI model called ZAYA1-8B uses a clever design to perform as well as much larger models. It could make advanced AI tools more accessible and affordable for everyday users.
Researchers have created EMO, an AI model that can learn different skills separately and combine them as needed. This could make AI more flexible and efficient for everyday tasks.
A small, specialized AI model trained for legal work beat larger models at extracting key details from contracts. It did so at a fraction of the cost, showing smaller models can sometimes be better for specific tasks.
Researchers created XL-SafetyBench to test AI models on country-specific safety issues and cultural sensitivities. This tool helps ensure AI understands and respects local norms beyond general English benchmarks.
A new open-source AI model is designed to run locally and help detect cyber threats. It's small, specialized, and built for everyday users to protect their devices.
OpenAI has added new voice models to its API that can understand, translate, and transcribe speech in real time. This makes voice interactions more natural and intelligent for everyday users.
The new vLLM V1 model focuses on improving AI accuracy before applying fine-tuning. This approach could make AI models more reliable for everyday users.
OpenAI has launched GPT-5.5 Instant, a new default model for ChatGPT that reduces hallucinations in sensitive areas like law, medicine, and finance. The model maintains the speed of its predecessor while improving accuracy.
Apple is planning to allow users to choose which third-party AI models they want to use on their iPhones. This could change how you interact with AI on your device.
A new study introduces AgentFloor, a benchmark to test how well smaller AI models can handle routine tasks. The goal is to see which parts of AI workflows need big, advanced models and which can be done by smaller ones.
Meta has acquired Assured Robot Intelligence, a humanoid robotics startup, to enhance its AI models for robots. This move underscores Meta's growing interest in physical AI applications beyond virtual environments.
DeepInfra is now part of Hugging Face's Inference Providers, making it easier to deploy AI models. This collaboration simplifies running models for developers and researchers.
A 200-person Chinese team released DeepSeek V4, surpassing models from larger labs. The model achieves state-of-the-art performance on key benchmarks, challenging the dominance of well-funded Western AI labs.
IBM has released Granite 4.1, a suite of open-source large language models trained using advanced techniques like mixture-of-experts and fine-tuning. The models are optimized for both efficiency and performance, setting a new standard in open-source AI.
A new study explores source-modality monitoring in vision-language models, assessing their ability to track and communicate the origin of information. The research evaluates how models bind words to specific input components across 11 different models.
A study reveals that LLMs trained on Western data fail to detect health misinformation in non-Western contexts, such as cow urine remedies on Indian YouTube. This highlights a critical gap in AI's ability to handle culturally nuanced content.