Researchers at the Tokyo-based startup Sakana AI have developed a new technique that enables language models to use memory more efficiently, helping enterprises cut the costs of building applications on top of large language models (LLMs) and other ...

New research suggests that AI memory systems can degrade model performance and encourage sycophantic tendencies.

You can now download Gemma 4 models with quantization-aware training to reduce the amount of mobile memory required to 1GB.

What if your AI could remember every meaningful detail of a conversation—just like a trusted friend or a skilled professional? In 2025, this isn’t a futuristic dream; it’s the reality of conversational memory in AI systems. At the forefront of this ...

Researchers build fleeting memory transformers with human-like memory decay, proving memory limits help AI learn grammar efficiently.

Microsoft takes a defense-in-depth approach to protect AI memory spanning every layer of the stack: storage, retrieval, model interaction, and user control. AI systems use memory to retain and recall information across interactions. This information is then used to shape future behavior. This enables:

Open-source OCR from Baidu eliminates the GPU memory wall that limits long-document parsing. Unlimited OCR uses a constant KV cache to process entire books on a single GPU in one forward pass, scoring approximately 93 on OmniDocBench and 35 percent faster than DeepSeek OCR at long output lengths.

As humans and machine learning systems often face similar computational challenges 1, there has been synergy between machine learning and cognitive science research, leveraging machine learning advancements to better model human cognition 2,3 and cognitive ...

In the fast-paced world of artificial intelligence, memory is crucial to how AI models interact with users. Imagine talking to a friend who forgets the middle of your conversation—it would be frustrating. This is similar to what happens when AI models ...