Auto Added by WPeMatico
Can a fully sovereign open reasoning model match state of the art systems when every part of its training pipeline is transparent. Researchers from Mohamed bin Zayed University of Artificial Intelligence (MBZUAI) release K2 Think V2, a fully sovereign reasoning model designed to test how far open and fully documented pipelines can push long horizon […]
Data science agents should inspect datasets, design workflows, run code, and return verifiable answers, not just autocomplete Pandas code. DSGym, introduced by researchers from Stanford University, Together AI, Duke University, and Harvard University, is a framework that evaluates and trains such agents across more than 1,000 data science challenges with expert curated ground truth and
StepFun has introduced Step-DeepResearch, a 32B parameter end to end deep research agent that aims to turn web search into actual research workflows with long horizon reasoning, tool use and structured reporting. The model is built on Qwen2.5 32B-Base and is trained to act as a single agent that plans, explores sources, verifies evidence and
Chroma 1.0 is a real time speech to speech dialogue model that takes audio as input and returns audio as output while preserving the speaker identity across multi turn conversations. It is presented as the first open source end to end spoken dialogue system that combines low latency interaction with high fidelity personalized voice cloning
Salesforce AI research team present FOFPred, a language driven future optical flow prediction framework that connects large vision language models with diffusion transformers for dense motion forecasting in control and video generation settings. FOFPred takes one or more images and a natural language instruction such as ‘moving the bottle from right to left’ and predicts
Microsoft Research has released OptiMind, an AI based system that converts natural language descriptions of complex decision problems into mathematical formulations that optimization solvers can execute. It targets a long standing bottleneck in operations research, where translating business intent into mixed integer linear programs usually needs expert modelers and days of work. What OptiMind Is
Google AI has released TranslateGemma, a suite of open machine translation models built on Gemma 3 and targeted at 55 languages. The family comes in 4B, 12B and 27B parameter sizes. It is designed to run across devices from mobile and edge hardware to laptops and a single H100 GPU or TPU instance in the
As context lengths move into tens and hundreds of thousands of tokens, the key value cache in transformer decoders becomes a primary deployment bottleneck. The cache stores keys and values for every layer and head with shape (2, L, H, T, D). For a vanilla transformer such as Llama1-65B, the cache reaches about 335 GB
Transformers use attention and Mixture-of-Experts to scale computation, but they still lack a native way to perform knowledge lookup. They re-compute the same local patterns again and again, which wastes depth and FLOPs. DeepSeek’s new Engram module targets exactly this gap by adding a conditional memory axis that works alongside MoE rather than replacing it.
DeepSeek AI Researchers Introduce Engram: A Conditional Memory Axis For Sparse LLMs Read More »
How do you design an LLM agent that decides for itself what to store in long term memory, what to keep in short term context and what to discard, without hand tuned heuristics or extra controllers? Can a single policy learn to manage both memory types through the same action space as text generation? Researchers
How This Agentic Memory Research Unifies Long Term and Short Term Memory for LLM Agents Read More »
