Datalab Releases lift: A 9B Open-Weights Vision Model That Extracts Structured JSON From PDFs Using Schemas
Source: MarkTechPost Datalab has released lift, a 9B open-weights vision model for structured extraction. You pass it a...
Prime Intellect Releases prime-rl 0.6.0 to Train Trillion-Parameter MoE Models on Agentic RL Workloads
Source: MarkTechPost Prime Intellect has released prime-rl version 0.6.0. The framework targets reinforcement learning on trillion-parameter Mixture-of-Experts (MoE)...
MoonMath AI Open-Sources a HIP Attention Kernel for AMD MI300X That Beats AITER v3 on Every Shape and Rounding Mode
Source: MarkTechPost MoonMath AI team has released a bf16 forward attention kernel for AMD’s MI300X GPU. It is...
Crawlee for Python: Build a Web Crawling Pipeline with Robots Handling, Link Graphs, and RAG Chunk Export
Source: MarkTechPost In this tutorial, we build a full Crawlee-for-Python workflow that covers environment setup, local website generation,...
Nous Research Updates Hermes Agent With a Blank Slate Mode That Pins Toolsets via platform_toolsets.cli and disabled_toolsets
Source: MarkTechPost Nous Research has added a Blank Slate setup mode to its open-source Hermes Agent. It inverts...
Yandex Open-Sources YaFF: A Zero-Copy Wire Format for Protobuf With Near-Struct Read Speed
Source: MarkTechPost TLDR YaFF is Yandex’s open-source zero-copy wire format for Protobuf — Apache 2.0, currently C++, v0.1.0....
NVIDIA AI Introduce SpatialClaw: A Training-Free Agent That Treats Code as the Action Interface for Spatial Reasoning
Source: MarkTechPost NVIDIA Research has released SpatialClaw, a training-free framework for spatial reasoning. It targets a persistent weakness...
VibeThinker-3B: A 3B Dense Reasoning Model Built on Qwen2.5-Coder-3B With the Spectrum-to-Signal Post-Training Pipeline
Source: MarkTechPost While recent breakthroughs in AI reasoning have largely been driven by massive scale, pouring in billions...
Liquid AI Introduces LFM2.5-Embedding-350M and LFM2.5-ColBERT-350M: Dense Bi-Encoder and Late-Interaction Models for Fast Multilingual Search Across 11 Languages
Source: MarkTechPost This week, Liquid AI released two new retrieval models. They are LFM2.5-ColBERT-350M and LFM2.5-Embedding-350M. Both hold...
Perplexity Launches Brain, a Self-Improving Memory System That Builds a Context Graph of an Agent’s Work and Learns Overnight
Source: MarkTechPost Most AI memory remembers the user. It stores your preferences, your tastes, and your role. Perplexity...