#Open source

How does Dyania Health use Synapsis AI to assist healthcare teams in improving patient care efficiency?

SparseRead: A reusable control layer for AI agents to efficiently sparse read external content

The SparseRead control layer reduces excessive reading of external content by AI agents through Read Intent Protocol, Adaptive Reader Backends, and Budgeted Read Gate, without modifying the agent model.

Google releases TPU Sync: an open-source KV cache transfer library for TPUs

Google has released the open-source C++ library TPU Sync, used to move KV cache and model weights on Cloud TPUs, treating TPU HBM, host DRAM, shared storage, and data center network as a unified memory hierarchy.

inclusionAI/Duo-1.2-causal-base released: A multimodal world model for full-duplex interaction

inclusionAI has released the Duo 1.2 causal-base model, a full-duplex multimodal world model for real-time audio-video interaction, featuring improved generation quality, and model weights can be downloaded from Hugging Face.

inclusionAI/Duo-1.0-distill released: A multimodal world model for full-duplex interaction

inclusionAI releases Duo-1.0-distill, a full-duplex multimodal world model for real-time audio-video interaction, including Realization weights with four-step distillation, which needs to be used in conjunction with the causal-base suite.

inclusionAI/Duo-1.0-causal-base released: A multimodal world model for full-duplex interaction

inclusionAI releases Duo 1.0 causal-base model, a full-duplex multimodal world model for real-time audio-video interaction, including implementation weights and backbones, intent models and adapters, audio-video encoders, speech recognizers, and forced aligners. The model weights are based on MiniMax H3 initialization and are open-sourced.

inclusionAI/Duo-1.0-distill-quant released: An FP8 quantized real-time audio-visual full-duplex multimodal world model with four-step distillation

inclusionAI releases the Duo 1.0 Realization weights for FP8-quantized four-step distillation, used for its causal base model, supporting full-duplex real-time audio-video interaction, and needs to be overlaid with the causal base model weights.

PhysLoop: Utilizing the physical perception capabilities of large language models to achieve self-improvement of video generation models

PhysLoop utilizes large language models to guide video generation, selection, and correction, achieving physically consistent self-improvement and controllable data construction. The framework drives recursive self-improvement (RSI) of video generation models with limited human intervention by identifying and correcting physical errors in generated videos, and releases a diverse dataset containing 100K videos along with generation tools.

Understanding the decision model in long-term intelligent agents: Actor, Judge, or Teacher?

Decision models, even as actors, can effectively teach reinforcement learning strategies by evaluating complete action trajectories, improving success rates on ALFWorld and WebShop.

Hugging Face Daily Papers: Hyper-Connections Architecture Research Proposes SimpleHC Design

Researchers conduct a systematic study on the Hyper-Connections architecture, proposing the SimpleHC design, which minimizes training overhead and improves stability while achieving performance comparable to mHC by removing residual mixing and using shared memory access. SimpleHC maintains performance when scaling model size from 15B to 30B MoE, with smoother gradient dynamics in standard training, and only increases training time by 2.4% over the base residual baseline at maximum test scale.

Edge0 open sources 145B and 120B edge-side models and inference frameworks.

Edge0 open-sourced the Edge0-145B and Edge0-120B two edge models, and also released a unified inference framework and deployment tools. Officially, the 145B model can run locally on compatible laptops, with peak memory of 29GB, decoding speed of 80+ tokens/s, pre-filling speed of 1100+ tokens/s, supporting context lengths of 128K–256K.

Duo: A Reciprocal World Model for Full-Duplex Interaction

Duo v1 introduces the Reciprocal World Model (RWM), which jointly models intentions and reality through autoregressive reasoning, synchronized attention, and dual inference distillation, achieving real-time full-duplex audio-video interaction. The model continuously perceives audio-video input while responding to users in real time, treating intelligence and physical reality as equal foundational components of the world, supporting interactions such as dialogue, sharing objects, and reshaping virtual scenes. The first batch of models has been open-sourced.

smolmaxxing enabling large language models to run on older devices

The smolmaxxing project enables large language models to run on old devices like Xiaomi TV boxes and iPad Air by customizing the kernel, optimizing memory usage, and streaming weights from flash storage. On Xiaomi TV boxes, the Qwen3.5-2B model processes 7.7 tokens per second, and the Ling-mini-2.0 model processes 5.1 tokens per second. Support for more devices is coming soon.

BirdDreams: Joint Perspective and BEV Video Generation for Reasonable, Reactive Driving World Models

BirdDreams jointly generates bird's-eye view (BEV) videos and bird's-eye view videos, making scene layout a part of predicting the future. By providing an overhead view of vehicle position and movement through BEV, it reduces occlusion, while the perspective video retains scene details. On PhysicalAI-AV and nuScenes, BirdDreams more faithfully follows the input trajectory of its own vehicle and generates more reasonable self-motion without HD map or vehicle state input.

GitHub Copilot 0.171.0-alpha.2 released

GitHub Copilot 0.171.0-alpha.2 has been released, the AI coding agent is used for tasks, projects, and automation work, supporting code review, collaboration, and cloud-based development environments.

GitHub Copilot rust-v0.171.0-alpha.3 released

GitHub Copilot rust-v0.171.0-alpha.3 released, this version is used for code review and collaboration.

Alibaba Xiami App returns in AI form after five years: Happy Xiami officially launched, members start at 30 yuan per month

Alibaba's AI music creation platform, HappyShrimp, has officially launched on iOS and Android platforms, with the App Store version at 0.2.14. The platform supports generating human-vocal songs and pure music based on natural language descriptions, possessing music world knowledge, and provides two modes: smart lyrics and pure music. Standard members can generate 150 songs per month for 30 yuan.

ZigZag: An open-source visual embroidery editor that supports AI intelligent agent collaboration creation

ZigZag is a visual embroidery editor written in Rust, supporting the MCP protocol for AI agents to collaborate on design, converting SVG to embroidery stitches, and exporting multiple formats such as PES, DST. It is compatible with Brother Skitch (PP1) and supports Bluetooth transmission, offering various embroidery types and planning functions like Tatami, Satin, Stitch, and is available for download on Mac and Windows platforms.

inclusionAI/SingVL_S1_4B_GGUF releases the SingVL-4B GGUF multimodal decision model

SingVL-4B GGUF is the GGUF version of the 4B parameter multimodal decision-making model Sing VL S1 based on Qwen3.5, which can answer named entity questions with text or JSON and up to four images, and uses a full forward pass scoring option, scoring 69.76 in the Text evaluation and 73.94 in the Vision evaluation. The model uses the llama.cpp adapter, with a default context size of 4096 tokens, supporting text and image input.

GitHub Copilot 0.171.0-alpha.1 released

GitHub Copilot has released version 0.171.0-alpha.1, offering code generation, review, and security detection features, supporting enterprise integration and support services.

Clarification on the misunderstanding of the Lakebase architecture's LTAP.

Lakebase architecture serves both Postgres and analytics with a single persistent data copy, without the need for CDC pipelines or a second database. This architecture stores data hierarchically in object storage and cache, not traditional replication. It supports both point-in-time and scan access paths, optimized respectively using Postgres heap pages and Parquet format, with no additional synchronization tasks.

SGLang-Neuron deployed on AWS Trainium for cutting-edge AI models

SGLang-Neuron made available via AWS Deep Learning Container, supporting SGLang inference and reinforcement learning deployment on AWS Trainium, using the same interface as SGLang, running on native PyTorch, supporting PD disaggregation and 10240 token context length.

Eclipse Aerospace uses Databricks to simplify flight data ingestion

Eclipse Aerospace partnered with Databricks to make nearly 20 years of proprietary flight data (totaling 3TB) more accessible for service centers and engineers via a custom data source using PySpark, without requiring additional infrastructure.

GitHub Copilot 0.170.0-alpha.4 has been released.

GitHub Copilot has released version 0.170.0-alpha.4, providing code review, security vulnerability detection, and key scanning features.