Researchers from Tsinghua and UC Berkeley just open-sourced uni-robot-agent, a unified harness that lets open-weight models control robots in simulation and the real world. Running locally on Qwen3.8-Flash-Next, it scored 31.39 on RoboDojo, edging past GPT-6 Astra's baseline at roughly 1/20th the cost.
Researchers from Tsinghua University just open-sourced Falcon, a lightweight model that isolates target voices in noisy rooms by tracking mouth movements. With just 0.5M trainable parameters, it drastically cuts latency compared to prior baselines. The accompanying Falcon Studio app runs on a laptop and feeds the clean audio straight into Zoom or Tencent Meeting.
Ant Group and Tsinghua University just introduced Realtime-Venus, a multimodal agent system that talks, listens, and watches while executing complex tasks in the background. Powered by two 9B models and a delegation harness, it handles heavy reasoning without pausing the conversation, making it a natural fit for smart glasses and in-car assistants.
ModelBest and OpenBMB just open-sourced MiniCPM-V 4.6, a 1.3B multimodal model designed to run on-device with just 6GB of RAM. Despite its small size, it beats rivals like Qwen3.5-0.8B in multi-benchmark tests while slashing token consumption to a fraction of the cost. Why it matters: It shows tiny edge models can deliver serious multimodal intelligence on everyday consumer devices.
Tsinghua University researchers just open-sourced OpenMAIC, an AI platform that turns any topic or document into a full interactive classroom. Instead of watching static video lectures, users learn alongside AI teachers and classmates who speak, draw formulas on whiteboards, and engage in real-time debates. It basically shifts online learning into an active virtual classroom under a permissive MIT license.
ByteDance and Tsinghua just introduced DreamID-Omni, an AI model that turns reference portraits, text, and voice clips into talking videos. It eliminates lip-sync confusion in multi-person scenes and supports full video face-and-voice editing, with open-source code expected in March.
Tsinghua University's Xmax AI team just introduced X1, a real-time interactive video model that lets you interact with virtual characters via hand gestures. Using a phone camera, it enables millisecond-level latency and infinite-length generation. The team is currently accepting signups for a private beta.
Researchers from Shanghai Jiao Tong and Tsinghua University just unveiled LightGen, an all-optical chip designed for generative AI. In image generation and style transfer tasks, it clocks speeds and energy efficiency over 100 times better than Nvidia's A100 GPU by processing data entirely with light and metasurfaces. Why it matters: generative inference is becoming an unsustainable power drain, and photonic computing offers a radical way out—though LightGen still relies on bulky lab lasers before it can see real-world silicon.
Shengshu Technology and Tsinghua University just unveiled Vidu, a text-to-video AI capable of generating 16-second clips at 1080p resolution in one click. Built on their U-ViT architecture, it supports multi-camera transitions and simulates real-world lighting. While it doesn't quite match Sora's photorealism yet, its temporal consistency marks a serious step forward for Chinese video models.
