Researchers from Shanghai Jiao Tong University and Shanghai AI Lab unveiled Warp-as-History, a method that guides AI video camera paths without heavy control modules. By disguising camera warps as visual history and tuning on just one video, it enables precise camera control across unseen scenes while naturally generating missing angles.
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.
Researchers from Shanghai Jiao Tong University, CAS, and DUT just introduced EyeVLA, a biomimetic robotic eyeball for embodied AI. Unlike fixed cameras, it physically rotates and zooms in based on user instructions, turning movements into action tokens inside a vision-language model. This gives robots clear, fine-grained visual details across wide spaces without relying on expensive sensors.
Researchers just introduced MemOS, a dedicated memory operating system that treats AI memory like a schedulable computational resource. In testing, it boosted temporal reasoning performance by 159% over OpenAI's memory system and slashed first-token latency by up to 94%. Why it matters: It introduces portable "MemCubes" to finally end memory silos across tools.
