Xiaohan Zhang

Current audio-visual generation models struggle to maintain coherence and alignment when scaling to minute-long content, a problem exposed by the new LongAV-Compass benchmark.

Over 96% of real-world MCP servers using OAuth for authentication suffer from dynamic client registration flaws, potentially leading to sensitive information leakage and account takeover.

Forget expensive real-world robotics data collection: ExpertGen uses RL to turn noisy, simulated behavior priors (even from LLMs!) into expert policies that transfer to real robots.

Forget retraining: a single, carefully chosen noise vector can boost your robot's pre-trained policy performance by up to 60% in the real world.

A compact 0.9B multimodal model, GLM-OCR, achieves state-of-the-art document understanding by predicting multiple tokens at once, boosting decoding throughput without blowing up memory.

By injecting 2D instance cues from camera data into the BEV space of 4D radar data, SIFormer overcomes radar's sparse geometry and significantly boosts 3D object detection accuracy.

Overcome the extreme sparsity and noise of 4D radar data with SD4R, a new method that significantly boosts 3D object detection performance.

GLM-5 doesn't just code; it engineers, showcasing unprecedented capability in tackling end-to-end software engineering challenges.