Jiacheng Xu

Code generation models can now self-improve at test time without ground-truth unit tests by turning behavioral execution agreement on generated input probes into a stable, hack-resistant policy gradient signal.

TCS not only generates sound test cases but also adapts to the model's weaknesses, leading to a marked improvement in code generation performance.

Directly editing 3D meshes in Blender through a visual-centric, agentic approach could revolutionize how artists interact with complex geometry.

Achieving six times the inference throughput of current LLMs while maintaining accuracy, Nemotron 3 Ultra redefines performance benchmarks for agentic reasoning tasks.

Nemotron 3 Super proves you can achieve comparable accuracy to existing 120B models, but with significantly higher inference throughput, by combining Mamba, Attention, and Mixture-of-Experts.

Skip the costly real-world data collection: GraspDreamer uses generated human demonstrations from visual generative models to train robots for zero-shot functional grasping.