Yao Wang

Dynamic 3D scene compression does not require specialized motion models—simply appending frame indices to Gaussians and feeding them into off-the-shelf static codecs slashes bitrates by up to 71.8%.

FlashVector is an agentic system that optimizes performance across all layers of the model serving stack, and the key contribution is an extensible framework to generalize the single kernel optimization agent paradigm to heterogeneous technical stacks, and to deliver performance improvements holistically.

FoRIS redefines in-context segmentation by transforming it into a progressive refinement process, achieving state-of-the-art results without the need for training.

Aggressive 4-bit quantization can cripple MLLM performance, but a novel residual reconstruction technique recovers lost capabilities with minimal overhead.

RGE reveals that long-horizon agents can drift significantly from their intended tasks, even while appearing compliant at each step, highlighting the need for deeper oversight mechanisms.

Achieving coupled-cluster accuracy for molecular properties with the computational cost of a single DFT calculation could revolutionize molecular modeling in chemistry.

Forget perturbation theory: this dissipaton-based approach offers a fully nonperturbative and non-Markovian route to modeling heat transport in locally probed systems.