Yifei Wang

Bridging the gap in multi-camera depth prediction, SurroundNEXO achieves a 33.2% reduction in single-view error by rethinking how we leverage ego-centric geometry.

Ditch K-means: sparse coding slashes indexing time by 15x while simultaneously boosting retrieval accuracy in multi-vector retrieval.

Diffusion LLMs can achieve up to 6.1x higher throughput than autoregressive models by dynamically adjusting decoding granularity based on real-time load, a feat unattainable with fixed-block approaches.

Open-source QUEST agents, trained solely on 8K synthetic tasks, rival or surpass proprietary research agents, proving that scaling data synthesis can unlock frontier performance.

Outlier tokens in Diffusion Transformers aren't just extreme values; they corrupt local patch semantics, and can be tamed with Dual-Stage Registers to boost image generation quality.