Ying Li

Achieving a 30x speedup in inference without sacrificing action performance, Efficient-WAM redefines efficiency in embodied control models.

GraspFoM reveals that leveraging 3D object priors can dramatically enhance both grasping accuracy and 3D reconstruction fidelity with minimal overhead.

Achieving up to 6.4x faster autoregressive image generation without sacrificing quality could redefine efficiency benchmarks in the field.

CEON bridges critical gaps in circular economy knowledge representation, enabling seamless data sharing across diverse industries.

LLM agents can be tricked into unauthorized actions via indirect prompt injection, but AuthGraph's dual-graph approach slashes attack success rates from 40% to 1% while preserving utility.

Freezing your VQ decoder during text-to-image post-training might be why your images are getting worse even as your CLIP scores improve.

RFT's Achilles heel? This benchmark reveals how fragile reinforcement fine-tuning is, and introduces an automated system to catch and fix training failures before they tank your LLM.

Frustrated with clunky architecture simulators? Akita offers a breath of fresh air with its focus on developer experience, promising faster prototyping and experimentation.