Jiarui Liu

Skill-switching accuracy in LLMs drops significantly on complex tasks, but a new training approach boosts performance from 34.4% to 68.4% on challenging benchmarks.

Infrared adversarial attacks can compromise Optical Flow Estimation Networks in real time, exposing critical vulnerabilities in autonomous systems.

Proprietary MLLMs may achieve high diagnostic accuracy, but they still struggle with reliable clinical reasoning, revealing significant gaps in their practical utility.

PACE-Bench predicts agentic performance with remarkable accuracy while slashing evaluation costs to a fraction of traditional methods.

Prioritizing domains based on their cross-domain transferability can boost multi-domain RLVR performance by up to 10%.

PaperMentor delivers actionable writing feedback that 90.6% of users found useful, setting a new standard for AI-assisted manuscript development.

LLMs fail to deliver personalized responses that align with human judgments, often producing results indistinguishable from generic outputs.

Turn sparse binary rewards into dense supervision signals by having a model revise its own work, then distilling the revision strategy back into the original generation.