Yi Yang

Bypassing RGB entirely, Latent-to-4D achieves significant improvements in 4D scene generation while maintaining a reusable framework across different video models.

Achieving a 96.30% attack success rate, DFCS reveals that strategic sample selection based on feature diversity can dramatically enhance the effectiveness of backdoor attacks.

OCSD reveals how isolating observation effects can lead to more effective token-level updates in reinforcement learning, outperforming traditional methods.

Local correction mechanisms in offline RL can significantly enhance value estimation stability, reducing the impact of out-of-distribution errors.

Teacher guidance can be strategically enhanced by targeting high-disagreement states, leading to significant performance gains in agentic tasks.

RoMeRL achieves an 80% reduction in the Cold-Q ratio while enhancing feedback density sixfold, revolutionizing how LLM agents manage memory and rewards.

ClinFusion sets a new benchmark in multimodal medical understanding, outperforming both open-source and proprietary models in generating clinically relevant insights from diverse medical images.

Forget expensive audio-text data collection: TASU2 lets you dial in the perfect amount of noise for training your speech LLM, all from text.

Forget static attention allocation – Flux Attention dynamically routes layers between full and sparse attention based on context, delivering significant speedups without sacrificing performance in long-context LLMs.