Ruizhong Qiu

RECONTEXT boosts long-context reasoning in LLMs by effectively reusing evidence from the input, leading to superior performance without the need for retraining.

G2Rec captures user interest prototypes more accurately than existing methods, enabling generative recommendation systems to operate without ground-truth user interests.

Looping language models isn't just for single agents anymore: Recursive Multi-Agent Systems (RecursiveMAS) show that agent collaboration itself can be scaled through recursion, yielding faster and more efficient problem-solving.

Diffusion language models can achieve faster decoding and better accuracy by learning directly from the token reveal order suggested by a lightweight autoregressive teacher, without expensive distillation.

Forget imbalanced LoRA usage: ReMix leverages reinforcement learning to route effectively among LoRAs, boosting performance in parameter-efficient fine-tuning.