Defu Lian

Distilling operational knowledge from GitHub repositories boosts AI research agents' performance by over 134% on key benchmarks.

CHAP achieves a breakthrough in generative retrieval by aligning dynamic queries with static item representations, enhancing both relevance and inference efficiency.

SWIM redefines list evaluation by modeling user engagement as a survival process, leading to substantial gains in recommendation effectiveness.

Bridging the intent gap in e-commerce, TTP boosts order volume by 0.46% through reasoning-driven personalized retrieval.

OPD transfers reasoning skills rather than answers, revealing a complex interplay between teacher-student origins that can either enhance or hinder model capabilities.

Achieving duplicate-free item selection in recommendation systems without sacrificing efficiency, DIRECTOR revolutionizes how we approach reranking by leveraging transport-optimized retrieval.

Cross-sample consistency regularization can eliminate feature fragmentation in Sparse Autoencoders, leading to more reliable and interpretable latent representations.

RAVEN achieves a remarkable 20.2% improvement in forecasting accuracy for S&P500 by dynamically adapting its context windows to the financial regime.

Surprisingly, the "think before answer" paradigm fails to enhance generative recommendation models, prompting a novel approach that redefines how reasoning is integrated into these systems.

LLMs can beat traditional time-series models by orchestrating specialized agents in a dynamic workflow, iteratively refining forecasts with memory and ensemble methods.

LLMs get a reasoning boost by treating information extraction not as a one-off task, but as a dynamic cache that persists and filters information across multiple steps.

Asymmetric encoders, trained with a novel two-stage approach, can beat symmetric LLM-based models in Chinese medical text retrieval while maintaining low latency.