We introduce ALPBench, a benchmark for attribution-level long-term personal behavior understanding. Unlike item-focused benchmarks, ALPBench predicts user-interested attribute combinations, enabling ground-truth evaluation even for newly introduced items.

We propose OneRec-V2 with Lazy Decoder-Only Architecture that eliminates encoder bottlenecks and incorporates real-world user feedback for better preference alignment.

We propose OneRec, which reshapes the recommendation system through an end-to-end generative approach and achieves promising results. Firstly, we have enhanced the computational FLOPs of the current recommendation model by 10 × and have identified the scaling laws for recommendations within certain boundaries.

We propose CoSP, an intelligent inverse design method based on contrastive pretrained LLM for reconfigurable multi-state metamaterials.

We propose AHEAD: a heterogeneity-aware unsupervised graph anomaly detection approach based on the encoder-decoder framework.

We present TwiBot-22, the largest graph-based Twitter bot detection benchmark to date, which provides diversified entities and relations in Twittersphere and has considerably better annotation quality.