Search arXiv⌕ Search

arXiv subjects

Weiqing Zeng

Publications and source records attributed to Weiqing Zeng.

2 recordsLinked to original sources

SAGE-PAIR: Source-Pretrained Routed Residual Adaptation for Sparse-Feedback Recommendation

Recommendation systems often enter a new serving window before enough outcomes are available to retrain the deployed model. We study this regime with 0.05-1.0% target feedback, a range that spans our stress tests while keeping supervision far below the degrees of freedom of the source recommender. At this scale, existing fine-tuning and meta-learning methods still estimate target-specific updates from extremely sparse feedback, leaving the update direction weakly identified. SAGE-PAIR instead transfers a source-supported residual correction space and only calibrates this space using target outcomes. We introduce SAGE-PAIR, a staged adapter that pretrains a low-dimensional global residual on an adjacent source period and adds a soft router over residual experts conditioned on source user profiles. Target feedback then calibrates this residual state rather than relearning the recommender. On a locked test split of KuaiSAR-v2, SAGE-PAIR (Full) achieves a 1.77% relative improvement in NDCG@10, while a core-protocol comparison shows a further 0.25% gain from routed experts beyond source-pretrained PAIR. Matched source-pretrained LoRA and Adapter-Tuning baselines remain near the source model, supporting the need for a different adaptation space. Thus, SAGE-PAIR improves ranking quality with millisecond-scale adaptation and inference costs. Sparse-feedback adaptation is fundamentally governed by the identifiability of the update space rather than by label count alone. Source pretraining supplies estimable correction directions for scarce labels, while user-conditioned routing contributes a consistent, differentiated cross-user correction on top of the global correction. Our code is available at https://anonymous.4open.science/r/SAGE-PAIR-610E/.

cs.IR↗

Controllably releasing long-lived quantum memory for photonic polarization qubit into multiple separate photonic channels

We report an experiment in which long-lived quantum memories for photonic polarization qubits (PPQs) are controllably released into any one of multiple separate channels. The PPQs are implemented with an arbitrarily-polarized coherent signal light pulses at the single-photon level and are stored in cold atoms by means of electromagnetic-induced-transparency scheme. Reading laser pulses propagating along the direction at a small angle relative to quantum axis are applied to release the stored PPQs into an output channel. By changing the propagating directions of the read laser beam, we controllably release the retrieved PPQs into 7 different photonic output channels, respectively. At one of the output channels, the measured maximum quantum-process fidelity for the PPQs is 94.2% at storage time of t= 0.85ms. At storage time of 6 ms, the quantum-process fidelity is still beyond 78%, the threshold for the violation of the Bell inequality. The demonstrated controllable release of the stored PPQs may extend the capabilities of the quantum information storage technique.

quant-ph↗