arXiv subjects

Xuesi Wang

Publications and source records attributed to Xuesi Wang.

6 recordsLinked to original sources

arXiv2026

Decoupled Residual Quantization for Robust Semantic IDs in Recommendation

Semantic IDs represent items as shared discrete token sequences and have become a practical tool for recommendation and retrieval. Yet it remains difficult to tell why a tokenizer fails: poor quality may come from codebook underutilization, unstable decision boundaries, or geometric distortion of the embedding space. This paper develops a quantitative framework for diagnosing these failures through expected codeword overlap and effective codebook capacity. The former measures expected codeword confusion under retrieval-time perturbation, while the latter converts that confusion into an effective number of usable, well-separated codes. The framework links semantic boundary confusion to both code usage imbalance and Euclidean geometric constraints. As a proof of concept, we present Decoupled Residual Quantization (DRQ), which separates continuous geometry reconstruction from discrete distribution matching. Experiments on a large-scale industrial dataset show that Semantic ID quality is multi-objective: symbolic robustness, reconstruction fidelity, and behavior-aware soft matching each stress different aspects of a tokenizer. These downstream observations are based on one proprietary industrial dataset, so they should be read as a case study rather than a universal benchmark claim.

cs.IR↗

arXiv2026

UniRec: Bridging the Expressive Gap between Generative and Discriminative Recommendation via Chain-of-Attribute

Generative Recommendation (GR) reframes retrieval and ranking as autoregressive decoding over Semantic IDs (SIDs), unifying the multi-stage pipeline into a single model. Yet a fundamental expressive gap persists: discriminative models score items with direct feature access enabling explicit user-item crossing, whereas GR decodes over compact SID tokens without item-side signal. We formalize this via Bayes' theorem: ranking by p(y|f,u) is equivalent to ranking by p(f|y,u), which factorizes autoregressively over item features, showing that a generative model with full feature access matches its discriminative counterpart, with any practical gap stemming solely from incomplete feature coverage. We propose UniRec with Chain-of-Attribute (CoA) as its core mechanism. CoA prefixes each SID sequence with structured attribute tokens:category, seller, brand, before decoding the SID, recovering the item-side feature crossing that discriminative models exploit. Since items sharing identical attributes cluster in adjacent SID regions, attribute conditioning yields a measurable per-step entropy reduction H(s_k|s<k,a) < H(s_k|s<k), narrowing the search space and stabilizing beam search. We further address two deployment challenges: Capacity-constrained SID introduces exposure-weighted capacity penalties into residual quantization to suppress token collapse and the Matthew effect; Conditional Decoding Context (CDC) combines Task-Conditioned BOS with hash-based Content Summaries to inject scenario signals at each decoding step. A joint RFT and DPO framework aligns the model with business objectives beyond distribution matching. Experiments show UniRec outperforms the strongest baseline by +22.6% HR@50 overall and +15.5% on high-value orders. Deployed on Shopee's e-commerce platform, online A/B tests confirm significant gains in PVCTR (+5.37%), orders (+4.76%), and GMV (+5.60%).

cs.IR↗

arXiv2025

Establishing Reliability Metrics for Reward Models in Large Language Models

The reward model (RM) that represents human preferences plays a crucial role in optimizing the outputs of large language models (LLMs), e.g., through reinforcement learning from human feedback (RLHF) or rejection sampling. However, a long challenge for RM is its uncertain reliability, i.e., LLM outputs with higher rewards may not align with actual human preferences. Currently, there is a lack of a convincing metric to quantify the reliability of RMs. To bridge this gap, we propose the \textit{\underline{R}eliable at \underline{$η$}} (RETA) metric, which directly measures the reliability of an RM by evaluating the average quality (scored by an oracle) of the top $η$ quantile responses assessed by an RM. On top of RETA, we present an integrated benchmarking pipeline that allows anyone to evaluate their own RM without incurring additional Oracle labeling costs. Extensive experimental studies demonstrate the superior stability of RETA metric, providing solid evaluations of the reliability of various publicly available and proprietary RMs. When dealing with an unreliable RM, we can use the RETA metric to identify the optimal quantile from which to select the responses.

cs.AI↗

arXiv2023

Learning-To-Ensemble by Contextual Rank Aggregation in E-Commerce

Ensemble models in E-commerce combine predictions from multiple sub-models for ranking and revenue improvement. Industrial ensemble models are typically deep neural networks, following the supervised learning paradigm to infer conversion rate given inputs from sub-models. However, this process has the following two problems. Firstly, the point-wise scoring approach disregards the relationships between items and leads to homogeneous displayed results, while diversified display benefits user experience and revenue. Secondly, the learning paradigm focuses on the ranking metrics and does not directly optimize the revenue. In our work, we propose a new Learning-To-Ensemble (LTE) framework RAEGO, which replaces the ensemble model with a contextual Rank Aggregator (RA) and explores the best weights of sub-models by the Evaluator-Generator Optimization (EGO). To achieve the best online performance, we propose a new rank aggregation algorithm TournamentGreedy as a refinement of classic rank aggregators, which also produces the best average weighted Kendall Tau Distance (KTD) amongst all the considered algorithms with quadratic time complexity. Under the assumption that the best output list should be Pareto Optimal on the KTD metric for sub-models, we show that our RA algorithm has higher efficiency and coverage in exploring the optimal weights. Combined with the idea of Bayesian Optimization and gradient descent, we solve the online contextual Black-Box Optimization task that finds the optimal weights for sub-models given a chosen RA model. RA-EGO has been deployed in our online system and has improved the revenue significantly.

cs.LG↗

arXiv2017

On the Achievable Spectral Efficiency of Spatial Modulation Aided Downlink Non-Orthogonal Multiple Access

In this paper, a novel spatial modulation aided non-orthogonal multiple access (SM-NOMA) system is proposed. We use mutual information (MI) to characterize the achievable spectral efficiency (SE) of the proposed SM-NOMA system. Due to the finite-alphabet space-domain inputs employed by SM, the expression of the corresponding MI lacks a closed-form formulation. Hence, a lower bound is proposed to quantify the MI of the SM-NOMA system. Furthermore, its asymptotic property is also theoretically investigated in both low and high signal-to-noise ratio (SNR) regions. The SE performance and its analysis of our proposed SM-NOMA system are confirmed by simulation results.

cs.IT↗

arXiv2013

Prolonged spontaneous emission and dephasing of localized excitons in air-bridged carbon nanotubes

The bright exciton emission of semiconducting carbon nanotubes is appealing for optoelectronic and quantum photonic devices as well as fundamental studies of light-matter interaction in one-dimensional nanostructures. The photophysics of excitons in carbon nanotubes till date is however largely affected by extrinsic effects of the dielectric environment. Here we carried out time-resolved photoluminescence measurements over 14 orders of magnitude for ultra-clean carbon nanotubes bridging an airgap over pillar posts. Our measurements demonstrate a new regime of intrinsic exciton photophysics with prolonged spontaneous emission times up to T1=18 ns, between one to two orders of magnitude better than prior measurements and in agreement with values first hypothesized by theorists about a decade ago. Further we establish for the first time the exciton decoherence times of individual nanotubes in the time-domain and found four-fold prolonged values up to T2=2.1 ps compared to ensemble measurements. These first observations motivate new discussions about the magnitude of the intrinsic dephasing mechanism while the prolonged exciton dynamics is promising for device applications.

cond-mat.mes-hall↗