arXiv subjects

Yifang Yuan

Publications and source records attributed to Yifang Yuan.

9 recordsLinked to original sources

arXiv2026

SPAR: Enhancing Industrial-Scale Generative POI Recommendation via Real-World Spatial Perception

Generative Point-of-Interest (POI) recommendation, autoregressively generating a target POI's semantic ID (SID), holds great promise for Location-Based Services, where a recommendation helps only if the user can reach it. Yet, existing methods operate within an interest space defined by behavior sequences and collaborative signals, where geography enters only as a textual attribute of the SID, leaving no explicit mechanism to learn or preserve how urban places are related by distance, direction, and reachability; their predictions are thus behaviorally plausible yet far from the user's real-time location. We argue that such services require injecting real urban spatial knowledge into the interest space, rather than inferring geography from behavior alone. Hence, we propose SPAR, a unified framework whose three synergistic stages jointly construct, cultivate, and preserve urban spatial knowledge: (1) at the tokenization level, Spatially-Intrinsic SID (SI-SID) explicitly encodes longitude--latitude coordinates into a sinusoidal geospatial embedding and fuses it with the textual semantic embedding, producing identifiers via RQ-Kmeans that are simultaneously semantically and geographically consistent; (2) at the cognition level, Multi-Granular Geospatial CPT (MG-CPT) continually pre-trains the base LLM on 25 curated geospatial datasets organized into three tiers of basic attributes, pairwise relations, and city-scale navigation, so that scattered POIs cohere into a connected urban space; and (3) at the adaptation level, Task-Vector Anchored SFT (TV-SFT) anchors the acquired spatial knowledge as a frozen parameter-space task vector to prevent its catastrophic forgetting during behavioral fine-tuning, thereby fusing the two spaces. Extensive quantitative and visualization experiments on two public and four industrial-scale datasets demonstrate the effectiveness of SPAR.

cs.IR↗

arXiv2026

GeoGR: Enabling Spatio-Temporal Aware Industrial-scale Generative POI Recommendations

Next Point-of-Interest (POI) prediction is a fundamental task in location-based services (LBS), especially critical for large-scale navigation platforms such as AMAP that serve billions of users in diverse lifestyle scenarios. Although recent POI recommendation approaches based on SIDs have achieved promising performance, they struggle in complex, sparse real-world environments due to two key limitations: (1) inadequate modeling of high-quality SIDs that capture cross-category spatio-temporal collaborative relationships, and (2) poor alignment between large language models (LLMs) and the POI recommendation task. To this end, we propose GeoGR, a geographic generative recommendation framework tailored for navigation-based LBS like AMAP, which perceives changes in users' contextual states and enables spatio-temporal aware POI recommendation. GeoGR features a two-stage design: (i) a geo-aware SID tokenization pipeline that explicitly learns spatio-temporal collaborative semantic representations via geographically constrained co-visited POI pairs, contrastive semantic representation learning, and iterative refinement; and (ii) a multi-stage LLM training strategy that aligns non-native SID tokens through continued pre-training with multiple prompt templates and enables autoregressive POI generation via supervised fine-tuning. Extensive experiments on multiple real-world datasets demonstrate GeoGR superiority over state-of-the-art baselines. Moreover, the deployment on the large-scale AMAP platform over three months, serving millions of users and delivering significant online gains of +2.91% in WINRATE and +5.55% in PV_CTR, confirms its practical effectiveness and scalability in production.

cs.IR↗

arXiv2026

Guess Where You Go: Generative Next Point-of-Interest Recommendation in Amap

Generative retrieval enables recommender systems to retrieve items by generating compact item identifiers, but scaling it to industrial scenarios remains challenging due to redundant or colliding token assignments and insufficient integration of heterogeneous item signals. These challenges are particularly critical for next Point-of-Interest (POI) recommendation, where models must represent structured spatial entities, capture sequential mobility patterns, and produce predictions consistent with real user behavior. We propose Gwhere, an end-to-end industrial framework that integrates semantic identifier (SID) generation with LLM-based generative next POI recommendation. Gwhere first learns discriminative POI SIDs through a contrastive residual-quantization tokenizer that aligns textual, visual, spatial, and collaborative signals. Based on these SIDs, Gwhere adapts LLMs to mobility scenarios via continued pretraining on enriched spatio-temporal corpora, supervised fine-tuning, and Exposure-Aware Kahneman-Tversky Optimization (EAKTO), a reinforcement learning objective for behavioral preference alignment. Experiments on public datasets and Amap's large-scale industrial dataset demonstrate the effectiveness of Gwhere. The system has been deployed in Amap's homepage service under high-concurrency and low-latency constraints. Long-term online A/B tests show improvements of 5.83% in P-CTR and 6.20% in U-CTR over the production baseline. The implementation is publicly available at https://github.com/alibaba/SimCIT.

cs.IR↗

arXiv2025

Cognitive-Aligned Spatio-Temporal Large Language Models For Next Point-of-Interest Prediction

The next point-of-interest (POI) recommendation task aims to predict the users' immediate next destinations based on their preferences and historical check-ins, holding significant value in location-based services. Recently, large language models (LLMs) have shown great potential in recommender systems, which treat the next POI prediction in a generative manner. However, these LLMs, pretrained primarily on vast corpora of unstructured text, lack the native understanding of structured geographical entities and sequential mobility patterns required for next POI prediction tasks. Moreover, in industrial-scale POI prediction applications, incorporating world knowledge and alignment of human cognition, such as seasons, weather conditions, holidays, and users' profiles (such as habits, occupation, and preferences), can enhance the user experience while improving recommendation performance. To address these issues, we propose CoAST (Cognitive-Aligned Spatial-Temporal LLMs), a framework employing natural language as an interface, allowing for the incorporation of world knowledge, spatio-temporal trajectory patterns, profiles, and situational information. Specifically, CoAST mainly comprises of 2 stages: (1) Recommendation Knowledge Acquisition through continued pretraining on the enriched spatial-temporal trajectory data of the desensitized users; (2) Cognitive Alignment to align cognitive judgments with human preferences using enriched training data through Supervised Fine-Tuning (SFT) and a subsequent Reinforcement Learning (RL) phase. Extensive offline experiments on various real-world datasets and online experiments deployed in "Guess Where You Go" of AMAP App homepage demonstrate the effectiveness of CoAST.

cs.AI↗

arXiv2025

A Simple Contrastive Framework Of Item Tokenization For Generative Recommendation

Generative retrieval-based recommendation has emerged as a promising paradigm aiming at directly generating the identifiers of the target candidates. However, in large-scale recommendation systems, this approach becomes increasingly cumbersome due to the redundancy and sheer scale of the token space. To overcome these limitations, recent research has explored the use of semantic tokens as an alternative to ID tokens, which typically leveraged reconstruction-based strategies, like RQ-VAE, to quantize content embeddings and significantly reduce the embedding size. However, reconstructive quantization aims for the precise reconstruction of each item embedding independently, which conflicts with the goal of generative retrieval tasks focusing more on differentiating among items. Moreover, multi-modal side information of items, such as descriptive text and images, geographical knowledge in location-based recommendation services, has been shown to be effective in improving recommendations by providing richer contexts for interactions. Nevertheless, effectively integrating such complementary knowledge into existing generative recommendation frameworks remains challenging. To overcome these challenges, we propose a novel unsupervised deep quantization exclusively based on contrastive learning, named SimCIT (a Simple Contrastive Item Tokenization framework). Specifically, different from existing reconstruction-based strategies, SimCIT propose to use a learnable residual quantization module to align with the signals from different modalities of the items, which combines multi-modal knowledge alignment and semantic tokenization in a mutually beneficial contrastive learning framework. Extensive experiments across public datasets and a large-scale industrial dataset from various domains demonstrate SimCIT's effectiveness in LLM-based generative recommendation.

cs.IR↗

arXiv2021

Pressure-induced Reemergence of Superconductivity in Topological Kagome Metal CsV3Sb5

Quasi-two-dimensional kagome metals AV3Sb5 (A = K, Rb, and Cs) have attracted much recent interest due to exotic quantum phenomena such as unconventional superconductivity, topological charge order and giant anomalous Hall effect. Here we report pressure-induced reemergent superconductivity in CsV3Sb5 by electrical transport measurements under high pressures up to 47.9 GPa. We show that the superconducting critical temperature Tc is first enhanced by pressure and reaches its first maximum ~ 8.9 K at 0.8 GPa, then the Tc is suppressed by pressure and cannot be detected above 7.5 GPa, forming a dome-shaped superconducting phase diagram. Remarkably, upon further compression above 16.5 GPa, a new superconducting state arises, of which Tc is enhanced by pressure to a second maximum ~ 5.0 K and the reemergent superconductivity keeps robust up to 47.9 GPa. Combined with high-pressure synchrotron x-ray diffraction measurements that demonstrate the stability of the pristine hexagonal phase up to 43.1 GPa, we suggest that the reemergence of superconductivity in the V-based superconductor could be attributed to a pressure-induced Lifshitz transition.

cond-mat.supr-con↗

arXiv2019

Persistent Insulator: Avoidance of Metallization at Megabar Pressures in Strongly Spin-Orbit-Coupled Sr2IrO4

It is commonly anticipated that an insulating state collapses in favor of an emergent metallic state at high pressures as the unit cell shrinks and the electronic bandwidth broadens to fill the insulating energy band gap. Here we report a rare insulating state that persists up to at least 185 GPa in the antiferromagnetic iridate Sr2IrO4, which is the archetypical spin-orbit-driven Jeff = 1/2 insulator. This study shows the electrical resistance of single-crystal Sr2IrO4 initially decreases with applied pressure, reaches a minimum in the range, 32 - 38 GPa, then abruptly rises to fully recover the insulating state with further pressure increases up to 185 GPa. Our synchrotron x-ray diffraction and Raman scattering data show the onset of the rapid increase in resistance is accompanied by a structural phase transition from the native tetragonal I41/acd phase to an orthorhombic Pbca phase (with much reduced symmetry) at 40.6 GPa. The clear-cut correspondence of these two anomalies is key to understanding the stability of the insulating state at megabar pressures: Pressure-induced, severe structural distortions prevent the expected metallization, despite the 26% volume compression attained at the highest pressure accessed in this study. Moreover, the resistance of Sr2IrO4 remains stable while the applied pressure is tripled from 61 GPa to 185 GPa. These results suggest that a novel type of electronic Coulomb correlation compensates the anticipated band broadening in strongly spin-orbit-coupled materials at megabar pressures.

cond-mat.str-el↗

arXiv2019

Pressure-tunable large anomalous Hall effect of the ferromagnetic kagome-lattice Weyl semimetal Co3Sn2S2

We investigate the pressure evolution of the anomalous Hall effect in magnetic topological semimetal Co3Sn2S2 in diamond anvil cells with pressures up to 44.9-50.9 GPa. No evident trace of structural phase transition is detected through synchrotron x-ray diffraction over the measured pressure range of 0.2-50.9 GPa. We find that the anomalous Hall resistivity and the ferromagnetism are monotonically suppressed as increasing pressure and almost vanish around 22 GPa. The anomalous Hall conductivity varies non-monotonically against pressure at low temperatures, involving competition between original and emergent Weyl nodes. Combined with first-principle calculations, we reveal that the intrinsic mechanism due to the Berry curvature dominates the anomalous Hall effect under high pressure.

cond-mat.mtrl-sci↗

arXiv2017

Pressure-induced Superconductivity in the Three-component Fermion Topological Semimetal Molybdenum Phosphide

Topological semimetal, a novel state of quantum matter hosting exotic emergent quantum phenomena dictated by the non-trivial band topology, has emerged as a new frontier in condensed-matter physics. Very recently, a coexistence of triply degenerate points of band crossing and Weyl points near the Fermi level was theoretically predicted and immediately experimentally verified in single crystalline molybdenum phosphide (MoP). Here we show in this material the high-pressure electronic transport and synchrotron X-ray diffraction (XRD) measurements, combined with density functional theory (DFT) calculations. We report the emergence of pressure-induced superconductivity in MoP with a critical temperature Tc of about 2 K at 27.6 GPa, rising to 3.7 K at the highest pressure of 95.0 GPa studied. No structural phase transitions is detected up to 60.6 GPa from the XRD. Meanwhile, the Weyl points and triply degenerate points topologically protected by the crystal symmetry are retained at high pressure as revealed by our DFT calculations. The coexistence of three-component fermion and superconductivity in heavily pressurized MoP offers an excellent platform to study the interplay between topological phase of matter and superconductivity.

cond-mat.supr-con↗