{"total":13,"items":[{"citing_arxiv_id":"2605.23702","ref_index":11,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"TubiFM: Unified Item, Carousel, and Search Ranking for Streaming Discovery","primary_cat":"cs.IR","submitted_at":"2026-05-22T14:53:00+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A Llama-based model trained on serialized user stories unifies item, carousel, and search ranking and outperforms specialist baselines offline while improving some online metrics and reducing latency.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.21832","ref_index":16,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"FLUID: From Ephemeral IDs to Multimodal Semantic Codes for Industrial-Scale Livestreaming Recommendation","primary_cat":"cs.AI","submitted_at":"2026-05-20T23:52:51+00:00","verdict":null,"verdict_confidence":null,"novelty_score":null,"formal_verification":null,"one_line_summary":null,"context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.17131","ref_index":27,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"A Systematic Survey on Deep Learning Architectures for Point Cloud Classification and Segmentation","primary_cat":"cs.CV","submitted_at":"2026-05-16T19:37:41+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"A systematic literature survey that categorizes deep learning architectures for point cloud classification, part segmentation, and semantic segmentation, evaluates them on benchmarks, and discusses innovations, limitations, and future directions.","context_count":1,"top_context_role":"dataset","top_context_polarity":"background","context_text":"Based on data origin, 3D datasets can be categorized assyntheticorreal-world. Synthetic datasets, such as ModelNet [113] and ShapeNet [10], consist of CAD models that are hand-crafted by humans and represented as 3D meshes. Synthetic datasets are simpler to deal with because there are no occlusions or noise associated with them. In contrast, Real-world datasets, such as KITTI [27], ScanNet [15], and nuScenes [8], are acquired by scanning the real world with 3D sensors and often contain artifacts. There are primarily two types of 3D sensors: LiDAR and RGB-D. Outdoor scenes (KITTI, nuScenes, etc.) are usually scanned by LiDARs, and indoor scenes (ScanNet, ScanObjectNN [100], etc.) by RGB-D cameras. Datasets also differ in scope: some point cloud datasets contain the whole scene (ScanNet, S3DIS [2], etc."},{"citing_arxiv_id":"2605.11662","ref_index":49,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"HSUGA: LLM-Enhanced Recommendation with Hierarchical Semantic Understanding and Group-Aware Alignment","primary_cat":"cs.IR","submitted_at":"2026-05-12T07:22:42+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"HSUGA improves LLM-enhanced sequential recommendation via staged hierarchical semantic understanding for better preference extraction and group-aware alignment that varies intensity by user activity level.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.10408","ref_index":24,"ref_count":2,"confidence":0.9,"is_internal_anchor":false,"paper_title":"VISOR: A Vision-Language Model-based Test Oracle for Testing Robots","primary_cat":"cs.SE","submitted_at":"2026-05-11T11:46:57+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"VISOR is a VLM-based automated test oracle that evaluates robot task correctness and quality from videos while reporting its own uncertainty, tested on GPT and Gemini across four tasks and over 1000 videos with Gemini showing higher recall and GPT higher precision but low uncertainty-correctness tie","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"Models (LLMs) and VLMs for failure detection and automated cor- rection. REFLECT [30] converts multi-sensory robot actions into hi- erarchical textual summaries, enabling LLMs to explain failures and suggest corrective actions. RoboReflect [32] employs VLMs for re- flective reasoning and trajectory planning adjustment in ambiguous grasping scenarios, while SC-VLA [24] integrates fast action predic- tion with a slower VLM-based system for detecting and correcting errors via chain-of-thought reasoning. Code-as-Monitor [54] lever- ages VLMs to generate code to monitor spatio-temporal constraints in both reactive and proactive modes of robotic tasks, and meth- ods like RoboFAC [31] and AHA [15] fine-tune VLMs for natural-"},{"citing_arxiv_id":"2605.10323","ref_index":13,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Every Preference Has Its Strength: Injecting Ordinal Semantics into LLM-Based Recommenders","primary_cat":"cs.IR","submitted_at":"2026-05-11T10:21:36+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"OSA improves LLM-based recommenders by anchoring ordinal preference levels as numeric tokens in the model's latent space to retain fine-grained strength information when fusing collaborative signals.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"which integrates collaborative filtering (CF) signals into the LLM's input or latent space. This integration is typically achieved by pro- jecting or aligning user or item representations from CF models within the LLM, allowing the LLM to jointly leverage textual seman- tics and collaborative information. Most existing approaches frame this integration primarily as a representation mapping or projection problem [13, 15], for example by injecting embeddings from CF models as additional tokens [14, 23] or applying distillation [5] and binarization [22] techniques. These works have shown that inject- ing collaborative information into LLM-driven recommendation can yield substantial improvements over purely textual [ 2, 9] or purely collaborative baselines [8, 11, 17]."},{"citing_arxiv_id":"2605.10207","ref_index":24,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"LASAR: Latent Adaptive Semantic Aligned Reasoning for Generative Recommendation","primary_cat":"cs.IR","submitted_at":"2026-05-11T08:52:53+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"LASAR uses two-stage supervised training plus reinforcement learning to ground semantic IDs, align latent reasoning trajectories to CoT hidden states via KL divergence, and adaptively choose reasoning depth, halving average steps while improving quality on three datasets.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"8bb0d291acd4acf06ef112099c16f326-Abstract-Conference.html. [23] Xiaoyu Kong, Leheng Sheng, Junfei Tan, Yuxin Chen, Jiancan Wu, An Zhang, Xiang Wang, and Xiangnan He. Minionerec: An open-source framework for scaling generative recommendation. CoRR, abs/2510.24431, 2025. doi: 10.48550/ARXIV .2510.24431. URL https://doi.org/ 10.48550/arXiv.2510.24431. [24] Xinhang Li, Chong Chen, Xiangyu Zhao, Yong Zhang, and Chunxiao Xing. E4srec: An elegant effective efficient extensible solution of large language models for sequential recommendation. CoRR, abs/2312.02443, 2023. doi: 10.48550/ARXIV .2312.02443. URL https://doi.org/ 10.48550/arXiv.2312.02443. [25] Jiacheng Lin, Tian Wang, and Kun Qian. Rec-r1: Bridging generative large language models"},{"citing_arxiv_id":"2605.06906","ref_index":28,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"TraXion: Rethinking Pre-training Frameworks for Mobility and Beyond","primary_cat":"cs.LG","submitted_at":"2026-05-07T20:10:53+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"TraXion supplies a unified pre-training approach for multi-entity spatiotemporal event streams that outperforms task-specific baselines on mobility tasks and transfers unchanged to authentication logs and ICU mortality prediction.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.23593","ref_index":68,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"When AI reviews science: Can we trust the referee?","primary_cat":"cs.AI","submitted_at":"2026-04-26T08:03:32+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"AI peer review systems are vulnerable to prompt injections, prestige biases, assertion strength effects, and contextual poisoning, as demonstrated by a new attack taxonomy and causal experiments on real conference submissions.","context_count":1,"top_context_role":"background","top_context_polarity":"unclear","context_text":", et al. (2018). Black- box adversarial attacks with limited queries and infor- mation. Proc. Int. Conf. Mach. Learn. 2018:2137-2146. DOI:10.48550/arXiv.1804.08598 [67] Papernot N., McDaniel P ., Sinha A., et al. (2018). Sok: Security and privacy in machine learning. Proc. IEEE Eur. Symp. Secur. Priv. 2018:399-414. DOI:10.1109/ Eu- roSP .2018.00035 [68] Fredrikson M., Jha S. and Ristenpart T. (2015). Model inversion attacks that exploit confidence in- formation and basic countermeasures. Proc. ACM SIGSAC Conf. Comput. Commun. Secur. 2015:1322-1333. DOI:10.1145/2810103.2813677 [69] Shokri R., Stronati M., Song C., et al. (2017). Member- ship inference attacks against machine learning models. Proc."},{"citing_arxiv_id":"2604.21305","ref_index":15,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"WPGRec: Wavelet Packet Guided Graph Enhanced Sequential Recommendation","primary_cat":"cs.IR","submitted_at":"2026-04-23T05:44:26+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"WPGRec is a new sequential recommender that performs multi-scale temporal modeling via stationary wavelet packets and injects high-order collaborative information through scale-aligned graph propagation with energy-aware gated fusion.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.06928","ref_index":4,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Leveraging LLMs and Heterogeneous Knowledge Graphs for Persona-Driven Session-Based Recommendation","primary_cat":"cs.IR","submitted_at":"2026-04-08T10:40:30+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A persona-driven SBRS framework learns unsupervised user personas from an LLM-initialized heterogeneous KG and incorporates them into data-driven sequential recommenders, reporting consistent gains over session-history baselines on Amazon Books and Movies & TV.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.19793","ref_index":14,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"SkillGraph: Graph Foundation Priors for LLM Agent Tool Sequence Recommendation","primary_cat":"cs.AI","submitted_at":"2026-04-07T09:43:52+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"SkillGraph builds a reusable execution-transition graph prior from LLM trajectories and applies it via hybrid retrieval plus learned reranking to raise tool-sequence quality on ToolBench and API-Bank benchmarks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.02833","ref_index":27,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"BIPCL: Bilateral Intent-Enhanced Sequential Recommendation via Embedding Perturbation Contrastive Learning","primary_cat":"cs.IR","submitted_at":"2026-04-03T07:55:04+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"BIPCL improves sequential recommendation accuracy by bilaterally injecting collective intent prototypes into representations and enforcing contrastive alignment via bounded embedding perturbations.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"[26] Nian Li, Xin Ban, Cheng Ling, Chen Gao, Lantao Hu, Peng Jiang, Kun Gai, Yong Li, and Qingmin Liao. 2024. Modeling User Fatigue for Sequential Recommendation. InProceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR '24). Association for Computing Machinery, New York, NY, USA, 996-1005. doi:10.1145/3626772.3657802 [27] Sitao Lin, Shuai Tang, Xiaofeng Zhang, Jianghong Ma, and Ziao Wang. 2026. CoDeR+: Interest-aware Counterfactual Reasoning for Sequential Recommenda- tion.ACM Trans. Inf. Syst.44, 2 (2026), 1-39. doi:10.1145/3778863 [28] Xiaolin Lin, Weike Pan, and Zhong Ming. 2025. Towards Interest Drift-driven User Representation Learning in Sequential Recommendation."}],"limit":50,"offset":0}