PPaperPicks

Jun Zhou

Ant Financial Services Group, AI Department (Beijing), China

87 papers at tracked venues · 65 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. From Entity Reliability to Clean Feedback: An Entity-Aware Denoising Framework Beyond Interaction-Level Signals
  2. LLaDA 1.5: Variance-Reduced Preference Optimization for Large Language Diffusion Models
  3. Learning to Translate by Translating: Stabilizing the Dual Loop via Semantic-Aware Self-Evolution
  4. LookAhead Tuning: Safer Language Models via Partial Answer Previews
  5. RV-Syn: Rational and Verifiable Mathematical Reasoning Data Synthesis based on Structured Function Library
  6. ReportLogic: Evaluating Logical Quality in Deep Research Reports
  7. Rethinking Sample Polarity in Reinforcement Learning with Verifiable Rewards
  8. SepSeq: A Training-Free Framework for Long Numerical Sequence Processing in LLMs
  9. Taming the Long Tail: Efficient Item-wise Sharpness-Aware Minimization for LLM-based Recommender Systems
  10. Thinker: Training LLMs in Hierarchical Thinking for Deep Search via Multi-Turn Interaction
  11. Token-level Collaborative Alignment for LLM-based Generative Recommendation
  12. UniGeM: Unifying Data Selection and Mixing via Geometric Exploration and Mining
  13. ARGenSeg: Image Segmentation with Autoregressive Image Generation Model
  14. AntAkso: Claims Management System for Health Insurance in Alipay
  15. Arrows of Math Reasoning Data Synthesis for Large Language Models: Diversity, Complexity and Correctness
  16. BOSE: A Systematic Evaluation Method Optimized for Base Models
  17. Controllable Unlearning for Image-to-Image Generative Models via ϵ-Constrained Optimization
  18. Effective and Efficient Masked Image Generation Models
  19. Effectively PAIRing LLMs with Online Marketing via Progressive Prompting Augmentation
  20. Explore What LLM Does Not Know in Complex Question Answering
  21. Fine-Grained Zero-Shot Composed Image Retrieval with Complementary Visual-Semantic Integration
  22. Graph Disentangle Causal Model: Enhancing Causal Inference in Networked Observational Data
  23. IceBerg: Debiased Self-Training for Class-Imbalanced Node Classification
  24. KAG: Boosting LLMs in Professional Domains via Knowledge Augmented Generation
  25. LSSF: Safety Alignment for Large Language Models through Low-Rank Safety Subspace Fusion
  26. LaMP-Val: Large Language Models Empower Personalized Valuation in Auction
  27. Large Language Diffusion Models
  28. Learning Causal Transition Matrix for Instance-dependent Label Noise
  29. MAQInstruct: Instruction-based Unified Event Relation Extraction
  30. MASS: Mathematical Data Selection via Skill Graphs for Pretraining Large Language Models
  31. Mix Data or Merge Models? Balancing the Helpfulness, Honesty, and Harmlessness of Large Language Model via Model Merging
  32. NATRA: Noise-Agnostic Framework for Trajectory Prediction with Noisy Observations
  33. OneKE: A Dockerized Schema-Guided LLM Agent-based Knowledge Extraction System
  34. RED: Unleashing Token-Level Rewards from Holistic Feedback via Reward Redistribution
  35. Refining Sentence Embedding Model through Ranking Sentences Generation with Large Language Models
  36. Rethinking Causal Ranking: A Balanced Perspective on Uplift Model Evaluation
  37. Robust Preference Optimization via Dynamic Target Margins
  38. Stable Representation Learning on Graphs from Multiple Environments with Structure Distribution Shift
  39. SurvFormer: A Transformer Based Framework for Survival Analysis in Insurance Underwriting
  40. Understanding and Mitigating Overrefusal in LLMs from an Unveiling Perspective of Safety Decision Boundary
  41. Unlocking the Power of Function Vectors for Characterizing and Mitigating Catastrophic Forgetting in Continual Instruction Tuning
  42. A Merge Sort Based Ranking System for the Evaluation of Large Language Models
  43. Adaptively Denoising Graph Neural Networks for Knowledge Distillation
  44. Aligned Side Information Fusion Method for Sequential Recommendation
  45. An Active Masked Attention Framework for Many-to-Many Cross-Domain Recommendations
  46. AntDT: A Self-Adaptive Distributed Training Framework for Leader and Straggler Nodes
  47. Backdoor Adjustment via Group Adaptation for Debiased Coupon Recommendations
  48. Breaking the Length Barrier: LLM-Enhanced CTR Prediction in Long Textual User Behaviors
  49. Calibrating Graph Neural Networks from a Data-centric Perspective
  50. Can Small Language Models be Good Reasoners for Sequential Recommendation?
  51. Collaborative Refining for Learning from Inaccurate Labels
  52. Cost-Efficient Fraud Risk Optimization with Submodularity in Insurance Claim
  53. Counterfactual Data Augmentation for Debiased Coupon Recommendations Based on Potential Knowledge
  54. Domain Level Interpretability: Interpreting Black-box Model with Domain-specific Embedding
  55. EasyTPP: Towards Open Benchmarking Temporal Point Processes
  56. Efficient Model Stealing Defense with Noise Transition Matrix
  57. Enhancing Sequential Recommendation via LLM-based Semantic Embedding Learning
  58. Enhancing Sequential Recommenders with Augmented Knowledge from Aligned Large Language Models
  59. Exploring Multi-Scenario Multi-Modal CTR Prediction with a Large Scale Dataset
  60. Factor Model-Based Large Covariance Estimation from Streaming Data Using a Knowledge-Based Sketch Matrix
  61. GATS: Generative Audience Targeting System for Online Advertising
  62. GMP-AR: Granularity Message Passing and Adaptive Reconciliation for Temporal Hierarchy Forecasting
  63. Invariant Graph Learning for Causal Effect Estimation
  64. KGFabric: A Scalable Knowledge Graph Warehouse for Enterprise Data Interconnection
  65. Keypoint-based Progressive Chain-of-Thought Distillation for LLMs
  66. Knowledge-augmented Financial Market Analysis and Report Generation
  67. LASCA: A Large-Scale Stable Customer Segmentation Approach to Credit Risk Assessment
  68. LLMRG: Improving Recommendations through Large Language Model Reasoning Graphs
  69. Learning to Plan for Retrieval-Augmented Large Language Models from Knowledge Graphs
  70. Leave No One Behind: Online Self-Supervised Self-Distillation for Sequential Recommendation
  71. Lower Bounds of Uniform Stability in Gradient-Based Bilevel Algorithms for Hyperparameter Optimization
  72. MDGNN: Multi-Relational Dynamic Graph Neural Network for Comprehensive and Dynamic Stock Investment Prediction
  73. Multi-view Temporal Knowledge Graph Reasoning
  74. Multiscale Representation Enhanced Temporal Flow Fusion Model for Long-Term Workload Forecasting
  75. Not All Negatives Are Worth Attending to: Meta-Bootstrapping Negative Sampling Framework for Link Prediction
  76. OneEdit: A Neural-Symbolic Collaboratively Knowledge Editing System
  77. OneGen: Efficient One-Pass Unified Generation and Retrieval for LLMs
  78. OptScaler: A Collaborative Framework for Robust Autoscaling in the Cloud
  79. Optimizing Language Models with Fair and Stable Reward Composition in Reinforcement Learning
  80. PEACE: Prototype lEarning Augmented transferable framework for Cross-domain rEcommendation
  81. ReLand: Integrating Large Language Models' Insights into Industrial Recommenders via a Controllable Reasoning Pool
  82. Rethinking Memory and Communication Costs for Efficient Data Parallel Training of Large Language Models
  83. Self-cognitive Denoising in the Presence of Multiple Noisy Label Sources
  84. TEXT CAN BE FAIR: Mitigating Popularity Bias with PLMs by Learning Relative Preference
  85. TimeMixer: Decomposable Multiscale Mixing for Time Series Forecasting
  86. Unifying Bayesian Flow Networks and Diffusion Models through Stochastic Differential Equations
  87. π-Light: Programmatic Interpretable Reinforcement Learning for Resource-Limited Traffic Signal Control