PPaperPicks

Yao Hu

Xiaohongshu Inc., Beijing, China

69 papers at tracked venues · 54 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. A Creator-Aware Recommendation System for Content Platforms
  2. Anti-Length Shift: Dynamic Outlier Truncation for Training Efficient Reasoning Models
  3. Building and Benchmarking Large Language Models for Machine Translation in Social Network Services
  4. CCD-Level and Load-Aware Thread Orchestration for in-Memory Vector ANNS on Multi-Core CPUs
  5. Causality Enhancement for Cross-Domain Recommendation
  6. CrossVid: A Comprehensive Benchmark for Evaluating Cross-Video Reasoning in Multimodal Large Language Models
  7. HyMiRec: A Hybrid Multi-interest Learning Framework for LLM-based Sequential Recommendation
  8. LLM-Powered Benchmark Factory: Reliable, Generic, and Efficient
  9. Optimizing Generative Ranking Relevance via Reinforcement Learning in Xiaohongshu Search
  10. RedGR: Unified Generative Retrieval for Recommendation in REDnote
  11. Robust Tool Use via Fission-GRPO: Learning to Recover from Execution Errors
  12. R³A: Reinforced Reasoning for Relevance Assessment for RAG in User-Generated Content Platforms
  13. SPARD: Self-Paced Curriculum for RL Alignment via Integrating Reward Dynamics and Data Utility
  14. TimeMM: Time-as-Operator Spectral Filtering for Dynamic Multimodal Recommendation
  15. A Sanity Check for AI-generated Image Detection
  16. Beyond One-Size-Fits-All: Tailored Benchmarks for Efficient Evaluation
  17. CQ-DINO: Mitigating Gradient Dilution via Category Queries for Vast Vocabulary Object Detection
  18. CogLM: Tracking Cognitive Development of Large Language Models
  19. DecEx-RAG: Boosting Agentic Retrieval-Augmented Generation with Decision and Execution Optimization via Process Supervision
  20. DynaPrompt: Dynamic Test-Time Prompt Tuning
  21. DynamicFace: High-Quality and Consistent Face Swapping for Image and Video Using Composable 3D Facial Priors
  22. EcoLANG: Efficient and Effective Agent Communication Language Induction for Social Simulation
  23. Every Rollout Counts: Optimal Resource Allocation for Efficient Test-Time Scaling
  24. From Sub-Ability Diagnosis to Human-Aligned Generation: Bridging the Gap for Text Length Control via MarkerGen
  25. Improving Synthetic Image Detection Towards Generalization: An Image Transformation Perspective
  26. InsBank: Evolving Instruction Subset for Ongoing Alignment
  27. InstanceAssemble: Layout-Aware Image Generation via Instance Assembling Attention
  28. LamRA: Large Multimodal Model as Your Advanced Retrieval Assistant
  29. Make Every Penny Count: Difficulty-Adaptive Self-Consistency for Cost-Efficient Reasoning
  30. Mind the Quote: Enabling Quotation-Aware Dialogue in LLMs via Plug-and-Play Modules
  31. MoDification: Mixture of Depths Made Easy
  32. Multi-Granularity Distribution Modeling for Video Watch Time Prediction via Exponential-Gaussian Mixture Network
  33. NoteLLM-2: Multimodal Large Representation Models for Recommendation
  34. Object-Centric Video Question Answering with Visual Grounding and Referring
  35. PaRT: Enhancing Proactive Social Chatbots with Personalized Real-Time Retrieval
  36. Qilin: A Multimodal Information Retrieval Dataset with APP-level User Sessions
  37. RAG-IGBench: Innovative Evaluation for RAG-based Interleaved Generation in Open-domain Question Answering
  38. RealBench: A Chinese Multi-image Understanding Benchmark Close to Real-world Scenarios
  39. Revisiting Self-Consistency from Dynamic Distributional Alignment Perspective on Answer Aggregation
  40. SNS-Bench: Defining, Building, and Assessing Capabilities of Large Language Models in Social Networking Services
  41. Scalable Overload-Aware Graph-Based Index Construction for 10-Billion-Scale Vector Similarity Search
  42. SelfAug: Mitigating Catastrophic Forgetting in Retrieval-Augmented Generation via Distribution Self-Alignment
  43. SelfRACG: Enabling LLMs to Self-Express and Retrieve for Code Generation
  44. Silencer: From Discovery to Mitigation of Self-Bias in LLM-as-Benchmark-Generator
  45. Single Trajectory Distillation for Accelerating Image and Video Style Transfer
  46. Speculative Decoding for Multi-Sample Inference
  47. Think-Search-Patch: A Retrieval-Augmented Reasoning Framework for Repository-Level Code Repair
  48. Towards the Law of Capacity Gap in Distilling Language Models
  49. UniCBE: An Uniformity-driven Comparing Based Evaluation Framework with Unified Multi-Objective Optimization
  50. VLRMBench: A Comprehensive and Challenging Benchmark for Vision-Language Reward Models
  51. Wide-Horizon Thinking and Simulation-Based Evaluation for Real-World LLM Planning with Multifaceted Constraints
  52. iPET: An Interactive Emotional Companion Dialogue System with LLM-Powered Virtual Pet World Simulation
  53. AQ-DETR: Low-Bit Quantized Detection Transformer with Auxiliary Queries
  54. BatchEval: Towards Human-like Text Evaluation
  55. Bi-Level User Modeling for Deep Recommenders
  56. Controllable Mind Visual Diffusion Model
  57. Efficient Stochastic Approximation of Minimax Excess Risk Optimization
  58. Focused Large Language Models are Stable Many-Shot Learners
  59. Instruction Embedding: Latent Representations of Instructions Towards Task Identification
  60. Integrate the Essence and Eliminate the Dross: Fine-Grained Self-Consistency for Free-Form Language Generation
  61. NoteLLM: A Retrievable Large Language Model for Note Recommendation
  62. Poor-Supervised Evaluation for SuperLLM via Mutual Consistency
  63. PyramidInfer: Pyramid KV Cache Compression for High-throughput LLM Inference
  64. SSR-Encoder: Encoding Selective Subject Representation for Subject-Driven Generation
  65. Small-loss Adaptive Regret for Online Convex Optimization
  66. VISA: Reasoning Video Object Segmentation via Large Language Models
  67. VideoLLM-MoD: Efficient Video-Language Streaming with Mixture-of-Depths Vision Computation
  68. Vript: A Video Is Worth Thousands of Words
  69. ZONE: Zero-Shot Instruction-Guided Local Editing