PPaperPicks

Tong Yu

Adobe Research, San Jose, CA, USA

53 papers at tracked venues · 27 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. A Survey on LLM-based Conversational User Simulation
  2. Building, Serving, and Growing a Conversational AI Assistant for Enterprise
  3. CachePrune: Teaching LLMs What Not to Follow via KV-Cache Editing
  4. DrunkAgent: Stealthy Memory Corruption in LLM-Powered Recommender Agents
  5. Dual Conditional Diffusion for Sequential Recommendation
  6. Multi-Agent Collaborative Filtering: Orchestrating Users and Items for Agentic Recommendations
  7. Skill Discovery for Software Scripting Automation via Offline Simulations with LLMs
  8. VipAct: Visual-Perception Enhancement via Specialized VLM Agent Collaboration and Tool-use
  9. A Tutorial on Agentic LLM for Recommender Systems
  10. ARTIST: Improving the Generation of Text-Rich Images with Disentangled Diffusion Models and Large Language Models
  11. Adaptive Offline Data Replay in Offline-to-Online Reinforcement Learning
  12. Augment before You Try: Knowledge-Enhanced Table Question Answering via Table Expansion
  13. Cache-Craft: Managing Chunk-Caches for Efficient Retrieval-Augmented Generation
  14. Causal Discovery-Driven Change Point Detection in Time Series
  15. CoMMIT: Coordinated Multimodal Instruction Tuning
  16. Diffusion Policies for Risk-Averse Behavior Modeling in Offline Reinforcement Learning
  17. Diversify-verify-adapt: Efficient and Robust Retrieval-Augmented Ambiguous Question Answering
  18. Doc-React: Multi-page Heterogeneous Document Question-answering
  19. Explainable Chain-of-Thought Reasoning: An Empirical Analysis on State-Aware Reasoning Dynamics
  20. Federated In-Context Learning: Iterative Refinement for Improved Answer Quality
  21. From Selection to Generation: A Survey of LLM-based Active Learning
  22. Fully Dynamic Embedding into ℓp Spaces
  23. GUI Agents: A Survey
  24. Image Difference Captioning via Adversarial Preference Optimization
  25. Interactive Visualization Recommendation with Hier-SUCB
  26. Knowledge-Aware Query Expansion with Large Language Models for Textual and Relational Retrieval
  27. LaMP-Cap: Personalized Figure Caption Generation With Multimodal Figure Profiles
  28. Large Language Models and Causal Inference in Collaboration: A Comprehensive Survey
  29. Listwise Preference Diffusion Optimization for User Behavior Trajectories Prediction
  30. Mitigating Visual Knowledge Forgetting in MLLM Instruction-tuning via Modality-decoupled Gradient Descent
  31. Numerical Pruning for Efficient Autoregressive Models
  32. OCEAN: Offline Chain-of-thought Evaluation and Alignment in Large Language Models
  33. Offline-to-Online Reinforcement Learning with Classifier-Free Diffusion Generation
  34. Personalizing Data Delivery: Investigating User Characteristics and Enhancing LLM Predictions
  35. SAND: Boosting LLM Agents with Self-Taught Action Deliberation
  36. SV-RAG: LoRA-Contextualizing Adaptation of MLLMs for Long Document Understanding
  37. Self-Debiasing Large Language Models: Zero-Shot Recognition and Reduction of Stereotypes
  38. Weakly-supervised VLM-guided Partial Contrastive Learning for Visual Language Navigation
  39. Advancing Vision-Language Models with Adapter Ensemble Strategies
  40. Aligning as Debiasing: Causality-Aware Alignment via Reinforcement Learning with Interventional Feedback
  41. Calibrating Reasoning in Language Models with Internal Consistency
  42. CoRAL: Collaborative Retrieval-Augmented Large Language Models Improve Long-tail Recommendation
  43. DeCoT: Debiasing Chain-of-Thought for Knowledge-Intensive Tasks in Large Language Models via Causal Intervention
  44. Editing Partially Observable Networks via Graph Diffusion Models
  45. Hallucination Diversity-Aware Active Learning for Text Summarization
  46. Interact with the Explanations: Causal Debiased Explainable Recommendation System
  47. Personalized Federated Learning for Text Classification with Gradient-Free Prompt Tuning
  48. SciCapenter: Supporting Caption Composition for Scientific Figures with Machine-Generated Captions and Ratings
  49. Self-Cleaning: Improving a Named Entity Recognizer Trained on Noisy Data with a Few Clean Instances
  50. Tackling Long-Tail Entities for Temporal Knowledge Graph Completion
  51. The Closeness of In-Context Learning and Weight Shifting for Softmax Regression
  52. ToolChain*: Efficient Action Space Navigation in Large Language Models with A* Search
  53. Which LLM to Play? Convergence-Aware Online Model Selection with Time-Increasing Bandits