PPaperPicks

Jingbo Shang

University of California, San Diego, Department of Computer Science and Engineering, CA, USA

52 papers at tracked venues · 32 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. Bidirectional LMs are Better Knowledge Memorizers? A Benchmark for Real-world Knowledge Injection
  2. Deriving Character Logic from Storyline as Codified Decision Trees
  3. PersonaAgent: Bridging Memory and Action for Personalized LLM Agents
  4. SceneAlign: Aligning Multimodal Reasoning to Scene Graphs in Complex Visual Scenes
  5. ALERT: An LLM-powered Benchmark for Automatic Evaluation of Recommendation Explanations
  6. Can Language Models Follow Multiple Turns of Entangled Instructions?
  7. CoMMIT: Coordinated Multimodal Instruction Tuning
  8. Codifying Character Logic in Role-Playing
  9. Correlation and Navigation in the Vocabulary Key Representation Space of Language Models
  10. Cuckoo: An IE Free Rider Hatched by Massive Nutrition in LLM's Nest
  11. Direct Prompt Optimization with Continuous Representations
  12. Entangled Relations: Leveraging NLI and Meta-analysis to Enhance Biomedical Relation Extraction
  13. Explainable Chain-of-Thought Reasoning: An Empirical Analysis on State-Aware Reasoning Dynamics
  14. LiveCodeBench Pro: How Do Olympiad Medalists Judge LLMs in Competitive Programming?
  15. Mitigating Visual Knowledge Forgetting in MLLM Instruction-tuning via Modality-decoupled Gradient Descent
  16. Mixture of Inputs: Text Generation Beyond Discrete Token Sampling
  17. OCEAN: Offline Chain-of-thought Evaluation and Alignment in Large Language Models
  18. Self-Taught Agentic Long Context Understanding
  19. Speculative RAG: Enhancing Retrieval Augmented Generation through Drafting
  20. The Price of Format: Diversity Collapse in LLMs
  21. Toward Multi-Session Personalized Conversation: A Large-Scale Dataset and Hierarchical Tree Framework for Implicit Reasoning
  22. Train a Unified Multimodal Data Quality Classifier with Synthetic Data
  23. Training Language Models to Generate Quality Code with Program Analysis Feedback
  24. ULTRABENCH: Benchmarking LLMs under Extreme Fine-grained Text Generation
  25. Vector-ICL: In-context Learning with Continuous Vector Representations
  26. VeriLocc: End-to-End Cross-Architecture Register Allocation via LLM
  27. ZeroHAR: Sensor Context Augments Zero-Shot Wearable Action Recognition
  28. Answer is All You Need: Instruction-following Text Embedding via Answering the Question
  29. Beyond Scaling: Predicting Patent Approval with Domain-specific Fine-grained Claim Dependency Graph
  30. Can LLMs Learn from Previous Mistakes? Investigating LLMs' Errors to Boost for Reasoning
  31. Chain-of-Table: Evolving Tables in the Reasoning Chain for Table Understanding
  32. Controllable Data Augmentation for Few-Shot Text Mining with Chain-of-Thought Attribute Manipulation
  33. DOCMASTER: A Unified Platform for Annotation, Training, & Inference in Document Question-Answering
  34. Data Contamination Can Cross Language Barriers
  35. Debug like a Human: A Large Language Model Debugger via Verifying Runtime Execution Step by Step
  36. Evaluating the Smooth Control of Attribute Intensity in Text Generation with LLMs
  37. Fast-ELECTRA for Efficient Pre-training
  38. How Few Davids Improve One Goliath: Federated Learning in Resource-Skewed Edge Computing Environments
  39. Incubating Text Classifiers Following User Instruction with Nothing but LLM
  40. Large Language Models for Time Series: A Survey
  41. Learn from Failure: Fine-tuning LLMs with Trial-and-Error Data for Intuitionistic Propositional Logic Proving
  42. MEMORYLLM: Towards Self-Updatable Large Language Models
  43. Multi-step Problem Solving Through a Verifier: An Empirical Analysis on Model-induced Process Supervision
  44. Open-world Multi-label Text Classification with Extremely Weak Supervision
  45. Quantifying and Optimizing Global Faithfulness in Persona-driven Role-playing
  46. READ: Improving Relation Extraction from an ADversarial Perspective
  47. Smaller Language Models are capable of selecting Instruction-Tuning Training Data for Larger Language Models
  48. Stronger, Lighter, Better: Towards Life-Long Attribute Value Extraction for E-Commerce Products
  49. TOOLVERIFIER: Generalization to New Tools via Self-Verification
  50. Text Grafting: Near-Distribution Weak Supervision for Minority Classes in Text Classification
  51. Toward Student-oriented Teacher Network Training for Knowledge Distillation
  52. UniMTS: Unified Pre-training for Motion Time Series