PPaperPicks

Zilong Zheng

33 papers at tracked venues · 23 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. MMUIE: Massive Multi-Domain Universal Information Extraction for Long Documents
  2. NarrativeLoom: Enhancing Creative Storytelling through Multi-Persona Collaborative Improvisation
  3. v-HUB: A Benchmark for Video Humor Understanding from Vision and Sound
  4. Absolute Zero: Reinforced Self-play Reasoning with Zero Data
  5. Adaptive Preference Optimization with Uncertainty-aware Utility Anchor
  6. Amulet: ReAlignment During Test Time for Personalized Preference Adaptation of LLMs
  7. Are the Values of LLMs Structurally Aligned with Humans? A Causal Perspective
  8. DiveR-CT: Diversity-enhanced Red Teaming Large Language Model Assistants with Relaxing Constraints
  9. Evaluating Generalization Capabilities of LLM-Based Agents in Mixed-Motive Scenarios Using Concordia
  10. How to Synthesize Text Data without Model Collapse?
  11. In-Context Editing: Learning Knowledge from Self-Induced Distributions
  12. In-situ Value-aligned Human-Robot Interactions with Physical Constraints
  13. Look Both Ways and No Sink: Converting LLMs into Text Encoders without Training
  14. MCU: An Evaluation Framework for Open-Ended Game Agents
  15. MMKE-Bench: A Multimodal Editing Benchmark for Diverse Visual Knowledge
  16. Navi2Gaze: Leveraging Foundation Models for Navigation and Target Gazing
  17. OmniMMI: A Comprehensive Multi-modal Interaction Benchmark in Streaming Video Contexts
  18. ReflectEvo: Improving Meta Introspection of Small LLMs by Learning Self-Reflection
  19. Reinforced Query Reasoners for Reasoning-intensive Retrieval Tasks
  20. TokenSwift: Lossless Acceleration of Ultra Long Sequence Generation
  21. Understanding and Leveraging the Expert Specialization of Context Faithfulness in Mixture-of-Experts LLMs
  22. VideoLLaMB: Long Streaming Video Understanding with Recurrent Memory Bridges
  23. An Efficient Recipe for Long Context Extension via Middle-Focused Positional Encoding
  24. Boosting LLM Agents with Recursive Contemplation for Effective Deception Handling
  25. Combining Supervised Learning and Reinforcement Learning for Multi-Label Classification Tasks with Partial Labels
  26. Efficient Temporal Extrapolation of Multimodal Large Language Models with Temporal Grounding Bridge
  27. LangSuit·E: Planning, Controlling and Interacting with Large Language Models in Embodied Text Environments
  28. LooGLE: Can Long-Context Language Models Understand Long Contexts?
  29. Mars: Situated Inductive Reasoning in an Open-World Environment
  30. MathBench: Evaluating the Theory and Application Proficiency of LLMs with a Hierarchical Mathematics Benchmark
  31. MindAgent: Emergent Gaming Interaction
  32. Towards Better Chinese Spelling Check for Search Engines: A New Dataset and Strong Baseline
  33. Varying Sentence Representations via Condition-Specified Routers