PPaperPicks

Nanyun Peng

University of Southern California, Los Angeles, CA, USA

79 papers at tracked venues · 44 at CORE A* · active 2024–2026

DBLP profile ↗ORCID 0000-0002-8509-6595 ↗Homepage ↗

Venues

ACL ×21EMNLP ×21NAACL ×11NeurIPS ×9ICML ×6AAAI ×2ACM MM ×2ICLR ×2CVPR ×1EACL ×1ICCV ×1IUI ×1WACV ×1

Frequent coauthors

Tanmay Parekh
DBLP profile ↗ORCID search ↗
×5
Yufei Tian
DBLP profile ↗ORCID search ↗
×4
Wenbo Hu
DBLP profile ↗ORCID search ↗
×3
Haoyi Qiu
DBLP profile ↗ORCID search ↗
×3
Xueqing Wu
DBLP profile ↗ORCID search ↗
×3
Alexander Spangher
DBLP profile ↗ORCID search ↗
×3
Mingyu Derek Ma
DBLP profile ↗ORCID search ↗
×3
Jia-Chen Gu
DBLP profile ↗ORCID search ↗
×2
Pei-Fu Guo
DBLP profile ↗ORCID search ↗
×2
Hyeonjeong Ha
DBLP profile ↗ORCID search ↗
×2
Zhecheng Li
DBLP profile ↗ORCID search ↗
×2
Bingxuan Li
DBLP profile ↗ORCID search ↗
×2

Papers

  1. BRIEF-Pro: Universal Context Compression with Short-to-Long Synthesis for Fast and Accurate Multi-Hop Reasoning
    ACL 2026 ·
    Jia-Chen Gu
    DBLP profile ↗ORCID search ↗
  2. Beyond Facts- Benchmarking Distributional Reading Comprehension in Large Language Models
    ACL 2026 ·
    Pei-Fu Guo
    DBLP profile ↗ORCID search ↗
  3. CoLyricist: Enhancing Lyric Writing with AI through Workflow-Aligned Support
    IUI 2026 ·
    Masahiro Yoshida
    DBLP profile ↗ORCID search ↗
  4. Decoupling Task-Solving and Output Formatting in LLM Generation
    ACL 2026 ·
    Haikang Deng
    DBLP profile ↗ORCID search ↗
  5. LiveCLKTBench: Towards Reliable Evaluation of Cross-Lingual Knowledge Transfer in Multilingual LLMs
    ACL 2026 ·
    Pei-Fu Guo
    DBLP profile ↗ORCID search ↗
  6. MM-PoisonRAG: Disrupting Multimodal RAG with Local and Global Knowledge Poisoning Attacks
    ACL 2026 ·
    Hyeonjeong Ha
    DBLP profile ↗ORCID search ↗
  7. Rethinking Creativity Evaluation: A Critical Analysis of Existing Creativity Evaluations
    EACL 2026 ·
    Li-Chun Lu
    DBLP profile ↗ORCID search ↗
  8. 3DLLM-Mem: Long-Term Spatial-Temporal Memory for Embodied 3D Large Language Model
    NeurIPS 2025 ·
    Wenbo Hu
    DBLP profile ↗ORCID search ↗
  9. AI Debate Aids Assessment of Controversial Claims
    NeurIPS 2025 ·
    Salman Rahman
    DBLP profile ↗ORCID search ↗
  10. BRIEF: Bridging Retrieval and Inference for Multi-hop Reasoning via Compression
    NAACL 2025 ·
    Yuankai Li
    DBLP profile ↗ORCID search ↗
  11. CaKE: Circuit-aware Editing Enables Generalizable Knowledge Learners
    EMNLP 2025 ·
    Yunzhi Yao
    DBLP profile ↗ORCID search ↗
  12. Collapse of Dense Retrievers: Short, Early, and Literal Biases Outranking Factual Evidence
    ACL 2025 ·
    Mohsen Fayyaz
    DBLP profile ↗ORCID search ↗
  13. Comparing Bad Apples to Good Oranges Aligning Large Language Models via Joint Preference Optimization
    ACL 2025 ·
    Hritik Bansal
    DBLP profile ↗ORCID search ↗
  14. Contrastive Visual Data Augmentation
    ICML 2025 ·
    Yu Zhou
    DBLP profile ↗ORCID search ↗
  15. DRS: Deep Question Reformulation With Structured Output
    ACL 2025 ·
    Zhecheng Li
    DBLP profile ↗ORCID search ↗
  16. DiCoRe: Enhancing Zero-shot Event Detection via Divergent-Convergent LLM Reasoning
    EMNLP 2025 ·
    Tanmay Parekh
    DBLP profile ↗ORCID search ↗
  17. Evaluating Cultural and Social Awareness of LLM Web Agents
    NAACL 2025 ·
    Haoyi Qiu
    DBLP profile ↗ORCID search ↗
  18. FLAMES: Improving LLM Math Reasoning via a Fine-Grained Analysis of the Data Synthesis Pipeline
    EMNLP 2025 ·
    Parker Seegmiller
    DBLP profile ↗ORCID search ↗
  19. Guiding Through Complexity: What Makes Good Supervision for Hard Reasoning Tasks?
    NAACL 2025 ·
    Xuan He
    DBLP profile ↗ORCID search ↗
  20. How to Make Large Language Models Generate 100% Valid Molecules?
    EMNLP 2025 ·
    Wen Tao
    DBLP profile ↗ORCID search ↗
  21. Improving Faithfulness of Text-to-Image Diffusion Models through Inference Intervention
    WACV 2025 ·
    Danfeng Guo
    DBLP profile ↗ORCID search ↗
  22. METAL: A Multi-Agent Framework for Chart Generation with Test-Time Scaling
    ACL 2025 ·
    Bingxuan Li
    DBLP profile ↗ORCID search ↗
  23. MRAG-Bench: Vision-Centric Evaluation for Retrieval-Augmented Multimodal Models
    ICLR 2025 ·
    Wenbo Hu
    DBLP profile ↗ORCID search ↗
  24. Mind the Gesture: Evaluating AI Sensitivity to Culturally Offensive Non-Verbal Gestures
    ACL 2025 ·
    Akhila Yerukola
    DBLP profile ↗ORCID search ↗
  25. Model Extrapolation Expedites Alignment
    ACL 2025 ·
    Chujie Zheng
    DBLP profile ↗ORCID search ↗
  26. On the Loss of Context Awareness in General Instruction Fine-tuning
    NeurIPS 2025 ·
    Yihan Wang
    DBLP profile ↗ORCID search ↗
  27. OpenVLThinker: Complex Vision-Language Reasoning via Iterative SFT-RL Cycles
    NeurIPS 2025 ·
    Yihe Deng
    DBLP profile ↗ORCID search ↗
  28. PARTONOMY: Large Multimodal Models with Part-Level Visual Understanding
    NeurIPS 2025 ·
    Ansel Blume
    DBLP profile ↗ORCID search ↗
  29. REFFLY: Melody-Constrained Lyrics Editing Model
    NAACL 2025 ·
    Songyan Zhao
    DBLP profile ↗ORCID search ↗
  30. SNaRe: Domain-aware Data Generation for Low-Resource Event Detection
    EMNLP 2025 ·
    Tanmay Parekh
    DBLP profile ↗ORCID search ↗
  31. SYNTHIA: Novel Concept Design with Affordance Composition
    ACL 2025 ·
    Hyeonjeong Ha
    DBLP profile ↗ORCID search ↗
  32. Sandcastles in the Storm: Revisiting the (Im)possibility of Strong Watermarking
    ACL 2025 ·
    Fabrice Harel-Canada
    DBLP profile ↗ORCID search ↗
  33. Scaling Probabilistic Circuits via Monarch Matrices
    ICML 2025 ·
    Honghua Zhang
    DBLP profile ↗ORCID search ↗
  34. SkillVerse : Assessing and Enhancing LLMs with Tree Evaluation
    ACL 2025 ·
    Yufei Tian
    DBLP profile ↗ORCID search ↗
  35. VISCO: Benchmarking Fine-Grained Critique and Correction Towards Self-Improvement in Visual Reasoning
    CVPR 2025 ·
    Xueqing Wu
    DBLP profile ↗ORCID search ↗
  36. Verbalized Representation Learning for Interpretable Few-Shot Generalization
    ICCV 2025 ·
    Cheng-Fu Yang
    DBLP profile ↗ORCID search ↗
  37. Vulnerability of LLMs to Vertically Aligned Text Manipulations
    ACL 2025 ·
    Zhecheng Li
    DBLP profile ↗ORCID search ↗
  38. Vulnerability of Large Language Models to Output Prefix Jailbreaks: Impact of Positions on Safety
    NAACL 2025 ·
    Yiwei Wang
    DBLP profile ↗ORCID search ↗
  39. AMRFact: Enhancing Summarization Factuality Evaluation with AMR-Driven Negative Samples Generation
    NAACL 2024 ·
    Haoyi Qiu
    DBLP profile ↗ORCID search ↗
  40. Adaptable Logical Control for Large Language Models
    NeurIPS 2024 ·
    Honghua Zhang
    DBLP profile ↗ORCID search ↗
  41. Are Large Language Models Capable of Generating Human-Level Narratives?
    EMNLP 2024 ·
    Yufei Tian
    DBLP profile ↗ORCID search ↗
  42. Argument-Aware Approach To Event Linking
    ACL 2024 ·
    I-Hung Hsu
    DBLP profile ↗ORCID search ↗
  43. CaLM: Contrasting Large and Small Language Models to Verify Grounded Generation
    ACL 2024 ·
    I-Hung Hsu
    DBLP profile ↗ORCID search ↗
  44. ConTextual: Evaluating Context-Sensitive Text-Rich Visual Reasoning in Large Multimodal Models
    ICML 2024 ·
    Rohan Wadhawan
    DBLP profile ↗ORCID search ↗
  45. Contextual Label Projection for Cross-Lingual Structured Prediction
    NAACL 2024 ·
    Tanmay Parekh
    DBLP profile ↗ORCID search ↗
  46. Control Large Language Models via Divide and Conquer
    EMNLP 2024 ·
    Bingxuan Li
    DBLP profile ↗ORCID search ↗
  47. DACO: Towards Application-Driven and Comprehensive Data Analysis via Code Generation
    NeurIPS 2024 ·
    Xueqing Wu
    DBLP profile ↗ORCID search ↗
  48. Detecting Machine-Generated Long-Form Content with Latent-Space Variables
    EMNLP 2024 ·
    Yufei Tian
    DBLP profile ↗ORCID search ↗
  49. DiNADO: Norm-Disentangled Neurally-Decomposed Oracles for Controlling Language Models
    ICML 2024 ·
    Sidi Lu
    DBLP profile ↗ORCID search ↗
  50. Do LLMs Plan Like Human Writers? Comparing Journalist Coverage of Press Releases with LLMs
    EMNLP 2024 ·
    Alexander Spangher
    DBLP profile ↗ORCID search ↗
  51. Event Detection from Social Media for Epidemic Prediction
    NAACL 2024 ·
    Tanmay Parekh
    DBLP profile ↗ORCID search ↗
  52. Explaining Mixtures of Sources in News Articles
    EMNLP 2024 ·
    Alexander Spangher
    DBLP profile ↗ORCID search ↗
  53. Explaining and Improving Contrastive Decoding by Extrapolating the Probabilities of a Huge and Hypothetical LM
    EMNLP 2024 ·
    Haw-Shiuan Chang
    DBLP profile ↗ORCID search ↗
  54. Human-in-the-Loop Synthetic Text Data Inspection with Provenance Tracking
    NAACL 2024 ·
    Hong Jin Kang
    DBLP profile ↗ORCID search ↗
  55. Improving Event Definition Following For Zero-Shot Event Detection
    ACL 2024 ·
    Zefan Cai
    DBLP profile ↗ORCID search ↗
  56. LLM Self-Correction with DeCRIM: Decompose, Critique, and Refine for Enhanced Following of Instructions with Multiple Constraints
    EMNLP 2024 ·
    Thomas Palmeira Ferraz
    DBLP profile ↗ORCID search ↗
  57. LLM-A*: Large Language Model Enhanced Incremental Heuristic Search on Path Planning
    EMNLP 2024 ·
    Silin Meng
    DBLP profile ↗ORCID search ↗
  58. MIDDAG: Where Does Our News Go? Investigating Information Diffusion via Community-Level Information Pathways
    AAAI 2024 ·
    Mingyu Derek Ma
    DBLP profile ↗ORCID search ↗
  59. MIRACLE: An Online, Explainable Multimodal Interactive Concept Learning System
    ACM MM 2024 ·
    Ansel Blume
    DBLP profile ↗ORCID search ↗
  60. MacGyver: Are Large Language Models Creative Problem Solvers?
    NAACL 2024 ·
    Yufei Tian
    DBLP profile ↗ORCID search ↗
  61. Matryoshka Query Transformer for Large Vision-Language Models
    NeurIPS 2024 ·
    Wenbo Hu
    DBLP profile ↗ORCID search ↗
  62. Measuring Psychological Depth in Language Models
    EMNLP 2024 ·
    Fabrice Harel-Canada
    DBLP profile ↗ORCID search ↗
  63. Mitigating Bias for Question Answering Models by Tracking Bias Influence
    NAACL 2024 ·
    Mingyu Derek Ma
    DBLP profile ↗ORCID search ↗
  64. Model Editing Harms General Abilities of Large Language Models: Regularization to the Rescue
    EMNLP 2024 ·
    Jia-Chen Gu
    DBLP profile ↗ORCID search ↗
  65. New Job, New Gender? Measuring the Social Bias in Image Generation Models
    ACM MM 2024 ·
    Wenxuan Wang
    DBLP profile ↗ORCID search ↗
  66. On Prompt-Driven Safeguarding for Large Language Models
    ICML 2024 ·
    Chujie Zheng
    DBLP profile ↗ORCID search ↗
  67. Open-Domain Text Evaluation via Contrastive Distribution Methods
    ICML 2024 ·
    Sidi Lu
    DBLP profile ↗ORCID search ↗
  68. QUDSELECT: Selective Decoding for Questions Under Discussion Parsing
    EMNLP 2024 ·
    Ashima Suvarna
    DBLP profile ↗ORCID search ↗
  69. RLCD: Reinforcement Learning from Contrastive Distillation for LM Alignment
    ICLR 2024 ·
    Kevin Yang
    DBLP profile ↗ORCID search ↗
  70. Re-ReST: Reflection-Reinforced Self-Training for Language Agents
    EMNLP 2024 ·
    Zi-Yi Dou
    DBLP profile ↗ORCID search ↗
  71. SPEED++: A Multilingual Event Extraction Framework for Epidemic Prediction and Preparedness
    EMNLP 2024 ·
    Tanmay Parekh
    DBLP profile ↗ORCID search ↗
  72. STAR: Boosting Low-Resource Information Extraction by Structure-to-Text Data Generation with Large Language Models
    AAAI 2024 ·
    Mingyu Derek Ma
    DBLP profile ↗ORCID search ↗
  73. SafeWorld: Geo-Diverse Safety Alignment
    NeurIPS 2024 ·
    Da Yin
    DBLP profile ↗ORCID search ↗
  74. Synchronous Faithfulness Monitoring for Trustworthy Retrieval-Augmented Generation
    EMNLP 2024 ·
    Di Wu
    DBLP profile ↗ORCID search ↗
  75. TextEE: Benchmark, Reevaluation, Reflections, and Future Challenges in Event Extraction
    ACL 2024 ·
    Kuan-Hao Huang
    DBLP profile ↗ORCID search ↗
  76. Tracking the Newsworthiness of Public Documents
    ACL 2024 ·
    Alexander Spangher
    DBLP profile ↗ORCID search ↗
  77. Uncertainty Calibration for Tool-Using Language Agents
    EMNLP 2024 ·
    Hao Liu
    DBLP profile ↗ORCID search ↗
  78. VALOR-EVAL: Holistic Coverage and Faithfulness Evaluation of Large Vision-Language Models
    ACL 2024 ·
    Haoyi Qiu
    DBLP profile ↗ORCID search ↗
  79. VDebugger: Harnessing Execution Feedback for Debugging Visual Programs
    EMNLP 2024 ·
    Xueqing Wu
    DBLP profile ↗ORCID search ↗