PPaperPicks

Caiming Xiong

74 papers at tracked venues · 50 at CORE A* · active 2024–2026

DBLP profile ↗ORCID search ↗

Venues

ICLR ×14EMNLP ×12ACL ×11NeurIPS ×10NAACL ×8ICML ×6CVPR ×4ECCV ×3ICCV ×3AAAI ×1ICRA ×1UIST ×1

Frequent coauthors

Yiheng Xu
DBLP profile ↗ORCID search ↗
×3
Kung-Hsiang Huang
DBLP profile ↗ORCID search ↗
×3
Artemis Panagopoulou
DBLP profile ↗ORCID search ↗
×3
Jianguo Zhang
DBLP profile ↗ORCID search ↗
×2
Le Xue
DBLP profile ↗ORCID search ↗
×2
Prafulla Kumar Choubey
DBLP profile ↗ORCID search ↗
×2
Zhiwei Liu
DBLP profile ↗ORCID search ↗
×2
Xiangyu Peng
DBLP profile ↗ORCID search ↗
×2
Tianbao Xie
DBLP profile ↗ORCID search ↗
×2
Philippe Laban
DBLP profile ↗ORCID search ↗
×2
Simeng Han
DBLP profile ↗ORCID search ↗
×2
Zhiyuan Hu
DBLP profile ↗ORCID search ↗
×1

Papers

  1. Beyond 'Aha!': Toward Systematic Meta-Abilities Alignment in Large Reasoning Models
    ACL 2026 ·
    Zhiyuan Hu
    DBLP profile ↗ORCID search ↗
  2. From Passive Metric to Active Signal: The Evolving Role of Uncertainty Quantification in Large Language Models
    ACL 2026 ·
    Jiaxin Zhang
    DBLP profile ↗ORCID search ↗
  3. Hard2Verify: A Step-Level Verification Benchmark for Open-Ended Frontier Math
    ACL 2026 ·
    Shrey Pandit
    DBLP profile ↗ORCID search ↗
  4. J4R: Learning to Judge with Equivalent Initial State Group Relative Policy Optimization
    ACL 2026 ·
    Austin Xu
    DBLP profile ↗ORCID search ↗
  5. APIGen-MT: Agentic Pipeline for Multi-Turn Data Generation via Simulated Agent-Human Interplay
    NeurIPS 2025 ·
    Akshara Prabhakar
    DBLP profile ↗ORCID search ↗
  6. ActionStudio: A Lightweight Framework for Data and Training of Large Action Models
    EMNLP 2025 ·
    Jianguo Zhang
    DBLP profile ↗ORCID search ↗
  7. AgentTrek: Agent Trajectory Synthesis via Guiding Replay with Web Tutorials
    ICLR 2025 ·
    Yiheng Xu
    DBLP profile ↗ORCID search ↗
  8. Aguvis: Unified Pure Vision Agents for Autonomous GUI Interaction
    ICML 2025 ·
    Yiheng Xu
    DBLP profile ↗ORCID search ↗
  9. Automatic Curriculum Expert Iteration for Reliable LLM Reasoning
    ICLR 2025 ·
    Zirui Zhao
    DBLP profile ↗ORCID search ↗
  10. BLIP-3: A Family of Open Large Multimodal Models
    ICCV 2025 ·
    Le Xue
    DBLP profile ↗ORCID search ↗
  11. Benchmarking Deep Search over Heterogeneous Enterprise Data
    EMNLP 2025 ·
    Prafulla Kumar Choubey
    DBLP profile ↗ORCID search ↗
  12. Beyond Accuracy: Dissecting Mathematical Reasoning for LLMs Under Reinforcement Learning
    NeurIPS 2025 ·
    Jiayu Wang
    DBLP profile ↗ORCID search ↗
  13. BingoGuard: LLM Content Moderation Tools with Risk Levels
    ICLR 2025 ·
    Fan Yin
    DBLP profile ↗ORCID search ↗
  14. CRMArena: Understanding the Capacity of LLM Agents to Perform Professional CRM Tasks in Realistic Environments
    NAACL 2025 ·
    Kung-Hsiang Huang
    DBLP profile ↗ORCID search ↗
  15. CodeTree: Agent-guided Tree Search for Code Generation with Large Language Models
    NAACL 2025 ·
    Jierui Li
    DBLP profile ↗ORCID search ↗
  16. Contra4: Evaluating Contrastive Cross-Modal Reasoning in Audio, Video, Image, and 3D
    EMNLP 2025 ·
    Artemis Panagopoulou
    DBLP profile ↗ORCID search ↗
  17. Demystifying Domain-adaptive Post-training for Financial LLMs
    EMNLP 2025 ·
    Zixuan Ke
    DBLP profile ↗ORCID search ↗
  18. Direct Judgement Preference Optimization
    EMNLP 2025 ·
    Peifeng Wang
    DBLP profile ↗ORCID search ↗
  19. Diversity Empowers Intelligence: Integrating Expertise of Software Engineering Agents
    ICLR 2025 ·
    Kexun Zhang
    DBLP profile ↗ORCID search ↗
  20. Do RAG Systems Cover What Matters? Evaluating and Optimizing Responses with Sub-Question Coverage
    NAACL 2025 ·
    Kaige Xie
    DBLP profile ↗ORCID search ↗
  21. DyMU: Dynamic Merging and Virtual Unmerging for Efficient Variable-Length VLMs
    NeurIPS 2025 ·
    Zhenhailong Wang
    DBLP profile ↗ORCID search ↗
  22. Evaluating Judges as Evaluators: The JETTS Benchmark of LLM-as-Judges as Test-Time Scaling Evaluators
    ICML 2025 ·
    Yilun Zhou
    DBLP profile ↗ORCID search ↗
  23. FaithEval: Can Your Language Model Stay Faithful to Context, Even If "The Moon is Made of Marshmallows"
    ICLR 2025 ·
    Yifei Ming
    DBLP profile ↗ORCID search ↗
  24. GReaTer: Gradients Over Reasoning Makes Smaller Language Models Strong Prompt Optimizers
    ICLR 2025 ·
    Sarkar Snigdha Sarathi Das
    DBLP profile ↗ORCID search ↗
  25. Generative Frame Sampler for Long Video Understanding
    ACL 2025 ·
    Linli Yao
    DBLP profile ↗ORCID search ↗
  26. LAM SIMULATOR: Advancing Data Generation for Large Action Model Training via Online Exploration and Trajectory Feedback
    ACL 2025 ·
    Thai Quoc Hoang
    DBLP profile ↗ORCID search ↗
  27. LATTE: Learning to Think with Vision Specialists
    EMNLP 2025 ·
    Zixian Ma
    DBLP profile ↗ORCID search ↗
  28. MCPEval: Automatic MCP-based Deep Evaluation for AI Agent Models
    EMNLP 2025 ·
    Zhiwei Liu
    DBLP profile ↗ORCID search ↗
  29. Moirai-MoE: Empowering Time Series Foundation Models with Sparse Mixture of Experts
    ICML 2025 ·
    Xu Liu
    DBLP profile ↗ORCID search ↗
  30. PersonaBench: Evaluating AI Models on Understanding Personal Information through Accessing (Synthetic) Private User Data
    ACL 2025 ·
    Juntao Tan
    DBLP profile ↗ORCID search ↗
  31. ReGenesis: LLMs can Grow into Reasoning Generalists via Self-Improvement
    ICLR 2025 ·
    Xiangyu Peng
    DBLP profile ↗ORCID search ↗
  32. Reward-Guided Speculative Decoding for Efficient LLM Reasoning
    ICML 2025 ·
    Baohao Liao
    DBLP profile ↗ORCID search ↗
  33. Scaling Computer-Use Grounding via User Interface Decomposition and Synthesis
    NeurIPS 2025 ·
    Tianbao Xie
    DBLP profile ↗ORCID search ↗
  34. SiReRAG: Indexing Similar and Related Information for Multihop Reasoning
    ICLR 2025 ·
    Nan Zhang
    DBLP profile ↗ORCID search ↗
  35. SlackAgents: Scalable Collaboration of AI Agents in Workspaces
    EMNLP 2025 ·
    Zhiwei Liu
    DBLP profile ↗ORCID search ↗
  36. Spider 2.0: Evaluating Language Models on Real-World Enterprise Text-to-SQL Workflows
    ICLR 2025 ·
    Fangyu Lei
    DBLP profile ↗ORCID search ↗
  37. Strefer: Empowering Video LLMs with Space-Time Referring and Reasoning via Synthetic Instruction Data
    ICCV 2025 ·
    Honglu Zhou
    DBLP profile ↗ORCID search ↗
  38. Text2Data: Low-Resource Data Generation with Textual Control
    AAAI 2025 ·
    Shiyu Wang
    DBLP profile ↗ORCID search ↗
  39. ThinK: Thinner Key Cache by Query-Driven Pruning
    ICLR 2025 ·
    Yuhui Xu
    DBLP profile ↗ORCID search ↗
  40. Trust but Verify: Programmatic VLM Evaluation in the Wild
    ICCV 2025 ·
    Viraj Prabhu
    DBLP profile ↗ORCID search ↗
  41. Turning Conversations into Workflows: A Framework to Extract and Evaluate Dialog Workflows for Service AI Agents
    ACL 2025 ·
    Prafulla Kumar Choubey
    DBLP profile ↗ORCID search ↗
  42. Unanswerability Evaluation for Retrieval Augmented Generation
    ACL 2025 ·
    Xiangyu Peng
    DBLP profile ↗ORCID search ↗
  43. ViUniT: Visual Unit Tests for More Robust Visual Programming
    CVPR 2025 ·
    Artemis Panagopoulou
    DBLP profile ↗ORCID search ↗
  44. Why Vision Language Models Struggle with Visual Arithmetic? Towards Enhanced Chart and Geometry Understanding
    ACL 2025 ·
    Kung-Hsiang Huang
    DBLP profile ↗ORCID search ↗
  45. xLAM: A Family of Large Action Models to Empower AI Agent Systems
    NAACL 2025 ·
    Jianguo Zhang
    DBLP profile ↗ORCID search ↗
  46. APIGen: Automated PIpeline for Generating Verifiable and Diverse Function-Calling Datasets
    NeurIPS 2024 ·
    Zuxin Liu
    DBLP profile ↗ORCID search ↗
  47. ARM: Alignment with Residual Energy-Based Model
    NAACL 2024 ·
    Bo Pang
    DBLP profile ↗ORCID search ↗
  48. Beyond the Chat: Executable and Verifiable Text-Editing with LLMs
    UIST 2024 ·
    Philippe Laban
    DBLP profile ↗ORCID search ↗
  49. Consent in Crisis: The Rapid Decline of the AI Data Commons
    NeurIPS 2024 ·
    Shayne Longpre
    DBLP profile ↗ORCID search ↗
  50. Diffusion Model Alignment Using Direct Preference Optimization
    CVPR 2024 ·
    Bram Wallace
    DBLP profile ↗ORCID search ↗
  51. Embrace Divergence for Richer Insights: A Multi-document Summarization Benchmark and a Case Study on Summarizing Diverse Information from News Articles
    NAACL 2024 ·
    Kung-Hsiang Huang
    DBLP profile ↗ORCID search ↗
  52. FOFO: A Benchmark to Evaluate LLMs' Format-Following Capability
    ACL 2024 ·
    Congying Xia
    DBLP profile ↗ORCID search ↗
  53. FOLIO: Natural Language Reasoning with First-Order Logic
    EMNLP 2024 ·
    Simeng Han
    DBLP profile ↗ORCID search ↗
  54. Fair Abstractive Summarization of Diverse Perspectives
    NAACL 2024 ·
    Yusen Zhang
    DBLP profile ↗ORCID search ↗
  55. HIVE: Harnessing Human Feedback for Instructional Visual Editing
    CVPR 2024 ·
    Shu Zhang
    DBLP profile ↗ORCID search ↗
  56. Hierarchical Point Attention for Indoor 3D Object Detection
    ICRA 2024 ·
    Manli Shu
    DBLP profile ↗ORCID search ↗
  57. How Do Transformers Learn In-Context Beyond Simple Functions? A Case Study on Learning with Representations
    ICLR 2024 ·
    Tianyu Guo
    DBLP profile ↗ORCID search ↗
  58. INDICT: Code Generation with Internal Dialogues of Critiques for Both Security and Helpfulness
    NeurIPS 2024 ·
    Hung Le
    DBLP profile ↗ORCID search ↗
  59. LayoutDETR: Detection Transformer Is a Good Multimodal Layout Designer
    ECCV 2024 ·
    Ning Yu
    DBLP profile ↗ORCID search ↗
  60. Lemur: Harmonizing Natural Language and Code for Language Agents
    ICLR 2024 ·
    Yiheng Xu
    DBLP profile ↗ORCID search ↗
  61. MINT-1T: Scaling Open-Source Multimodal Data by 10x: A Multimodal Dataset with One Trillion Tokens
    NeurIPS 2024 ·
    Anas Awadalla
    DBLP profile ↗ORCID search ↗
  62. OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
    NeurIPS 2024 ·
    Tianbao Xie
    DBLP profile ↗ORCID search ↗
  63. P-FOLIO: Evaluating and Improving Logical Reasoning with Abundant Human-Written Reasoning Chains
    EMNLP 2024 ·
    Simeng Han
    DBLP profile ↗ORCID search ↗
  64. Position: TrustLLM: Trustworthiness in Large Language Models
    ICML 2024 ·
    Yue Huang
    DBLP profile ↗ORCID search ↗
  65. Retroformer: Retrospective Large Language Agents with Policy Gradient Optimization
    ICLR 2024 ·
    Weiran Yao
    DBLP profile ↗ORCID search ↗
  66. Sample-Efficient Learning of POMDPs with Multiple Observations In Hindsight
    ICLR 2024 ·
    Jiacheng Guo
    DBLP profile ↗ORCID search ↗
  67. Spider2-V: How Far Are Multimodal Agents From Automating Data Science and Engineering Workflows?
    NeurIPS 2024 ·
    Ruisheng Cao
    DBLP profile ↗ORCID search ↗
  68. Summary of a Haystack: A Challenge to Long-Context LLMs and RAG Systems
    EMNLP 2024 ·
    Philippe Laban
    DBLP profile ↗ORCID search ↗
  69. ULIP-2: Towards Scalable Multimodal Pre-Training for 3D Understanding
    CVPR 2024 ·
    Le Xue
    DBLP profile ↗ORCID search ↗
  70. Unified Training of Universal Time Series Forecasting Transformers
    ICML 2024 ·
    Gerald Woo
    DBLP profile ↗ORCID search ↗
  71. Unlocking Anticipatory Text Generation: A Constrained Approach for Large Language Models Decoding
    EMNLP 2024 ·
    Lifu Tu
    DBLP profile ↗ORCID search ↗
  72. What Are We Measuring When We Evaluate Large Vision-Language Models? An Analysis of Latent Factors and Biases
    NAACL 2024 ·
    Anthony Meng Huat Tiong
    DBLP profile ↗ORCID search ↗
  73. X-InstructBLIP: A Framework for Aligning Image, 3D, Audio, Video to LLMs and its Emergent Cross-Modal Reasoning
    ECCV 2024 ·
    Artemis Panagopoulou
    DBLP profile ↗ORCID search ↗
  74. xGen-VideoSyn-1: High-Fidelity Text-to-Video Synthesis with Compressed Representations
    ECCV 2024 ·
    Can Qin
    DBLP profile ↗ORCID search ↗