PPaperPicks

Jun Wang

University College London, Department of Computer Science, UCL Centre for Artificial Intelligence, London, UK

56 papers at tracked venues · 42 at CORE A* · active 2024–2026

DBLP profile ↗ORCID 0000-0002-4021-4228 ↗Google Scholar ↗Homepage ↗

Venues

NeurIPS ×16ICLR ×9AAMAS ×6ICML ×5AAAI ×4EMNLP ×4ACL ×3SIGKDD ×2WWW ×2EACL ×1ECAI ×1ICRA ×1NAACL ×1SIGIR ×1

Frequent coauthors

Qirui Mi
DBLP profile ↗ORCID search ↗
×4
Jiarui Jin
DBLP profile ↗ORCID search ↗
×3
Zhiyu Zhao
DBLP profile ↗ORCID search ↗
×2
Siyuan Guo
DBLP profile ↗ORCID search ↗
×2
Ziyu Wan
DBLP profile ↗ORCID search ↗
×2
Luoyang Sun
DBLP profile ↗ORCID search ↗
×1
Ning Yang
DBLP profile ↗ORCID search ↗
×1
Yuchen Li
DBLP profile ↗ORCID search ↗
×1
Milan Gritta
DBLP profile ↗ORCID search ↗
×1
Feng Xiong
DBLP profile ↗ORCID search ↗
×1
Biao Wu
DBLP profile ↗ORCID search ↗
×1
Anjie Liu
DBLP profile ↗ORCID search ↗
×1

Papers

  1. Dual Activation-Weight Sparsity: A Training-Free Framework for Efficient Large Language Model Compression
    ACL 2026 ·
    Luoyang Sun
    DBLP profile ↗ORCID search ↗
  2. Proactive Constrained Policy Optimization with Preemptive Penalty
    AAAI 2026 ·
    Ning Yang
    DBLP profile ↗ORCID search ↗
  3. Probe-and-Fetch: Dynamic KV Cache Pruning for Accelerated Long-Context Inference in Web-Scale AI Search
    WWW 2026 ·
    Yuchen Li
    DBLP profile ↗ORCID search ↗
  4. Process Evaluation for Agentic Systems
    EACL 2026 ·
    Milan Gritta
    DBLP profile ↗ORCID search ↗
  5. Towards Unified Affective Reasoning via In-Context Reinforcement Learning
    SIGIR 2026 ·
    Feng Xiong
    DBLP profile ↗ORCID search ↗
  6. Vision-Language Reasoning for Geolocalization: A Reinforcement Learning Approach
    AAAI 2026 ·
    Biao Wu
    DBLP profile ↗ORCID search ↗
  7. A Principle of Targeted Intervention for Multi-Agent Reinforcement Learning
    NeurIPS 2025 ·
    Anjie Liu
    DBLP profile ↗ORCID search ↗
  8. Boost, Disentangle, and Customize: A Robust System2-to-System1 Pipeline for Code Generation
    ACL 2025 ·
    Kounianhua Du
    DBLP profile ↗ORCID search ↗
  9. CMoB: Modality Valuation via Causal Effect for Balanced Multimodal Learning
    NeurIPS 2025 · Jun Wang
  10. Causal Sufficiency and Necessity Improves Chain-of-Thought Reasoning
    NeurIPS 2025 ·
    Xiangning Yu
    DBLP profile ↗ORCID search ↗
  11. Circuit Transformer: A Transformer That Preserves Logical Equivalence
    ICLR 2025 ·
    Xihan Li
    DBLP profile ↗ORCID search ↗
  12. Constrain Alignment with Sparse Autoencoders
    ICML 2025 ·
    Qingyu Yin
    DBLP profile ↗ORCID search ↗
  13. Curious Causality-Seeking Agents in Open-ended Worlds
    NeurIPS 2025 ·
    Zhiyu Zhao
    DBLP profile ↗ORCID search ↗
  14. Direct Value Optimization: Improving Chain-of-Thought Reasoning in LLMs with Refined Values
    EMNLP 2025 ·
    Hongbo Zhang
    DBLP profile ↗ORCID search ↗
  15. DistRL: An Asynchronous Distributed Reinforcement Learning Framework for On-Device Control Agent
    ICLR 2025 ·
    Taiyi Wang
    DBLP profile ↗ORCID search ↗
  16. EconGym: A Scalable AI Testbed with Diverse Economic Tasks
    NeurIPS 2025 ·
    Qirui Mi
    DBLP profile ↗ORCID search ↗
  17. GenSim: A General Social Simulation Platform with Large Language Model based Agents
    NAACL 2025 ·
    Jiakai Tang
    DBLP profile ↗ORCID search ↗
  18. Human-inspired Episodic Memory for Infinite Context LLMs
    ICLR 2025 ·
    Zafeirios Fountas
    DBLP profile ↗ORCID search ↗
  19. Large Language Models are Demonstration Pre-Selectors for Themselves
    ICML 2025 ·
    Jiarui Jin
    DBLP profile ↗ORCID search ↗
  20. Learning Macroeconomic Policies Through Dynamic Stackelberg Mean-Field Games
    ECAI 2025 ·
    Qirui Mi
    DBLP profile ↗ORCID search ↗
  21. Lightweight Neural App Control
    ICLR 2025 ·
    Filippos Christianos
    DBLP profile ↗ORCID search ↗
  22. MF-LLM: Simulating Population Decision Dynamics via a Mean-Field Large Language Model Framework
    NeurIPS 2025 ·
    Qirui Mi
    DBLP profile ↗ORCID search ↗
  23. Mean Field Correlated Imitation Learning
    AAMAS 2025 ·
    Zhiyu Zhao
    DBLP profile ↗ORCID search ↗
  24. Mixture of Attentions For Speculative Decoding
    ICLR 2025 ·
    Matthieu Zimmer
    DBLP profile ↗ORCID search ↗
  25. MobileUse: A Hierarchical Reflection-Driven GUI Agent for Autonomous Mobile Operation
    NeurIPS 2025 ·
    Ning Li
    DBLP profile ↗ORCID search ↗
  26. On the Optimization Landscape of Low Rank Adaptation Methods for Large Language Models
    ICLR 2025 ·
    Xu-Hui Liu
    DBLP profile ↗ORCID search ↗
  27. Optimizing Case-Based Reasoning System for Functional Test Script Generation with Large Language Models
    SIGKDD 2025 ·
    Siyuan Guo
    DBLP profile ↗ORCID search ↗
  28. ReMA: Learning to Meta-Think for LLMs with Multi-agent Reinforcement Learning
    NeurIPS 2025 ·
    Ziyu Wan
    DBLP profile ↗ORCID search ↗
  29. Retrieval-Augmented Process Reward Model for Generalizable Mathematical Reasoning
    ACL 2025 ·
    Jiachen Zhu
    DBLP profile ↗ORCID search ↗
  30. Risk-aware Direct Preference Optimization under Nested Risk Measure
    NeurIPS 2025 ·
    Lijun Zhang
    DBLP profile ↗ORCID search ↗
  31. Robust Function-Calling for On-Device Language Model via Function Masking
    ICLR 2025 ·
    Qiqiang Lin
    DBLP profile ↗ORCID search ↗
  32. Self-Verifying Reflection Helps Transformers with CoT Reasoning
    NeurIPS 2025 ·
    Zhongwei Yu
    DBLP profile ↗ORCID search ↗
  33. Spa-Bench: a comprehensive Benchmark for Smartphone Agent Evaluation
    ICLR 2025 ·
    Jingxuan Chen
    DBLP profile ↗ORCID search ↗
  34. SparsePO: Controlling Preference Alignment of LLMs via Sparse Token Masks
    EMNLP 2025 ·
    Fenia Christopoulou
    DBLP profile ↗ORCID search ↗
  35. Spiral of Silence in Large Language Model Agents
    EMNLP 2025 ·
    Mingze Zhong
    DBLP profile ↗ORCID search ↗
  36. Succeed or Learn Slowly: Sample Efficient Off-Policy Reinforcement Learning for Mobile App Control
    NeurIPS 2025 ·
    Georgios Papoudakis
    DBLP profile ↗ORCID search ↗
  37. Taming Multi-Agent Reinforcement Learning with Estimator Variance Reduction
    AAMAS 2025 ·
    Taher Jafferjee
    DBLP profile ↗ORCID search ↗
  38. ThinkBench: Dynamic Out-of-Distribution Evaluation for Robust LLM Reasoning
    NeurIPS 2025 ·
    Shulin Huang
    DBLP profile ↗ORCID search ↗
  39. Uncertainty-quantified Rollout Policy Adaptation for Unlabelled Cross-domain Video Temporal Grounding
    NeurIPS 2025 ·
    Jian Hu
    DBLP profile ↗ORCID search ↗
  40. Unlocking the Potential of Decentralized LLM-based MAS: Privacy Preservation and Monetization in Collective Intelligence
    AAMAS 2025 ·
    Yingxuan Yang
    DBLP profile ↗ORCID search ↗
  41. Why Not Together? A Multiple-Round Recommender System for Queries and Items
    SIGKDD 2025 ·
    Jiarui Jin
    DBLP profile ↗ORCID search ↗
  42. A Summary of Online Markov Decision Processes with Non-oblivious Strategic Adversary
    AAMAS 2024 ·
    Le Cong Dinh
    DBLP profile ↗ORCID search ↗
  43. AlphaZero-Like Tree-Search can Guide Large Language Model Decoding and Training
    ICML 2024 ·
    Ziyu Wan
    DBLP profile ↗ORCID search ↗
  44. Boosting Studies of Multi-Agent Reinforcement Learning on Google Research Football Environment: The Past, Present, and Future
    AAMAS 2024 ·
    Yan Song
    DBLP profile ↗ORCID search ↗
  45. DS-Agent: Automated Data Science by Empowering Large Language Models with Case-Based Reasoning
    ICML 2024 ·
    Siyuan Guo
    DBLP profile ↗ORCID search ↗
  46. Human-Guided Moral Decision Making in Text-Based Games
    AAAI 2024 ·
    Zijing Shi
    DBLP profile ↗ORCID search ↗
  47. InfoRank: Unbiased Learning-to-Rank via Conditional Mutual Information Minimization
    WWW 2024 ·
    Jiarui Jin
    DBLP profile ↗ORCID search ↗
  48. Language and Sketching: An LLM-driven Interactive Multimodal Multitask Robot Navigation Framework
    ICRA 2024 ·
    Weiqin Zu
    DBLP profile ↗ORCID search ↗
  49. Large Language Models Are Neurosymbolic Reasoners
    AAAI 2024 ·
    Meng Fang
    DBLP profile ↗ORCID search ↗
  50. Large Language Models Play StarCraft II: Benchmarks and A Chain of Summarization Approach
    NeurIPS 2024 ·
    Weiyu Ma
    DBLP profile ↗ORCID search ↗
  51. Multiple Knowledge-Enhanced Interactive Graph Network for Multimodal Conversational Emotion Recognition
    EMNLP 2024 ·
    Geng Tu
    DBLP profile ↗ORCID search ↗
  52. Policy Learning from Tutorial Books via Understanding, Rehearsing and Introspecting
    NeurIPS 2024 ·
    Xiong-Hui Chen
    DBLP profile ↗ORCID search ↗
  53. Reinforcing LLM Agents via Policy Optimization with Action Decomposition
    NeurIPS 2024 ·
    Muning Wen
    DBLP profile ↗ORCID search ↗
  54. TaxAI: A Dynamic Economic Simulator and Benchmark for Multi-agent Reinforcement Learning
    AAMAS 2024 ·
    Qirui Mi
    DBLP profile ↗ORCID search ↗
  55. Token-level Direct Preference Optimization
    ICML 2024 ·
    Yongcheng Zeng
    DBLP profile ↗ORCID search ↗