Junbo Li

9 papers · 2022–2026 · 6 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (16) 🐣 Hot Topic Early Bird 🔥 Unstoppable · Bronze

Venues

NeurIPS (3) ICML (2) EACL (1) ECCV (1) EMNLP (1) ICLR (1)

Top co-authors

Eric P. Xing (2) Zhangyang Wang (2) Lihong Li (1) Bohan Yu (1) Zutao Jiang (1) Zhiqiang Shen (1) Zhengzhong Liu (1) Omar Baldonado (1) Lei Wang (1) Jingyi Wang (1)

Research topics

Artificial Intelligence (7) Core AI (6) Machine Learning (5) Optimization & Theory (5) Natural Language Processing (3) Reinforcement Learning (2) Applications (2) Methods (2) Resources & Methods (2) Deep Learning (1) Generation (1) Learning Paradigms (1) Learning Types (1) Models (1)

Keywords

neural network optimization (2) variational inference (1) probabilistic framework (1) multilingual nlp (1) ridge regression (1) convergence analysis (1) code generation (1) semantic alignment (1) gradient clipping (1) instruction tuning (1) exponential family (1) model-based reinforcement learning (1) maximum likelihood estimation (1) score matching (1) uncertainty quantification (1) parameter server (1) regret bound (1) benchmark dataset (1) federated learning (1) model compression (1)

Papers

Turn-PPO: Turn-Level Advantage Estimation with PPO for Improved Multi-Turn RL in Agentic LLMs EACL 2026 HALoS: Hierarchical Asynchronous Local SGD over Slow Networks for Geo-Distributed Large Language Model Training ICML 2025 PIPA: Preference Alignment as Prior-Informed Statistical Estimation ICML 2025 TableEval: A Real-World Benchmark for Complex, Multilingual, and Multi-Structured Table Question Answering EMNLP 2025 Training Bayesian Neural Networks with Sparse Subspace Variational Inference ICLR 2024 Web2Code: A Large-scale Webpage-to-Code Dataset and Evaluation Framework for Multimodal LLMs NeurIPS 2024 FedNAR: Federated Optimization with Normalized Annealing Regularization NeurIPS 2023 Exponential Family Model-Based Reinforcement Learning via Score Matching NeurIPS 2022 VIP: Unified Certified Detection and Recovery for Patch Attack with Vision Transformers ECCV 2022