Junbo Zhao

56 papers · 2015–2026 · 11 conferences · across top CS/AI conferences

Achievements

🏃 Academic Marathon (10) 🐝 Cross-Pollinator (15) 🌍 Conference Polyglot (11) 🌈 Renaissance Researcher (5) 🌉 Interdisciplinary Bridge 🗺️ Taxonomy Completionist (15) 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird 🤝 Dynamic Duo (34) 👑 Triple Crown 🏆 Grand Slam 🔬 Deep Specialist (11) 🧬 Topic Evolution 🏆 Keyword Champion 🗃️ Keyword Collector (243) 📈 Trend Setter 💎 Century Club (55) 🔥 Unstoppable (5) ⚡ Prolific Year (14)

Conferences

EMNLP (13) ACL (11) NIPS (8) ICLR (6) ICML (4) IJCAI (4) AAAI (3) ICCV (3) CVPR (2) COLING (1) NAACL (1)

Top co-authors

Haobo Wang (35) Gang Chen (24) Ruixuan Xiao (10) Lei Feng (10) Sai Wu (9) Wentao Ye (8) Mingxuan Xia (7) Zhiqing Xiao (7) Runze Wu (6) Yiming Zhang (6)

Research topics

Techniques (1) Resources & Methods (1) Applications (1) Education (1)

Keywords

large language model (20) representation learning (6) contrastive learning (5) text classification (5) knowledge distillation (4) active learning (3) semi-supervised learning (3) in-context learning (3) benchmark evaluation (3) synthetic datum (3) optimal transport (3) black-box model (3) multi-agent system (3) named entity recognition (2) prompt engineering (2) text generation (2) feature alignment (2) question answering (2) data annotation (2) data augmentation (2)

Papers

An Invariant Latent Space Perspective on Language Model Inversion AAAI 2026

DataMan: Data Manager for Pre-training Large Language Models ICLR 2025

Towards Reverse Engineering of Language Models: A Survey EMNLP 2025

CrowdAgent: Multi-Agent Managed Multi-Source Annotation System EMNLP 2025

RPDR: A Round-trip Prediction-Based Data Augmentation Framework for Long-Tail Question Answering EMNLP 2025

Jailbreaking Prompt Attack: A Controllable Adversarial Attack against Diffusion Models NAACL 2025

Pi-GPS: Enhancing Geometry Problem Solving by Unleashing the Power of Diagrammatic Information ICCV 2025

POLO: An LLM-Powered Project-Level Code Performance Optimization Framework IJCAI 2025

LeTS: Learning to Think-and-Search via Process-and-Outcome Reward Hybridization EMNLP 2025

CYCLE-INSTRUCT: Fully Seed-Free Instruction Tuning via Dual Self-Training and Cycle Consistency EMNLP 2025

Ensembling Prompting Strategies for Zero-Shot Hierarchical Text Classification with Large Language Models EMNLP 2025

Towards Robust Incremental Learning Under Ambiguous Supervision IJCAI 2025

Revisiting Convolution Architecture in the Realm of DNA Foundation Models ICLR 2025

LongTableBench: Benchmarking Long-Context Table Reasoning across Real-World Formats and Domains EMNLP 2025

Bridging the Semantic Gap Between Text and Table: A Case Study on NL2SQL ICLR 2025

D.Va: Validate Your Demonstration First Before You Use It ACL 2025

Prompt Candidates, then Distill: A Teacher-Student Framework for LLM-driven Data Annotation ACL 2025

Large Margin Representation Learning for Robust Cross-lingual Named Entity Recognition ACL 2025

RealHiTBench: A Comprehensive Realistic Hierarchical Table Benchmark for Evaluating LLM-Based Table Analysis ACL 2025

AIGT: AI Generative Table Based on Prompt COLING 2025

ALPS: Attention Localization and Pruning Strategy for Efficient Adaptation of Large Language Models ACL 2025

RECOST: External Knowledge Guided Data-efficient Instruction Tuning ACL 2024

Locating What You Need: Towards Adapting Diffusion Models to OOD Concepts In-the-Wild NIPS 2024

A Separation and Alignment Framework for Black-Box Domain Adaptation AAAI 2024

Learning Geometry-Aware Representations for New Intent Discovery ACL 2024

DORY: Deliberative Prompt Recovery for LLM ACL 2024

Data Contamination Calibration for Black-box LLMs ACL 2024

On LLMs-Driven Synthetic Data Generation, Curation, and Evaluation: A Survey ACL 2024

Positive-Unlabeled Learning by Latent Group-Aware Meta Disambiguation CVPR 2024

Targeted Representation Alignment for Open-World Semi-Supervised Learning CVPR 2024

Embedding and Gradient Say Wrong: A White-Box Method for Hallucination Detection EMNLP 2024

FlowBench: Revisiting and Benchmarking Workflow-Guided Planning for LLM-based Agents EMNLP 2024

Navigate Complex Physical Worlds via Geometrically Constrained LLM EMNLP 2024

Energy-based Automated Model Evaluation ICLR 2024

Unbiased Multi-Label Learning from Crowdsourced Annotations ICML 2024

Prompt as Triggers for Backdoor Attack: Examining the Vulnerability in Language Models EMNLP 2023

Learning a Data-Driven Policy Network for Pre-Training Automated Feature Engineering ICLR 2023

Dynamic Ensemble of Low-Fidelity Experts: Mitigating NAS “Cold-Start” AAAI 2023

SPA: A Graph Spectral Alignment Perspective for Domain Adaptation NIPS 2023

Debiased and Denoised Entity Recognition from Distant Supervision NIPS 2023

Towards Controlled Data Augmentations for Active Learning ICML 2023

Latent Processes Identification From Multi-View Time Series IJCAI 2023

ProMix: Combating Label Noise via Maximizing Clean Sample Utility IJCAI 2023

FreeAL: Towards Human-Free Active Learning in the Era of Large Language Models EMNLP 2023

Revisiting the Knowledge Injection Frameworks EMNLP 2023

CAME: Contrastive Automated Model Evaluation ICCV 2023

iDAG: Invariant DAG Searching for Domain Generalization ICCV 2023

Towards Unifying the Label Space for Aspect- and Sentence-based Sentiment Analysis ACL 2022

TA-GATES: An Encoding Scheme for Neural Network Architectures NIPS 2022

SoLar: Sinkhorn Label Refinery for Imbalanced Partial-Label Learning NIPS 2022

PiCO: Contrastive Label Disambiguation for Partial Label Learning ICLR 2022

Joining datasets via data augmentation in the label space for neural networks ICML 2021

Levenshtein Transformer NIPS 2019

Adversarially Regularized Autoencoders ICML 2018

Disentangling factors of variation in deep representation using adversarial training NIPS 2016

Character-level Convolutional Networks for Text Classification NIPS 2015