2026

Policy and World Modeling Co-Training for Language Agents
Policy and World Modeling Co-Training for Language Agents

Ning Lu*, Baijiong Lin*, Shengcai Liu, Jiahao Wu, Haoze Lv, Yanbin Wei, Lingting Zhu, Shengju Qian, Xin Wang, Ying-Cong Chen, Qi Wang, Ke Tang (* equal contribution)

Under review. 2026

The first policy and world-modeling co-training RL framework for LLM agents.

[Paper]

Policy and World Modeling Co-Training for Language Agents

Ning Lu*, Baijiong Lin*, Shengcai Liu, Jiahao Wu, Haoze Lv, Yanbin Wei, Lingting Zhu, Shengju Qian, Xin Wang, Ying-Cong Chen, Qi Wang, Ke Tang (* equal contribution)

Under review. 2026

The first policy and world-modeling co-training RL framework for LLM agents.

[Paper]

AHD Agent: Agentic Reinforcement Learning for Automatic Heuristic Design
AHD Agent: Agentic Reinforcement Learning for Automatic Heuristic Design

Haoze Lv*, Ning Lu*, Ziang Zhou, Shengcai Liu (* equal contribution)

Under review. 2026

The first tool-integrated multi-turn agentic framework for automatic algorithm design.

[Paper]

AHD Agent: Agentic Reinforcement Learning for Automatic Heuristic Design

Haoze Lv*, Ning Lu*, Ziang Zhou, Shengcai Liu (* equal contribution)

Under review. 2026

The first tool-integrated multi-turn agentic framework for automatic algorithm design.

[Paper]

Train at the Moving Edge: Efficient RL for Large Reasoning Models via Rollout Selection
Train at the Moving Edge: Efficient RL for Large Reasoning Models via Rollout Selection

Jiahao Wu*, Ning Lu*, Shengcai Liu, Kun Wang, Yanting Yang, Li Qing, Ke Tang (* equal contribution)

Under review. 2026

The first online policy-verified data selection framework for efficient RL training.

[Paper]

Train at the Moving Edge: Efficient RL for Large Reasoning Models via Rollout Selection

Jiahao Wu*, Ning Lu*, Shengcai Liu, Kun Wang, Yanting Yang, Li Qing, Ke Tang (* equal contribution)

Under review. 2026

The first online policy-verified data selection framework for efficient RL training.

[Paper]

VL-RouterBench: A Benchmark for Vision-Language Model Routing
VL-RouterBench: A Benchmark for Vision-Language Model Routing

Zhehao Huang, Baijiong Lin, Jingyuan Zhang, Jingying Wang, Yuhang Liu, Ning Lu, Tao Li, Xiaolin Huang

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2026

The first benchmark for VLM router.

[Paper]

VL-RouterBench: A Benchmark for Vision-Language Model Routing

Zhehao Huang, Baijiong Lin, Jingyuan Zhang, Jingying Wang, Yuhang Liu, Ning Lu, Tao Li, Xiaolin Huang

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2026

The first benchmark for VLM router.

[Paper]

2025

Is PRM Necessary? Problem-Solving RL Implicitly Induces PRM Capability in LLMs
Is PRM Necessary? Problem-Solving RL Implicitly Induces PRM Capability in LLMs

Zhangying Feng*, Qianglong Chen*, Ning Lu, Yongqian Li, Siqi Cheng, Shuangmu Peng, Duyu Tang, Shengcai Liu, Zhirui Zhang (* equal contribution)

Conference on Neural Information Processing Systems (NeurIPS) 2025

Unifying problem solving and solution-process judgment.

[Paper]

Is PRM Necessary? Problem-Solving RL Implicitly Induces PRM Capability in LLMs

Zhangying Feng*, Qianglong Chen*, Ning Lu, Yongqian Li, Siqi Cheng, Shuangmu Peng, Duyu Tang, Shengcai Liu, Zhirui Zhang (* equal contribution)

Conference on Neural Information Processing Systems (NeurIPS) 2025

Unifying problem solving and solution-process judgment.

[Paper]

Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets
Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets

Ning Lu, Shengcai Liu, Jiahao Wu, Weiyu Chen, Zhirui Zhang, Yew-Soon Ong, Qi Wang, Ke Tang

International Conference on Machine Learning (ICML) 2025

The first safety-aware post-fine-tuning defense method for LLM alignment.

[Paper] [Code]

Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets

Ning Lu, Shengcai Liu, Jiahao Wu, Weiyu Chen, Zhirui Zhang, Yew-Soon Ong, Qi Wang, Ke Tang

International Conference on Machine Learning (ICML) 2025

The first safety-aware post-fine-tuning defense method for LLM alignment.

[Paper] [Code]

SemDiff: Generating Natural Unrestricted Adversarial Examples via Semantic Attributes Optimization in Diffusion Models
SemDiff: Generating Natural Unrestricted Adversarial Examples via Semantic Attributes Optimization in Diffusion Models

Zeyu Dai, Shengcai Liu, Rui He, Jiahao Wu, Ning Lu, Wenqi Fan, Qing Li, Ke Tang

Under review. 2025

[Paper]

SemDiff: Generating Natural Unrestricted Adversarial Examples via Semantic Attributes Optimization in Diffusion Models

Zeyu Dai, Shengcai Liu, Rui He, Jiahao Wu, Ning Lu, Wenqi Fan, Qing Li, Ke Tang

Under review. 2025

[Paper]

Backdoor graph condensation
Backdoor graph condensation

Jiahao Wu, Ning Lu, Zeiyu Dai, Kun Wang, Wenqi Fan, Weiyu Chen, Shengcai Liu, Qing Li, Ke Tang

IEEE International Conference on Data Engineering (ICDE) 2025 Oral

[Paper] [Code]

Backdoor graph condensation

Jiahao Wu, Ning Lu, Zeiyu Dai, Kun Wang, Wenqi Fan, Weiyu Chen, Shengcai Liu, Qing Li, Ke Tang

IEEE International Conference on Data Engineering (ICDE) 2025 Oral

[Paper] [Code]

2024

Training Overhead Ratio: A Practical Reliability Metric for Large Language Model Training Systems
Training Overhead Ratio: A Practical Reliability Metric for Large Language Model Training Systems

Ning Lu, Qian Xie, Hao Zhang, Wenyi Fang, Yang Zheng, Zheng Hu, Jiantao Ma

2024 IEEE 35th International Symposium on Software Reliability Engineering Workshops (ISSREW) 2024

[Paper]

Training Overhead Ratio: A Practical Reliability Metric for Large Language Model Training Systems

Ning Lu, Qian Xie, Hao Zhang, Wenyi Fang, Yang Zheng, Zheng Hu, Jiantao Ma

2024 IEEE 35th International Symposium on Software Reliability Engineering Workshops (ISSREW) 2024

[Paper]

Less is More: Understanding Word-level Textual Adversarial Attack via n-gram Frequency Descend
Less is More: Understanding Word-level Textual Adversarial Attack via n-gram Frequency Descend

Ning Lu, Shengcai Liu, Zhirui Zhang, Qi Wang, Haifeng Liu, Ke Tang

2024 IEEE Conference on Artificial Intelligence (CAI) 2024 Oral

[Paper]

Less is More: Understanding Word-level Textual Adversarial Attack via n-gram Frequency Descend

Ning Lu, Shengcai Liu, Zhirui Zhang, Qi Wang, Haifeng Liu, Ke Tang

2024 IEEE Conference on Artificial Intelligence (CAI) 2024 Oral

[Paper]

Large Language Models can be Guided to Evade AI-generated Text Detection
Large Language Models can be Guided to Evade AI-generated Text Detection

Ning Lu, Shengcai Liu, Rui He, Qi Wang, Yew-Soon Ong, Ke Tang

Transactions on Machine Learning Research (TMLR) 2024

Showing that LLMs themselves can evade AI detectors with fine-grained prompting.

[Paper] [Code]

Large Language Models can be Guided to Evade AI-generated Text Detection

Ning Lu, Shengcai Liu, Rui He, Qi Wang, Yew-Soon Ong, Ke Tang

Transactions on Machine Learning Research (TMLR) 2024

Showing that LLMs themselves can evade AI detectors with fine-grained prompting.

[Paper] [Code]

2023

Effective and Imperceptible Adversarial Textual Attack via Multi-objectivization
Effective and Imperceptible Adversarial Textual Attack via Multi-objectivization

Shengcai Liu, Ning Lu, W Hong, C Qian, Ke Tang

ACM Transactions on Evolutionary Learning and Optimization 2023

[Paper]

Effective and Imperceptible Adversarial Textual Attack via Multi-objectivization

Shengcai Liu, Ning Lu, W Hong, C Qian, Ke Tang

ACM Transactions on Evolutionary Learning and Optimization 2023

[Paper]

2021

Efficient Combinatorial Optimization for Word-level Adversarial Textual Attack
Efficient Combinatorial Optimization for Word-level Adversarial Textual Attack

Shengcai Liu, Ning Lu, Cheng Chen, Ke Tang

IEEE/ACM Transactions on Audio, Speech, and Language Processing (TALSP, CCF-B) 2021

[Paper] [Code]

Efficient Combinatorial Optimization for Word-level Adversarial Textual Attack

Shengcai Liu, Ning Lu, Cheng Chen, Ke Tang

IEEE/ACM Transactions on Audio, Speech, and Language Processing (TALSP, CCF-B) 2021

[Paper] [Code]