19 citations · 35 across the 16 of their papers we have counts for
17 papers
MuEvo: LLM-Driven Evolution of Multi-Heuristic Ensemble
Haoze Lv, Ning Lu, Shengcai Liu +2
Large language model-based automated heuristic design (LLM-AHD) has shown strong potential in discovering effective heuristics for combinatorial optimization problems. However, exi…
Cooperative Coevolution for Resource-Constrained Agentic LLM Post-Training
Zhiyuan Wang, Shengcai Liu, Jiahao Wu +5
Tool-using large language model (LLM) agents produce long, multi-turn trajectories, making gradient-based post-training memory-intensive. Evolution strategies (ES) enable memory-ef…
Policy and World Modeling Co-Training for Language Agents
Ning Lu, Baijiong Lin, Shengcai Liu +9
Reinforcement learning (RL) improves large language model (LLM) agents by teaching them which actions lead to high rewards, but provides little supervision on what those actions do…
AHD Agent: Agentic Reinforcement Learning for Automatic Heuristic Design
Haoze Lv, Ning Lu, Ziang Zhou +2
Automatic heuristic design (AHD) has emerged as a promising paradigm for solving NP-hard combinatorial optimization problems (COPs). Recent works show that large language models (L…
Train at Moving Edge: Online-Verified Prompt Selection for Efficient RL Training of Large Reasoning Model
Jiahao Wu, Ning Lu, Shengcai Liu +6
Reinforcement learning (RL) has become essential for post-training large language models (LLMs) in reasoning tasks. While scaling rollouts can stabilize training and enhance perfor…
Hardware-Aware DNN Compression for Homogeneous Edge Devices
Kunlong Zhang, Guiying Li, Ning Lu +2
Deploying deep neural networks (DNNs) across homogeneous edge devices (the devices with the same SKU labeled by the manufacturer) often assumes identical performance among them. Ho…
LLM-Driven Instance-Specific Heuristic Generation and Selection
Shaofeng Zhang, Shengcai Liu, Ning Lu +4
Combinatorial optimization problems are widely encountered in real-world applications. A critical research challenge lies in designing high-quality heuristic algorithms that effici…
Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets
Ning Lu, Shengcai Liu, Jiahao Wu +5
Large language models (LLMs) have shown great potential as general-purpose AI assistants across various domains. To fully leverage this potential in specific applications, many com…
Is PRM Necessary? Problem-Solving RL Implicitly Induces PRM Capability in LLMs
Zhangying Feng, Qianglong Chen, Ning Lu +6
The development of reasoning capabilities represents a critical frontier in large language models (LLMs) research, where reinforcement learning (RL) and process reward models (PRMs…
SemDiff: Generating Natural Unrestricted Adversarial Examples via Semantic Attributes Optimization in Diffusion Models
Zeyu Dai, Shengcai Liu, Rui He +5
Unrestricted adversarial examples (UAEs), allow the attacker to create non-constrained adversarial examples without given clean samples, posing a severe threat to the safety of dee…
Hardware-Aware DNN Compression for Homogeneous Edge Devices
Kunlong Zhang, Guiying Li, Ning Lu +2
Deploying deep neural networks (DNNs) across homogeneous edge devices (the devices with the same SKU labeled by the manufacturer) often assumes identical performance among them. Ho…
Backdoor Graph Condensation
Jiahao Wu, Ning Lu, Zeiyu Dai +5
Graph condensation has recently emerged as a prevalent technique to improve the training efficiency for graph neural networks (GNNs). It condenses a large graph into a small one su…
Large Language Models can be Guided to Evade AI-Generated Text Detection
Ning Lu, Shengcai Liu, Rui He +3
Large language models (LLMs) have shown remarkable performance in various tasks and have been extensively utilized by the public. However, the increasing concerns regarding the mis…
Less is More: Understanding Word-level Textual Adversarial Attack via n-gram Frequency Descend
Ning Lu, Shengcai Liu, Zhirui Zhang +3
Word-level textual adversarial attacks have demonstrated notable efficacy in misleading Natural Language Processing (NLP) models. Despite their success, the underlying reasons for…
Training Quantized Deep Neural Networks via Cooperative Coevolution
Fu Peng, Shengcai Liu, Ning Lu +1
This work considers a challenging Deep Neural Network(DNN) quantization task that seeks to train quantized DNNs without involving any full-precision operations. Most previous quant…
Effective and Imperceptible Adversarial Textual Attack via Multi-objectivization
Shengcai Liu, Ning Lu, Wenjing Hong +2
The field of adversarial textual attack has significantly grown over the last few years, where the commonly considered objective is to craft adversarial examples (AEs) that can suc…
Efficient Combinatorial Optimization for Word-level Adversarial Textual Attack
Shengcai Liu, Ning Lu, Cheng Chen +1
Over the past few years, various word-level textual attack approaches have been proposed to reveal the vulnerability of deep neural networks used in natural language processing. Ty…