activity
20242026
collaborators
Showing cs.LGShow all

6 papers · 1 filter

cs.LG2026

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…

cs.LG2026

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…

cs.LG20252 cited

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…

cs.LG2025

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…

cs.LG2025

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…

cs.LG2025

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…