19 citations · 77 across the 60 of their papers we have counts for
17 papers · 1 filter
Act First, Reason Later: Accelerating On-Policy Distillation for Multi-Turn Agents via Reference-Conditioned Inverse Dynamics
Zubin Zheng, Jiahao Wu, Shaofeng Zhang +3
On-policy distillation (OPD) trains multi-turn language agents with dense teacher supervision on student-generated responses. However, standard think-then-act rollouts require leng…
Learning-Augmented and Randomized Algorithms for Line Aggregation with Delays
Tianhang Lu, Runtian Ren, Shengcai Liu +1
This paper studies learning-augmented and randomized online aggregation with delays on a line metric. We consider advice given as online suggested service lengths, and evaluate the…
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…
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…
OD-Gear: Online Decomposition and Group Sampling for Expert-Guided Adversarial Routing in Scalable Capacitated Vehicle Routing
Dongbin Jiao, Zisheng Chen, Xianyi Wang +3
Solving large-scale capacitated vehicle routing problems (CVRP) is hindered by the high complexity of classical heuristics and the limited generalization of neural solvers. To brid…
Personalized Treatment Outcome Prediction from Scarce Data via Dual-Channel Knowledge Distillation and Adaptive Fusion
Wenjie Chen, Li Zhuang, Ziying Luo +3
Personalized treatment outcome prediction based on trial data for small-sample and rare patient groups is a critical task in precision medicine. However, the high cost and scarcity…
Scalable Structure Learning of Bayesian Networks by Learning Algorithm Ensembles
Shengcai Liu, Hui Ou-yang, Zhiyuan Wang +4
Learning the structure of Bayesian networks (BNs) from data is challenging, especially for datasets involving a large number of variables. The recently proposed divide-and-conquer…
Quality-Diversity Red-Teaming: Automated Generation of High-Quality and Diverse Attackers for Large Language Models
Ren-Jian Wang, Ke Xue, Zeyu Qin +7
Ensuring the safety and robustness of large language models (LLMs) is a fundamental challenge and a critical prerequisite for the responsible deployment of artificial intelligence.…
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…
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…
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…
Context-aware Diversity Enhancement for Neural Multi-Objective Combinatorial Optimization
Yongfan Lu, Zixiang Di, Bingdong Li +5
Multi-objective combinatorial optimization (MOCO) problems are prevalent in various real-world applications. Most existing neural MOCO methods rely on problem decomposition to tran…
Multi-Domain Learning From Insufficient Annotations
Rui He, Shengcai Liu, Jiahao Wu +2
Multi-domain learning (MDL) refers to simultaneously constructing a model or a set of models on datasets collected from different domains. Conventional approaches emphasize domain-…
Reliable Robustness Evaluation via Automatically Constructed Attack Ensembles
Shengcai Liu, Fu Peng, Ke Tang
Attack Ensemble (AE), which combines multiple attacks together, provides a reliable way to evaluate adversarial robustness. In practice, AEs are often constructed and tuned by huma…
Saliency Attack: Towards Imperceptible Black-box Adversarial Attack
Zeyu Dai, Shengcai Liu, Ke Tang +1
Deep neural networks are vulnerable to adversarial examples, even in the black-box setting where the attacker is only accessible to the model output. Recent studies have devised ef…
Multi-Domain Active Learning: Literature Review and Comparative Study
Rui He, Shengcai Liu, Shan He +1
Multi-domain learning (MDL) refers to learning a set of models simultaneously, where each model is specialized to perform a task in a particular domain. Generally, a high labeling…
A New Knowledge Gradient-based Method for Constrained Bayesian Optimization
Wenjie Chen, Shengcai Liu, Ke Tang
Black-box problems are common in real life like structural design, drug experiments, and machine learning. When optimizing black-box systems, decision-makers always consider multip…