6 papers
FailForge: Distilling Procedural Competence from Persistent Failures into Code Agents
Dongyi Lv, Fushun E, Aichen Cai +8
Rejection sampling fine-tuning (RFT) is widely used to train code agents by generating trajectories on verifiable software engineering tasks, retaining those that pass the tests, a…
Why Users Go There: World Knowledge-Augmented Generative Next POI Recommendation
Qiuyu Ding, Heng-Da Xu, Wei Zhang +4
Generative point-of-interest (POI) recommendation models based on large language models (LLMs) have shown promising results by formulating next POI prediction as a sequence generat…
Reasoning Over Space: Enabling Geographic Reasoning for LLM-Based Generative Next POI Recommendation
Dongyi Lv, Qiuyu Ding, Heng-Da Xu +4
Generative recommendation with large language models (LLMs) reframes prediction as sequence generation, yet existing LLM-based recommenders remain limited in leveraging geographic…
FedIDM: Achieving Fast and Stable Convergence in Byzantine Federated Learning through Iterative Distribution Matching
He Yang, Dongyi Lv, Wei Xi +3
Most existing Byzantine-robust federated learning (FL) methods suffer from slow and unstable convergence. Moreover, when handling a substantial proportion of colluded malicious cli…
InkDrop: Invisible Backdoor Attacks Against Dataset Condensation
He Yang, Dongyi Lv, Song Ma +4
Dataset Condensation (DC) is a data-efficient learning paradigm that synthesizes small yet informative datasets, enabling models to match the performance of full-data training. How…
SNEAKDOOR: Stealthy Backdoor Attacks against Distribution Matching-based Dataset Condensation
He Yang, Dongyi Lv, Song Ma +2
Dataset condensation aims to synthesize compact yet informative datasets that retain the training efficacy of full-scale data, offering substantial gains in efficiency. Recent stud…