Publications

49 results at ICLR 2025

Dynamic Loss-Based Sample Reweighting for Improved Large Language Model Pretraining
- - Daouda Sow
  - Herbert Woisetschläger
  - et al.
- 2025
- ICLR 2025
SEAL: Safety-enhanced Aligned LLM Fine-tuning via Bilevel Data Selection
- - Han Shen
  - Pin-Yu Chen
  - et al.
- 2025
- ICLR 2025
Vertical Federated Learning with Missing Features During Training and Inference
- - Pedro Valdeira
  - Shiqiang Wang
  - et al.
- 2025
- ICLR 2025
TabWak: A Watermark for Tabular Diffusion Models
- - Chaoyi Zhu
  - Jiayi Tang
  - et al.
- 2025
- ICLR 2025
Revisiting Mode Connectivity in Neural Networks with Bezier Surface
- - Jie Ren
  - Pin-Yu Chen
- 2025
- ICLR 2025
A new framework for evaluating model out-of-distribution generalisation for the biochemical domain
- - Raúl Fernández Díaz
  - Lam Thanh Hoang
  - et al.
- 2025
- ICLR 2025
REFINE: Inversion-Free Backdoor Defense via Model Reprogramming
- - Yukun Chen
  - Shuo Shao
  - et al.
- 2025
- ICLR 2025
When is Task Vector Provably Effective for Model Editing? A Generalization Analysis of Nonlinear Transformers
- - Hongkang Li
  - Yihua Zhang
  - et al.
- 2025
- ICLR 2025
Training Nonlinear Transformers for Chain-of-Thought Inference: A Theoretical Generalization Analysis
- - Hongkang Li
  - Songtao Lu
  - et al.
- 2025
- ICLR 2025
Privacy-Preserving Personalized Federated Prompt Learning for Multimodal Large Language Models
- - Linh Tran
  - Wei Sun
  - et al.
- 2025
- ICLR 2025