How to Leverage Demonstration Data in Alignment for Large Language Model? A Self-Imitation Learning Perspectiveby…
Unified Representation of Genomic and Biomedical Concepts through Multi-Task, Multi-Source Contrastive Learningby Hongyi Yuan, Suqi…
Self-Data Distillation for Recovering Quality in Pruned Large Language Modelsby Vithursan Thangarasa, Ganesh Venkatesh, Mike…
Targeted Vaccine: Safety Alignment for Large Language Models against Harmful Fine-Tuning via Layer-wise Perturbationby Guozhi…
Simultaneous Computation and Memory Efficient Zeroth-Order Optimizer for Fine-Tuning Large Language Modelsby Fei Wang, Li…
Uncovering, Explaining, and Mitigating the Superficial Safety of Backdoor Defenseby Rui Min, Zeyu Qin, Nevin…
Retrieval Instead of Fine-tuning: A Retrieval-based Parameter Ensemble for Zero-shot Learningby Pengfei Jin, Peng Shu,…
Dualformer: Controllable Fast and Slow Thinking by Learning with Randomized Reasoning Tracesby DiJia Su, Sainbayar…
ALLoRA: Adaptive Learning Rate Mitigates LoRA Fatal Flawsby Hai Huang, Randall BalestrieroFirst submitted to arxiv…
BiDoRA: Bi-level Optimization-Based Weight-Decomposed Low-Rank Adaptationby Peijia Qin, Ruiyi Zhang, Pengtao XieFirst submitted to arxiv…