NODE-AdvGAN: Improving the transferability and perceptual similarity of adversarial examples by dynamic-system-driven adversarial generative modelby…
Best-of-N Jailbreakingby John Hughes, Sara Price, Aengus Lynch, Rylan Schaeffer, Fazl Barez, Sanmi Koyejo, Henry…
Perception Tokens Enhance Visual Reasoning in Multimodal Language Modelsby Mahtab Bigverdi, Zelun Luo, Cheng-Yu Hsieh,…
Navigation World Modelsby Amir Bar, Gaoyue Zhou, Danny Tran, Trevor Darrell, Yann LeCunFirst submitted to…
Reinforced Symbolic Learning with Logical Constraints for Predicting Turbine Blade Fatigue Lifeby Pei Li, Joo-Ho…
Not All Adapters Matter: Selective Adapter Freezing for Memory-Efficient Fine-Tuning of Language Modelsby Hyegang Son,…
CovidLLM: A Robust Large Language Model with Missing Value Adaptation and Multi-Objective Learning Strategy for…
BatchLLM: Optimizing Large Batched LLM Inference with Global Prefix Sharing and Throughput-oriented Token Batchingby Zhen…
The Vulnerability of Language Model Benchmarks: Do They Accurately Reflect True LLM Performance?by Sourav Banerjee,…
CPTQuant - A Novel Mixed Precision Post-Training Quantization Techniques for Large Language Modelsby Amitash Nanda,…