Random Representations Outperform Online Continually Learned Representationsby Ameya Prabhu, Shiven Sinha, Ponnurangam Kumaraguru, Philip H.S.…
PRDP: Proximal Reward Difference Prediction for Large-Scale Reward Finetuning of Diffusion Modelsby Fei Deng, Qifei…
Test-Time Backdoor Attacks on Multimodal Large Language Modelsby Dong Lu, Tianyu Pang, Chao Du, Qian…
Label-Efficient Model Selection for Text Generationby Shir Ashury-Tahan, Ariel Gera, Benjamin Sznajder, Leshem Choshen, Liat…
Summing Up the Facts: Additive Mechanisms Behind Factual Recall in LLMsby Bilal Chughtai, Alan Cooney,…
Using Large Language Models to Automate and Expedite Reinforcement Learning with Reward Machineby Shayan Meshkat…
NICE: To Optimize In-Context Examples or Not?by Pragya Srivastava, Satvik Golechha, Amit Deshpande, Amit SharmaFirst…
Fight Back Against Jailbreaking via Prompt Adversarial Tuningby Yichuan Mo, Yuji Wang, Zeming Wei, Yisen…
Large Language Model Meets Graph Neural Network in Knowledge Distillationby Shengxiang Hu, Guobing Zou, Song…
GPT-4 Generated Narratives of Life Events using a Structured Narrative Prompt: A Validation Studyby Christopher…