Mitigating Object Hallucination in Large Vision-Language Models via Classifier-Free Guidanceby Linxi Zhao, Yihe Deng, Weitong…
Can LLMs Learn New Concepts Incrementally without Forgetting?by Junhao Zheng, Shengjie Qiu, Qianli MaFirst submitted…
Towards Faithful and Robust LLM Specialists for Evidence-Based Question-Answeringby Tobias Schimanski, Jingwei Ni, Mathias Kraus,…
BBox-Adapter: Lightweight Adapting for Black-Box Large Language Modelsby Haotian Sun, Yuchen Zhuang, Wei Wei, Chao…
Large Language Models as Agents in Two-Player Gamesby Yang Liu, Peng Sun, Hang LiFirst submitted…
An Efficient Rehearsal Scheme for Catastrophic Forgetting Mitigation during Multi-stage Fine-tuningby Andrew Bai, Chih-Kuan Yeh,…
A Competition Winning Deep Reinforcement Learning Agent in microRTSby Scott GoodfriendFirst submitted to arxiv on:…
Active Preference Learning for Large Language Modelsby William Muldrew, Peter Hayes, Mingtian Zhang, David BarberFirst…
Grounding Data Science Code Generation with Input-Output Specificationsby Yeming Wen, Pengcheng Yin, Kensen Shi, Henryk…
Task-conditioned adaptation of visual features in multi-task policy learningby Pierre Marza, Laetitia Matignon, Olivier Simonin,…