Multi-State-Action Tokenisation in Decision Transformers for Multi-Discrete Action Spacesby Perusha Moodley, Pramod Kaushik, Dhillu Thambi,…
Eliminating Position Bias of Language Models: A Mechanistic Approachby Ziqi Wang, Hanlin Zhang, Xiner Li,…
Efficient Automated Circuit Discovery in Transformers using Contextual Decompositionby Aliyah R. Hsu, Georgia Zhou, Yeshwanth…
A Two-stage Reinforcement Learning-based Approach for Multi-entity Task Allocationby Aicheng Gong, Kai Yang, Jiafei Lyu,…
Intrinsic PAPR for Point-level 3D Scene Albedo and Shading Editingby Alireza Moazeni, Shichong Peng, Ke…
A Simple Attention-Based Mechanism for Bimodal Emotion Classificationby Mazen Elabd, Sardar JafFirst submitted to arxiv…
Visual Language Model based Cross-modal Semantic Communication Systemsby Feibo Jiang, Chuanguo Tang, Li Dong, Kezhi…
Logicbreaks: A Framework for Understanding Subversion of Rule-based Inferenceby Anton Xue, Avishree Khare, Rajeev Alur,…
Less is More: Accurate Speech Recognition & Translation without Web-Scale Databy Krishna C. Puvvada, Piotr…
Modeling the Real World with High-Density Visual Particle Dynamicsby William F. Whitney, Jacob Varley, Deepali…