Language Models are Hidden Reasoners: Unlocking Latent Reasoning Capabilities via Self-Rewardingby Haolin Chen, Yihao Feng,…
No Culture Left Behind: ArtELingo-28, a Benchmark of WikiArt with Captions in 28 Languagesby Youssef…
A Mamba Foundation Model for Time Series Forecastingby Haoyu Ma, Yushu Chen, Wenlai Zhao, Jinzhe…
ManiBox: Enhancing Spatial Grasping Generalization via Scalable Simulation Data Generationby Hengkai Tan, Xuezhou Xu, Chengyang…
Abstracted Shapes as Tokens – A Generalizable and Interpretable Model for Time-series Classificationby Yunshi Wen,…
LIBMoE: A Library for comprehensive benchmarking Mixture of Experts in Large Language Modelsby Nam V.…
TaxaBind: A Unified Embedding Space for Ecological Applicationsby Srikumar Sastry, Subash Khanal, Aayush Dhakal, Adeel…
B-cosification: Transforming Deep Neural Networks to be Inherently Interpretableby Shreyash Arya, Sukrut Rao, Moritz Böhle,…
Black-Box Forgettingby Yusuke Kuwana, Yuta Goto, Takashi Shibata, Go IrieFirst submitted to arxiv on: 1…
Compositional Automata Embeddings for Goal-Conditioned Reinforcement Learningby Beyazit Yalcinkaya, Niklas Lauffer, Marcell Vazquez-Chanlatte, Sanjit A.…