FinGPT-HPC: Efficient Pretraining and Finetuning Large Language Models for Financial Applications with High-Performance Computingby Xiao-Yang…
GTBench: Uncovering the Strategic Reasoning Limitations of LLMs via Game-Theoretic Evaluationsby Jinhao Duan, Renming Zhang,…
In-Context Learning with Transformers: Softmax Attention Adapts to Function Lipschitznessby Liam Collins, Advait Parulekar, Aryan…
TuneTables: Context Optimization for Scalable Prior-Data Fitted Networksby Benjamin Feuer, Robin Tibor Schirrmeister, Valeriia Cherepanova,…
All in One and One for All: A Simple yet Effective Method towards Cross-domain Graph…
Embracing the black box: Heading towards foundation models for causal discovery from time series databy…
Can LLMs Learn New Concepts Incrementally without Forgetting?by Junhao Zheng, Shengjie Qiu, Qianli MaFirst submitted…
Autonomous Data Selection with Zero-shot Generative Classifiers for Mathematical Textsby Yifan Zhang, Yifan Luo, Yang…
Premier-TACO is a Few-Shot Policy Learner: Pretraining Multitask Representation via Temporal Action-Driven Contrastive Lossby Ruijie…
BIKED++: A Multimodal Dataset of 1.4 Million Bicycle Image and Parametric CAD Designsby Lyle Regenwetter,…