Foundation Models

To Repeat or Not To Repeat: Insights from Scaling LLM under Token-Crisis NeurIPS 2023 Toward Building General Foundation Models for Language, Vision, and Vision-Language Understanding Tasks EMNLP 2023 Towards a Mechanistic Interpretation of Multi-Step Reasoning Capabilities of Language Models EMNLP 2023 Towards Anytime Fine-tuning: Continually Pre-trained Language Models with Hypernetwork Prompts EMNLP 2023 Towards A Unified View of Sparse Feed-Forward Network in Pretraining Large Language Model EMNLP 2023 Towards Benchmarking and Improving the Temporal Reasoning Capability of Large Language Models ACL 2023 Towards Concept-Aware Large Language Models EMNLP 2023 Towards Foundation Models for Scientific Machine Learning: Characterizing Scaling and Transfer Behavior NeurIPS 2023 Towards Geospatial Foundation Models via Continual Pretraining ICCV 2023 Towards Making the Most of ChatGPT for Machine Translation EMNLP 2023 Towards Unifying Medical Vision-and-Language Pre-Training via Soft Prompts ICCV 2023 Training Data Extraction From Pre-trained Language Models: A Survey ACL 2023 Training Deep Surrogate Models with Large Scale Online Learning ICML 2023 Training Transitive and Commutative Multimodal Transformers with LoReTTa NeurIPS 2023 Transcending Scaling Laws with 0.1% Extra Compute EMNLP 2023 Transformer-Based Language Model Surprisal Predicts Human Reading Times Best with About Two Billion Training Tokens EMNLP 2023 Transformers as Algorithms: Generalization and Stability in In-context Learning ICML 2023 Transformers Learn In-Context by Gradient Descent ICML 2023 Transport Elliptical Slice Sampling AISTATS 2023 Tree Prompting: Efficient Task Adaptation without Fine-Tuning EMNLP 2023 TRIGO: Benchmarking Formal Mathematical Proof Reduction for Generative Language Models EMNLP 2023 trlX: A Framework for Large Scale Reinforcement Learning from Human Feedback EMNLP 2023 Trompt: Towards a Better Deep Neural Network for Tabular Data ICML 2023 True Detective: A Deep Abductive Reasoning Benchmark Undoable for GPT-3 and Challenging for GPT-4 ACL 2023 UMLS-KGI-BERT: Data-Centric Knowledge Integration in Transformers for Biomedical Entity Recognition ACL 2023