information gain

InfoGain-RAG: Boosting Retrieval-Augmented Generation through Document Information Gain-based Reranking and Filtering EMNLP 2025 Information-Based Exploration via Random Features for Reinforcement Learning ACML 2025 Integrating Inference and Experimental Design for Contextual Behavioral Model Learning AAAI 2025 Map Space Belief Prediction for Manipulation-Enhanced Mapping RSS 2025 MaxInfoRL: Boosting exploration in reinforcement learning through information gain maximization ICLR 2025 MIG: Automatic Data Selection for Instruction Tuning by Maximizing Information Gain in Semantic Space ACL 2025 Optimizing Test-Time Compute via Meta Reinforcement Finetuning ICML 2025 Pareto-frontier Entropy Search with Variational Lower Bound Maximization ICML 2025 POp-GS: Next Best View in 3D-Gaussian Splatting with P-Optimality CVPR 2025 Towards a Theoretical Understanding of Synthetic Data in LLM Post-Training: A Reverse-Bottleneck Perspective ICLR 2025 Towards Better Chain-of-Thought: A Reflection on Effectiveness and Faithfulness ACL 2025 Understanding Chain-of-Thought in LLMs through Information Theory ICML 2025 Active Learning for Derivative-Based Global Sensitivity Analysis with Gaussian Processes NeurIPS 2024 Bayesian Adaptive Calibration and Optimal Design NeurIPS 2024 Color-Oriented Redundancy Reduction in Dataset Distillation NeurIPS 2024 Fully-Dynamic Approximate Decision Trees With Worst-Case Update Time Guarantees ICML 2024 Fundamental Properties of Causal Entropy and Information Gain CLeaR 2024 Active Velocity Estimation using Light Curtains via Self-Supervised Multi-Armed Bandits RSS 2023 Bayesian Oracle for bounding information gain in neural encoding models ICLR 2023 Bregman Deviations of Generic Exponential Families COLT 2023 Contrastive Learning-based Sentence Encoders Implicitly Weight Informative Words EMNLP 2023 Information-Directed Selection for Top-Two Algorithms COLT 2023 Norm of Word Embedding Encodes Information Gain EMNLP 2023 Physics-Guided Active Learning of Environmental Flow Fields L4DC 2023 Prediction-Oriented Bayesian Active Learning AISTATS 2023