decision-making
Decision-making in AI encompasses the processes by which automated systems assess options and choose actions based on input data. Developing robust decision-making frameworks is crucial, particularly in real-time systems or autonomous applications.
- A Principled Approach to Randomized Selection under Uncertainty: Applications to Peer Review and Grant Funding
- ARIA: Training Language Agents with Intention-driven Reward Aggregation
- An Adaptive Quantum Circuit of Dempster's Rule of Combination for Uncertain Pattern Classification
- Architectural and Inferential Inductive Biases for Exchangeable Sequence Modeling
- CausalPFN: Amortized Causal Effect Estimation via In-Context Learning
- Conformal Mixed-Integer Constraint Learning with Feasibility Guarantees
- Contextual Integrity in LLMs via Reasoning and Reinforcement Learning
- Contextual Thompson Sampling via Generation of Missing Data
- DeepHalo: A Neural Choice Model with Controllable Context Effects
- Differentiable Constraint-Based Causal Discovery
- Distributive Fairness in Large Language Models: Evaluating Alignment with Human Values
- Doubly-Robust Estimation of Counterfactual Policy Mean Embeddings
- ESCORT: Efficient Stein-variational and Sliced Consistency-Optimized Temporal Belief Representation for POMDPs
- Explainably Safe Reinforcement Learning
- Feedback-Aware MCTS for Goal-Oriented Information Seeking
- Focus-Then-Reuse: Fast Adaptation in Visual Perturbation Environments
- HawkBench: Investigating Resilience of RAG Methods on Stratified Information-Seeking Tasks
- Integral Imprecise Probability Metrics
- Is the acquisition worth the cost? Surrogate losses for Consistent Two-stage Classifiers
- JarvisArt: Liberating Human Artistic Creativity via an Intelligent Photo Retouching Agent
- Layer-Wise Modality Decomposition for Interpretable Multimodal Sensor Fusion
- Learning to Plan Like the Human Brain via Visuospatial Perception and Semantic-Episodic Synergistic Decision-Making
- Learning-Augmented Online Bidding in Stochastic Settings
- NaDRO: Leveraging Dual-Reward Strategies for LLMs Training on Noisy Data
- OWMM-Agent: Open World Mobile Manipulation With Multi-modal Agentic Data Synthesis
- PHANTOM: A Benchmark for Hallucination Detection in Financial Long-Context QA
- Planning without Search: Refining Frontier LLMs with Offline Goal-Conditioned RL
- Probabilistic Reasoning with LLMs for Privacy Risk Estimation
- Resolution of Simpson's paradox via the common cause principle
- Setting $\varepsilon$ is not the Issue in Differential Privacy
- Solver-Informed RL: Grounding Large Language Models for Authentic Optimization Modeling
- SolverLLM: Leveraging Test-Time Scaling for Optimization Problem via LLM-Guided Search
- TwinMarket: A Scalable Behavioral and Social Simulation for Financial Markets
- VIBE: Annotation-Free Video-to-Text Information Bottleneck Evaluation for TL;DR
- World Models Should Prioritize the Unification of Physical and Social Dynamics