arXiv:2601.17160v1 Announce Type: cross Abstract: We develop a data-driven information-theoretic framework for sharp partial identification of causal effects under unmeasured confounding. Existing approaches often rely on restrictive assumptions, such as bounded or discrete outcomes; require external inputs (for example, instrumental variables, proxies, or user-specified sensitivity parameters); necessitate full structural causal model specifications; or focus solely […]
Towards Robust Evaluation of Visual Activity Recognition: Resolving Verb Ambiguity with Sense Clustering
arXiv:2508.04945v2 Announce Type: replace-cross Abstract: Evaluating visual activity recognition systems is challenging due to inherent ambiguities in verb semantics and image interpretation. When describing actions in images, synonymous verbs can refer to the same event (e.g., brushing vs. grooming), while different perspectives can lead to equally valid but distinct verb choices (e.g., piloting vs. operating). […]
Coordinates from Context: Using LLMs to Ground Complex Location References
arXiv:2510.08741v2 Announce Type: replace-cross Abstract: Geocoding is the task of linking a location reference to an actual geographic location and is essential for many downstream analyses of unstructured text. In this paper, we explore the challenging setting of geocoding compositional location references. Building on recent work demonstrating LLMs’ abilities to reason over geospatial data, we […]
TruthTensor: Evaluating LLMs through Human Imitation on Prediction Market under Drift and Holistic Reasoning
arXiv:2601.13545v3 Announce Type: replace Abstract: Evaluating language models and AI agents remains fundamentally challenging because static benchmarks fail to capture real-world uncertainty, distribution shift, and the gap between isolated task accuracy and human-aligned decision-making under evolving conditions. This paper introduces TruthTensor, a novel, reproducible evaluation paradigm that measures reasoning models not only as prediction engines […]
MobileCity: An Efficient Framework for Large-Scale Urban Behavior Simulation
arXiv:2504.16946v4 Announce Type: replace-cross Abstract: Generative agents offer promising capabilities for simulating realistic urban behaviors. However, existing methods oversimplify transportation choices, rely heavily on static agent profiles leading to behavioral homogenization, and inherit prohibitive computational costs. To address these limitations, we present MobileCity, a lightweight simulation platform designed to model realistic urban mobility with high […]
Trust, Don’t Trust, or Flip: Robust Preference-Based Reinforcement Learning with Multi-Expert Feedback
arXiv:2601.18751v1 Announce Type: cross Abstract: Preference-based reinforcement learning (PBRL) offers a promising alternative to explicit reward engineering by learning from pairwise trajectory comparisons. However, real-world preference data often comes from heterogeneous annotators with varying reliability; some accurate, some noisy, and some systematically adversarial. Existing PBRL methods either treat all feedback equally or attempt to filter […]
Complex-valued Phase Synchrony Reveals Directional Coupling in FMRI and Tracks Medication Effects
arXiv:2509.13481v2 Announce Type: replace Abstract: Understanding interactions in complex systems requires capturing the relative timing of coupling, not only its strength. Phase synchronization captures this timing, yet most methods either reduce the phase to its cosine or collapse it into scalar indices such as the phase-locking value, discarding relative timing. We propose a complex-valued phase […]
Code over Words: Overcoming Semantic Inertia via Code-Grounded Reasoning
arXiv:2601.18352v1 Announce Type: cross Abstract: LLMs struggle with Semantic Inertia: the inability to inhibit pre-trained priors (e.g., “Lava is Dangerous”) when dynamic, in-context rules contradict them. We probe this phenomenon using Baba Is You, where physical laws are mutable text rules, enabling precise evaluation of models’ ability to override learned priors when rules change. We […]
Masked Generative Policy for Robotic Control
arXiv:2512.09101v2 Announce Type: replace-cross Abstract: We present Masked Generative Policy (MGP), a novel framework for visuomotor imitation learning. We represent actions as discrete tokens, and train a conditional masked transformer that generates tokens in parallel and then rapidly refines only low-confidence tokens. We further propose two new sampling paradigms: MGP-Short, which performs parallel masked generation […]
The Need for a Socially-Grounded Persona Framework for User Simulation
arXiv:2601.07110v2 Announce Type: replace-cross Abstract: Synthetic personas are widely used to condition large language models (LLMs) for social simulation, yet most personas are still constructed from coarse sociodemographic attributes or summaries. We revisit persona creation by introducing SCOPE, a socially grounded framework for persona construction and evaluation, built from a 141-item, two-hour sociopsychological protocol collected […]
Rank-1 Approximation of Inverse Fisher for Natural Policy Gradients in Deep Reinforcement Learning
arXiv:2601.18626v1 Announce Type: cross Abstract: Natural gradients have long been studied in deep reinforcement learning due to their fast convergence properties and covariant weight updates. However, computing natural gradients requires inversion of the Fisher Information Matrix (FIM) at each iteration, which is computationally prohibitive in nature. In this paper, we present an efficient and scalable […]
Evolution of AI in Education: Agentic Workflows
arXiv:2504.20082v2 Announce Type: replace Abstract: The primary goal of this study is to analyze agentic workflows in education according to the proposed four major technological paradigms: reflection, planning, tool use, and multi-agent collaboration. We critically examine the role of AI agents in education through these key design paradigms, exploring their advantages, applications, and challenges. Second, […]