A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
New framework for AI to learn causal models through experience.
Perception of artificial agents is one the grand challenges of AI research. Deep Learning and data-driven approaches are successful on constrained problems where perception can be learned using supervision, but do not scale to open-worlds. In such case, for autonomous embodied agents with first-person sensors, percepti…
Alpha-GPT 2.0 integrates human insights into AI-driven investment research.
New text-to-image diffusion models improve scene understanding for AI agents.
Paper creates fair synthetic data ensuring equal predictions across sensitive attributes.
Improves AI agents' 3D navigation by learning from failures and 3D spatial relationships.
AIF improves physical AI agents' performance in dynamic environments.
New framework uses OR to ensure AI systems make safe decisions.
The development of autonomous robotic systems that can learn from human demonstrations to imitate a desired behavior - rather than being manually programmed - has huge technological potential. One major challenge in imitation learning is the correspondence problem: how to establish corresponding states and actions betw…
Reinforcement learning for embodied agents is a challenging problem. The accumulated reward to be optimized is often a very rugged function, and gradient methods are impaired by many local optimizers. We demonstrate, in an experimental setting, that incorporating an intrinsic reward can smoothen the optimization landsc…
This paper proposes a new method to connect language and physical actions in reinforcement learning.
Neural SDEs model continuous sequences using neural networks.
We study the question of how to imitate tasks across domains with discrepancies such as embodiment, viewpoint, and dynamics mismatch. Many prior works require paired, aligned demonstrations and an additional RL step that requires environment interactions. However, paired, aligned demonstrations are seldom obtainable an…
EDGI improves sample efficiency and generalization in tasks with spatial and temporal symmetries.
Embodied cognition states that semantics is encoded in the brain as firing patterns of neural circuits, which are learned according to the statistical structure of human multimodal experience. However, each human brain is idiosyncratically biased, according to its subjective experience history, making this biological s…
New approach categorizes objective functions for embodied agents.
For embodied agents to infer representations of the underlying 3D physical world they inhabit, they should efficiently combine multisensory cues from numerous trials, e.g., by looking at and touching objects. Despite its importance, multisensory 3D scene representation learning has received less attention compared to t…
Recent efforts on training visual navigation agents conditioned on language using deep reinforcement learning have been successful in learning policies for different multimodal tasks, such as semantic goal navigation and embodied question answering. In this paper, we propose a multitask model capable of jointly learnin…
We study financial distributions within the framework of the continuous time random walk (CTRW). We review earlier approaches and present new results related to overnight effects as well as the generalization of the formalism which embodies a non-Markovian formulation of the CTRW aimed to account for correlated increme…
Paper proves Toponogov's theorem in Alexandrov geometry.
We construct an elementary, combinatorial kind of topological quantum field theory, based on curves, surfaces, and orientations. The construction derives from contact invariants in sutured Floer homology and is essentially an elaboration of a TQFT defined by Honda--Kazez--Matic. This topological field theory stores inf…
What is the role of real-time control and learning in the formation of social conventions? To answer this question, we propose a computational model that matches human behavioral data in a social decision-making game that was analyzed both in discrete-time and continuous-time setups. Furthermore, unlike previous approa…
Animals (especially humans) have an amazing ability to learn new tasks quickly, and switch between them flexibly. How brains support this ability is largely unknown, both neuroscientifically and algorithmically. One reasonable supposition is that modules drawing on an underlying general-purpose sensory representation a…
AI stocks hedge against AI singularity's economic impact.
A major challenge in cognitive science and AI has been to understand how autonomous agents might acquire and predict behavioral and mental states of other agents in the course of complex social interactions. How does such an agent model the goals, beliefs, and actions of other agents it interacts with? What are the com…
Study analyzes AI's impact on firms, markets, and workers using large language model data.
New AI stock indices classify firms' AI engagement using 10-K filings.
The paper analyzes risk spillovers between AI ETFs, AI tokens, and green markets.
This review covers AI in finance, challenges, techniques, and opportunities.
Explainable AI improves human decision accuracy but does not enhance it significantly.
Econophysics embodies the recent upsurge of interest by physicists into financial economics, driven by the availability of large amount of data, job shortage in physics and the possibility of applying many-body techniques developed in statistical and theoretical physics to the understanding of the self-organizing econo…
The paper explores AI in finance, focusing on XAI's role in enhancing interpretability and trust.
Most common navigation tasks in human environments require auxiliary arm interactions, e.g. opening doors, pressing buttons and pushing obstacles away. This type of navigation tasks, which we call Interactive Navigation, requires the use of mobile manipulators: mobile bases with manipulation capabilities. Interactive N…
Paper defines AI-specific loss reconstruction problem and introduces CER framework.
Experiment shows cognitive biases impact human-AI collaboration, highlighting the need for diverse evaluator samples.
AI enhances financial forecasting with challenges in regulation and privacy.
AI+MPS workshop aims to strengthen AI's role in science.
Improved AI patent classifier measures U.S. and China's AI patenting.
FST.ai 2.0 improves Taekwondo decision-making with AI, reducing review time and increasing trust.
A multi-agent system is trialed as a means of crowd-sourcing inexpensive but high quality streams of predictions. Each agent is a microservice embodying statistical models and endowed with economic self-interest. The ability to fork and modify simple agents is granted to a large number of employees in a firm and empiri…
Article evaluates AI security threats and proposes multiple measures.
We describe three perspectives on higher quantization, using the example of magnetic Poisson structures which embody recent discussions of nonassociativity in quantum mechanics with magnetic monopoles and string theory with non-geometric fluxes. We survey approaches based on deformation quantization of twisted Poisson …
AI threatens financial stability through misuse and stealth adoption.
Adversarial policies beat superhuman Go AI systems.
The DoD needs a robust process to evaluate AI/ML model performance and robustness.
Paper tackles AI risks by customizing metrics and models.
Though deep reinforcement learning has led to breakthroughs in many difficult domains, these successes have required an ever-increasing number of samples. As state-of-the-art reinforcement learning (RL) systems require an exponentially increasing number of samples, their development is restricted to a continually shrin…
Qlib aims to integrate AI into quantitative investment.