Markov chain
PulseAugur coverage of Markov chain — every cluster mentioning Markov chain across labs, papers, and developer communities, ranked by signal.
- instance of alphaXiv 70%
- used by ScienceCast 70%
- instance of CatalyzeX Code Finder for Papers 70%
- used by CatalyzeX 70%
- instance of CORE Recommender 70%
- used by Gotit.pub 70%
- used by alphaXiv 70%
- instance of Influence Flower 60%
- instance of ScienceCast 60%
- instance of Gotit.pub 60%
- instance of CatalyzeX 60%
- instance of stat.ML 60%
9 day(s) with sentiment data
-
New RM-VLM approach uses LLMs and VLMs to automate reward machine generation
Researchers have introduced RM-VLM, a novel approach that leverages large language models (LLMs) and vision-language models (VLMs) to automatically generate reward machines (RMs) from natural-language task descriptions.…
-
Paper Explores AI Existential Risk for Mathematicians
A paper titled "Existential Risk from AI: An Exposition for Mathematicians" by Xiaoyu He explores the potential existential risks posed by artificial intelligence. The paper incorporates Markov chains and related discus…
-
AI-powered digital twin predicts cattle heat stress with 92% accuracy
Researchers have developed a novel digital twin framework for precision livestock farming, focusing on predicting core body temperature in dairy cattle to detect heat stress. This framework integrates physics-based simu…
-
arXiv sees new research on lifted reasoning and robust RL
Two new research papers were submitted to arXiv on October 26, 2026, focusing on distinct areas of AI. The first paper, "Query-Driven Learning for Lifted Reasoning," explores integrating learning and reasoning in first-…
-
AgentTrace framework identifies LLM agents' foundation models with 96% accuracy
Researchers have developed AgentTrace, a new framework designed to identify the underlying foundation model of black-box LLM agents. This method works by injecting probes that trigger serialization failures, which are t…
-
New method provides empirical concentration bounds for infinite-memory chains
Researchers have developed a new method for establishing empirical concentration bounds for stationary chains with infinite memory, extending beyond the traditional Markov chain framework. This approach estimates unknow…
-
New CausalCoT Framework Enhances AI Explanation Faithfulness
Researchers have introduced Causal Chain of Thought (CausalCoT), a new inference framework designed to improve the faithfulness of AI model explanations. Unlike standard Chain-of-Thought prompting, which can generate ju…
-
LLM Agents' Agreement Dynamics Revealed Through Aggregated Conversation Analysis
Researchers have developed a method to understand how large language model (LLM) agents converge on agreement during conversations. By analyzing internal representations across multiple conversations, they found that ag…
-
New research proves MCMC convergence diagnostics can't guarantee convergence
A new paper published on arXiv addresses the long-standing challenge of verifying convergence in Markov chain Monte Carlo (MCMC) methods. The research proves that no finite set of diagnostics can definitively guarantee …
-
New Bayesian inference method uses neural estimators for complex models
Researchers have developed a new semi-amortized Bayesian inference method that breaks down high-dimensional models into smaller blocks. This approach uses neural estimators to approximate conditional posteriors for bloc…
-
Markov Chains Achieve Tensor PCA Algorithmic Threshold
Researchers have demonstrated that Averaged Annealed Markov Chains can achieve the algorithmic threshold for Tensor PCA, a problem involving recovering an unknown vector from noisy observations of its tensor power. Prev…
-
New Q-learning frameworks tackle reinforcement learning challenges · 4 sources tracked
Researchers have developed novel Q-learning frameworks to address challenges in reinforcement learning. One approach, Q($ ext{γ}_H$), introduces a multi-horizon Q-learning system that adaptively combines discount-specif…
-
New arXiv papers refine Langevin sampling for LLMs and bandits
Two new arXiv papers explore advanced sampling techniques for machine learning. The first paper introduces Robust Langevin Sampling (R-LMC, A-LMC, RA-LMC) to address limitations in existing methods, particularly for fin…
-
Markov Chain Convergence Explored in Kernel-Induced Geometry
This paper investigates the convergence of Markov chains within a geometric framework defined by Hilbertian embeddings and positive definite kernels, specifically focusing on Maximum Mean Discrepancy (MMD). The research…
-
New paper details stationary bias in nonlinear stochastic approximation
A new paper published on arXiv explores stationary bias and extrapolation in nonlinear two-timescale stochastic approximation. The research details how constant-step stochastic approximation can lead to a persistent non…
-
New metric quantifies predictive gain from historical data
Researchers have introduced a new metric called Memory Prediction Excess (MPE) to quantify how much past information improves the prediction accuracy of stochastic processes. The MPE measures the average gain in predict…
-
New GFlowNet mixture framework enhances AI scientific discovery
Researchers have developed a new theoretical framework for mixtures of GFlowNets, which are used to improve state space exploration and convergence in AI-driven scientific discovery. This framework is divided into conti…
-
New research advances Schrödinger bridges for improved AI transport learning · 2 sources tracked
Two new research papers introduce advancements in Schrödinger bridges, a technique for learning stochastic transport between distributions. The first paper, "Cost-augmented Schrödinger bridges on graphs are exactly solv…
-
New arXiv papers detail advanced SGD optimization techniques · 2 sources tracked
Two new research papers published on arXiv explore advanced optimization techniques for stochastic gradient descent (SGD). The first paper, "Sharp Stationary Gaussian Approximation for Constant-Stepsize SGD," by Junghoo…
-
New statistical method improves estimation for time-dependent data
Researchers have developed a new statistical method called leave-a-window-out estimation for analyzing sequences of random variables. This technique aims to improve the estimation of functionals, such as the probability…