All Articles
16473 articles total
Euclid-MCP: A Model Context Protocol Server for Deterministic Logical Reasoning via Prolog
Euclid-MCP is an open-source MCP server that integrates LLMs with SWI-Prolog for deterministic logical reasoning in safety-critical domains.
Logical Regression for Planning with Axioms
A new methodology for approximating logical regression in automated planning domains that include axioms, significantly reducing variable counts for execution monitoring.
PATS: Policy-Aware Training Scaffolding for Agentic Reinforcement Learning
PATS is a policy-centric training paradigm for agentic RL that uses dynamic training scaffolds to improve the performance of weak policies in long-horizon tasks.
Bridging the Gap Between Plausibility and Admissibility: Constraint-Aware Flow Maps for Dynamic Graph Systems
Research on using symbolic constraints to improve the structural feasibility of generative trajectory modeling in dynamic graph systems.
Agent-Guided Relational Concept Discovery: Toward Interpretable Surgical Margin Assessment
A framework for Agent-Guided Concept Discovery to improve interpretable surgical margin assessment using mass spectrometry data.
Detecting LLM-Generated Tokens in Human--LLM Coauthored Text
A token-level detection method for identifying LLM-generated content within human-AI coauthored texts using an adaptive smoothing rule.
The Ever-Receding Pocket
A Hacker News discussion thread regarding the concept of the 'ever-receding pocket'.
Logic Programming Semantics for Causal Processes
Research investigating the relationship between logic programming semantics and the eventual states of causal processes, particularly for life sciences modeling.
BasketEvent: Understanding Who Did What and When in Basketball Videos
Introduction of BasketEvent, a player-centric basketball event understanding dataset and PlayNet, a reasoning framework for fine-grained sports video analysis.
An LLM-Driven Workflow for Automated Process Control Strategy Generation and Tuning from Dynamic Process Models
A structured LLM-driven workflow for automated process control strategy generation and tuning using dynamic process models and Bayesian optimization.
Expert Behavior Prior Reinforcement Learning
Proposed Expert Behavior Prior (EBP) algorithm to improve online reinforcement learning sample efficiency using a Q-guided conditional variational autoencoder.
Regulating autonomous and agentic AI
A study on the challenges of regulating autonomous and agentic AI, proposing a shift from reactive to active regulatory systems.
SPORD: A Simulation-Propose-then-OR-Dispose Approach for Supply Chain Planning
The SPORD method and NetSim platform by JD.com for decoupled supply chain planning using simulation and integer programming.
Towards Faithful Graph Explanations with Synergistic Edge Effects via Granular Balls
Introduction of SeeExplainer, a parameter-free explainer for Graph Neural Networks that captures synergistic edge effects via granular balls.
Multimodal Pretraining for Generalizable EEG Representation Learning
A multimodal EEG foundation model utilizing Mamba architecture and Vision Transformers for generalizable seizure detection.
MSBraM: A Multi-scale Self-supervised Brain Foundation Model for Hierarchical EEG Dynamics Learning
MSBraM, a multi-scale self-supervised brain foundation model designed to learn hierarchical EEG representations through a two-stage pretraining framework.
Flux 3 X Mimic: The Next Generation of Video-Action Models
Discusses Flux 3 X Mimic, a new generation of video-action models.
Nothing works and everyone is euphoric
A reflective or critical piece on the current state of technology or society where 'nothing works' despite general euphoria.
It's getting harder to focus every day
An exploration or discussion regarding the increasing difficulty of maintaining focus in the modern era.
Show HN: A static, client-side tarot calculator for Brazilian Portuguese
A showcase of a static, client-side tarot calculator specifically for Brazilian Portuguese users.