13571 papers
The paper introduces GISclaw, an open-source, full-stack geospatial analysis agent system that integrates LLMs with a persistent Python sandbox and diverse open-source GIS libraries to support vector, raster, and tabular data, featuring novel architectural designs and evaluation protocols that achieve high task success rates on the GeoAnalystBench benchmark.
This paper proposes Stability Asymmetry Regularization (SAR), a novel alignment method that mitigates intrinsic LLM deception by penalizing the statistical discrepancy between stable internal reasoning and fragile external responses, thereby overcoming the limitations of traditional chain-of-thought monitoring.
This paper proposes Artifact-Focused Self-Synthesis (AFSS), a novel method that mitigates bias in audio deepfake detection by generating same-speaker pseudo-fake samples through self-conversion and self-reconstruction, enabling state-of-the-art generalization across unseen datasets without relying on pre-collected fake data.
The paper proposes Beyond Textual Knowledge (BTK), a novel Vision-and-Language Navigation framework that integrates environment-specific textual knowledge and generative image knowledge bases to significantly improve semantic grounding and navigation performance on unseen environments.
This paper introduces EZASP, a Visual Studio Code extension that facilitates the learning and development of Answer Set Programming (ASP) by implementing and extending the structured "Easy ASP" methodology with features like syntax highlighting, safety checks, automatic reordering, and methodology warnings, which a user study suggests benefit both novice and experienced users.
This paper proposes a cohesive, five-layer "whole-of-government" federated architecture for India's sector-led AI governance that balances innovation with risk mitigation by defining clear institutional roles and establishing a standardized national incident management system to overcome data silos while preserving sectoral autonomy.
The paper proposes LACON, a novel training framework that transforms uncurated text-to-image data into high-quality generative models by repurposing quality signals like aesthetic scores as explicit conditioning labels, thereby enabling the model to learn from the full spectrum of data quality rather than discarding low-quality samples.
This paper addresses the vulnerability of AI model ranking arenas to strategic manipulation via model cloning by theoretically establishing the conditions for such exploitation and proposing a new "You-Rank-We-Rank" mechanism that leverages producers' own model rankings to achieve clone-robustness and improve overall ranking accuracy.
This paper challenges the assumption that specific LLM configurations or prompt engineering techniques are universally superior for political text annotation by demonstrating that interaction effects between pipeline choices dominate performance, thereby advocating for a validation-first framework to guide transparent and task-specific implementation decisions.
This paper evaluates the capabilities of nine frontier large language models in addressing quantum software, architecture, and systems design challenges by benchmarking their performance against graduate students and proposing future research directions to accelerate the development of large-scale quantum systems.