cs.AI papers | Gist.Science

FBFL: A Field-Based Coordination Approach for Data Heterogeneity in Federated Learning

This paper proposes Field-Based Federated Learning (FBFL), a novel macroprogramming-driven approach that utilizes distributed spatial leader election and self-organizing hierarchical architectures to effectively address data heterogeneity and centralization bottlenecks, demonstrating superior performance over state-of-the-art methods like FedAvg, FedProx, and Scaffold in non-IID scenarios while maintaining resilience against server failures.

Davide Domini, Gianluca Aguzzi, Lukas Esterle + 1 more2026-03-06💻 cs

Generative Models in Decision Making: A Survey

This survey proposes a principled, function-centric taxonomy grounded in Control as Inference to unify generative models in decision making into four distinct roles—Controllers, Modelers, Optimizers, and Evaluators—while critically analyzing their applications in high-stakes domains and outlining challenges for developing Generalist Physical Intelligence.

Xinyu Shao, Jianping Zhang, Haozhi Wang + 9 more2026-03-06💻 cs

Heuristics for AI-driven Graphical Asset Generation Tools in Game Design and Development Pipelines: A User-Centred Approach

This paper addresses the lack of guidelines for integrating AI-driven generative tools into game development pipelines by conducting a user study with 16 designers and developers, which revealed preferences for early-stage use and high-volume iteration, ultimately leading to a proposed set of heuristics for creating user-centered tools that ensure seamless integration and data compatibility.

Kaisei Fukaya, Damon Daylamani-Zad, Harry Agius2026-03-06💻 cs

The StudyChat Dataset: Analyzing Student Dialogues With ChatGPT in an Artificial Intelligence Course

This paper introduces StudyChat, a publicly available dataset of 16,851 annotated student interactions with an LLM-powered tutoring chatbot in an AI course, revealing that using the tool for conceptual understanding and coding assistance correlates with better academic performance, whereas using it to bypass learning objectives leads to lower exam scores.

Hunter McNichols, Fareya Ikram, Andrew Lan2026-03-06💻 cs

BACE-RUL: A Bi-directional Adversarial Network with Covariate Encoding for Machine Remaining Useful Life Prediction

This paper introduces BACE-RUL, a bi-directional adversarial network with covariate encoding that predicts machine Remaining Useful Life using only current sensor measurements to overcome the limitations of prior knowledge and temporal mining, demonstrating superior performance over state-of-the-art methods on real-world datasets.

Zekai Zhang, Dan Li, Shunyu Wu + 4 more2026-03-06💻 cs

Safety Mirage: How Spurious Correlations Undermine VLM Safety Fine-Tuning and Can Be Mitigated by Machine Unlearning

This paper identifies the "safety mirage" in Vision-Language Models, where supervised fine-tuning creates spurious correlations that leave models vulnerable to simple attacks and prone to over-refusal, and proposes machine unlearning as a superior alignment strategy that significantly reduces attack success rates and unnecessary rejections while preserving general capabilities.

Yiwei Chen, Yuguang Yao, Yihua Zhang + 3 more2026-03-06💻 cs

Advancing Problem-Based Learning in Biomedical Engineering in the Era of Generative AI

This paper presents a three-year case study demonstrating how an advanced Problem-Based Learning framework successfully integrated biomedical AI education for 248 students at Georgia Tech and Emory, overcoming challenges like diverse backgrounds and data privacy while fostering significant research productivity and providing a scalable roadmap for curriculum development.

Micky C. Nnamdi, J. Ben Tamo, Benoit Marteau + 2 more2026-03-06💻 cs

Assessing the Impact of Code Changes on the Fault Localizability of Large Language Models

This paper introduces a large-scale, mutation-based evaluation framework to assess the robustness of Large Language Models in fault localization, revealing that their reasoning is often brittle and reliant on syntactic cues rather than deep semantic understanding, as evidenced by a 78% failure rate when subjected to semantic-preserving code changes.

Sabaat Haroon, Ahmad Faraz Khan, Ahmad Humayun + 5 more2026-03-06💻 cs

ms-Mamba: Multi-scale Mamba for Time-Series Forecasting

This paper introduces ms-Mamba, a novel multi-scale architecture that employs Mamba blocks with varying sampling rates to capture temporal information at different scales, achieving state-of-the-art forecasting performance with greater efficiency than existing Transformer and Mamba-based models.

Yusuf Meric Karadag, Ismail Talaz, Ipek Gursel Dino + 1 more2026-03-06💻 cs

Enhancing multimodal analogical reasoning with Logic Augmented Generation

This paper introduces a Logic Augmented Generation (LAG) framework that combines semantic knowledge graphs with prompt heuristics to enhance multimodal analogical reasoning, demonstrating superior performance and explainability in metaphor detection tasks compared to existing baselines and human benchmarks, while also highlighting current limitations in domain-specific understanding.

Anna Sofia Lippolis, Andrea Giovanni Nuzzolese, Aldo Gangemi2026-03-06💻 cs

Foam-Agent: Towards Automated Intelligent CFD Workflows

The paper introduces Foam-Agent, a multi-agent framework leveraging large language models and retrieval-augmented generation to automate end-to-end computational fluid dynamics workflows from natural language prompts, achieving an 88.2% execution success rate on diverse simulation tasks without expert intervention.

Ling Yue, Nithin Somasekharan, Tingwen Zhang + 4 more2026-03-06💻 cs

ReactDance: Hierarchical Representation for High-Fidelity and Coherent Long-Form Reactive Dance Generation

ReactDance is a novel diffusion framework that achieves high-fidelity, coherent long-form reactive dance generation by employing Hierarchical Finite Scalar Quantization for fine-grained spatial control and a Blockwise Local Context strategy for efficient, temporally consistent sequence synthesis.

Jingzhong Lin, Xinru Li, Yuanyuan Qi + 8 more2026-03-06💻 cs

Balancing Progress and Safety: A Novel Risk-Aware Objective for RL in Autonomous Driving

This paper proposes a novel, hierarchical, and risk-aware reward function for reinforcement learning in autonomous driving that integrates normalized objectives and an extended Responsibility-Sensitive Safety model, resulting in a 21% reduction in collision rates while maintaining high route progress in unsignalized intersection scenarios.

Ahmed Abouelazm, Jonas Michel, Helen Gremmelmaier + 3 more2026-03-06💻 cs

Boundary-Guided Trajectory Prediction for Road Aware and Physically Feasible Autonomous Driving

This paper proposes a novel boundary-guided trajectory prediction framework that leverages HD map constraints and kinematic acceleration profiles to generate physically feasible, on-road, and robust autonomous driving predictions, significantly reducing off-road errors and improving generalization compared to existing baselines.

Ahmed Abouelazm, Mianzhi Liu, Christian Hubschneider + 3 more2026-03-06💻 cs

Automatic Curriculum Learning for Driving Scenarios: Towards Robust and Efficient Reinforcement Learning

This paper proposes an automatic curriculum learning framework that employs a "teacher" to dynamically generate driving scenarios with adaptive complexity based on an agent's current capabilities, thereby overcoming the inefficiencies of fixed scenarios and domain randomization to achieve faster convergence and superior generalization in end-to-end autonomous driving reinforcement learning.

Ahmed Abouelazm, Tim Weinstein, Tim Joseph + 2 more2026-03-06💻 cs

Ice Cream Doesn't Cause Drowning: Benchmarking LLMs Against Statistical Pitfalls in Causal Inference

This paper introduces CausalPitfalls, a comprehensive benchmark designed to rigorously evaluate and expose the significant limitations of large language models in handling statistical causal inference pitfalls, such as Simpson's paradox, through both direct and code-assisted prompting protocols.

Jin Du, Li Chen, Xun Xian + 6 more2026-03-06💻 cs

ShIOEnv: A Command Evaluation Environment for Grammar-Constrained Synthesis and Execution Behavior Modeling

This paper introduces ShIOEnv, a grammar-constrained, self-supervised Bash environment that generates 2.1 million system-grounded input-output pairs to significantly improve the accuracy of modeling complex command-line execution behaviors compared to prior execution-free approaches.

Jarrod Ragsdale, Rajendra Boppana2026-03-06💻 cs

VTool-R1: VLMs Learn to Think with Images via Reinforcement Learning on Multimodal Tool Use

VTool-R1 is a novel framework that leverages reinforcement learning to train vision-language models to generate multimodal chains of thought by strategically interleaving text with intermediate visual reasoning steps using Python-based editing tools, thereby enhancing performance on structured visual tasks without requiring process-based supervision.

Mingyuan Wu, Jingcheng Yang, Jize Jiang + 6 more2026-03-06💻 cs

SealQA: Raising the Bar for Reasoning in Search-Augmented Language Models

The paper introduces SealQA, a new benchmark comprising three challenging flavors (Seal-0, Seal-Hard, and LongSeal) designed to evaluate search-augmented language models on fact-seeking tasks with noisy or conflicting web results, revealing that even frontier models struggle significantly with reasoning accuracy, robustness to noise, and long-context document retrieval.

Thinh Pham, Nguyen Nguyen, Pratibha Zunjare + 3 more2026-03-06💻 cs

RoboPARA: Dual-Arm Robot Planning with Parallel Allocation and Recomposition Across Tasks

The paper introduces RoboPARA, a novel LLM-driven framework that utilizes dependency graph generation and re-traversal to optimize dual-arm task parallelism, accompanied by the new X-DAPT dataset for evaluation, demonstrating superior efficiency and reliability in complex multitasking scenarios compared to existing methods.

Shiying Duan, Pei Ren, Nanxiang Jiang + 5 more2026-03-06💻 cs

← Previous Next →