cs.AI papers | Gist.Science

M3GCLR: Multi-View Mini-Max Infinite Skeleton-Data Game Contrastive Learning For Skeleton-Based Action Recognition

This paper proposes M3GCLR, a game-theoretic contrastive learning framework that addresses limitations in existing skeleton-based action recognition methods by establishing an Infinite Skeleton-data Game model with a mini-max optimization strategy and dual-loss equilibrium optimizer to effectively handle view discrepancies, adversarial mechanisms, and augmentation perturbations, achieving state-of-the-art performance on multiple benchmarks.

Yanshan Li, Ke Ma, Miaomiao Wei, Linhui Dai2026-03-11🤖 cs.AI

MIL-PF: Multiple Instance Learning on Precomputed Features for Mammography Classification

The paper proposes MIL-PF, a scalable framework that combines frozen foundation model encoders with a lightweight attention-based Multiple Instance Learning head to achieve state-of-the-art mammography classification while significantly reducing computational costs and training complexity.

Nikola Jovišic, Milica Škipina, Nicola Dall'Asen, Dubravko Culibrk2026-03-11🤖 cs.AI

SPAARS: Safer RL Policy Alignment through Abstract Exploration and Refined Exploitation of Action Space

SPAARS is a curriculum learning framework for offline-to-online reinforcement learning that safely improves policies by initially exploring a low-dimensional latent space to ensure sample efficiency and stability, then seamlessly transitioning to raw action space to bypass decoder-induced performance ceilings, thereby achieving superior results over state-of-the-art baselines on both robotic manipulation and locomotion tasks.

Swaminathan S K, Aritra Hazra2026-03-11🤖 cs.AI

Physics-Informed Neural Engine Sound Modeling with Differentiable Pulse-Train Synthesis

This paper introduces the Pulse-Train-Resonator (PTR), a differentiable synthesis model that improves engine sound generation by directly modeling sequential exhaust pressure pulses and physical resonances rather than approximating spectral characteristics, achieving superior reconstruction accuracy and interpretability across diverse engine types.

Robin Doerfler, Lonce Wyse2026-03-11🤖 cs.AI

ICDAR 2025 Competition on End-to-End Document Image Machine Translation Towards Complex Layouts

This paper presents the ICDAR 2025 competition on end-to-end document image machine translation, detailing its dual-track structure for small and large models, participation statistics, and findings that highlight large-model approaches as a promising paradigm for handling complex document layouts.

Yaping Zhang, Yupu Liang, Zhiyang Zhang, Zhiyuan Chen, Lu Xiang, Yang Zhao, Yu Zhou, Chengqing Zong2026-03-11🤖 cs.AI

Reviving ConvNeXt for Efficient Convolutional Diffusion Models

This paper introduces the Fully Convolutional Diffusion Model (FCDM), a ConvNeXt-based architecture that achieves competitive generative performance with significantly fewer computational resources and training steps than Transformer-based counterparts, demonstrating that modern convolutional designs remain a highly efficient alternative for scaling diffusion models.

Taesung Kwon, Lorenzo Bianchi, Lennart Wittke, Felix Watine, Fabio Carrara, Jong Chul Ye, Romann Weber, Vinicius Azevedo2026-03-11🤖 cs.AI

PromptDLA: A Domain-aware Prompt Document Layout Analysis Framework with Descriptive Knowledge as a Cue

This paper introduces PromptDLA, a domain-aware framework that leverages descriptive knowledge as cues to customize prompts for integrating domain priors, thereby overcoming the limitations of directly merging diverse datasets and achieving state-of-the-art performance in Document Layout Analysis across multiple benchmarks.

Zirui Zhang, Yaping Zhang, Lu Xiang, Yang Zhao, Feifei Zhai, Yu Zhou, Chengqing Zong2026-03-11🤖 cs.AI

From Flow to One Step: Real-Time Multi-Modal Trajectory Policies via Implicit Maximum Likelihood Estimation-based Distribution Distillation

This paper proposes a real-time multi-modal trajectory policy framework that distills a Conditional Flow Matching expert into a single-step student using Implicit Maximum Likelihood Estimation and a bi-directional Chamfer distance, thereby eliminating the latency of iterative ODE integration while preserving multi-modal action diversity for high-frequency robotic control.

Ju Dong, Liding Zhang, Lei Zhang, Yu Fu, Kaixin Bai, Zoltan-Csaba Marton, Zhenshan Bing, Zhaopeng Chen, Alois Christian Knoll, Jianwei Zhang2026-03-11🤖 cs.AI

Investigating Gender Stereotypes in Large Language Models via Social Determinants of Health

This study investigates gender bias in Large Language Models within French healthcare contexts, demonstrating that these models rely on embedded stereotypes when processing interactions between gender and other social determinants of health, thereby highlighting the need for context-specific assessments that go beyond evaluating individual factors in isolation.

Trung Hieu Ngo, Adrien Bazoge, Solen Quiniou, Pierre-Antoine Gourraud, Emmanuel Morin2026-03-11🤖 cs.AI

Open-World Motion Forecasting

This paper introduces "Open-World Motion Forecasting," an end-to-end class-incremental framework that predicts future trajectories directly from camera images while mitigating catastrophic forgetting through pseudo-labeling with vision-language models and a novel query feature variance-based replay strategy, enabling continual adaptation to evolving object taxonomies in real-world autonomous driving.

Nicolas Schischka, Nikhil Gosala, B Ravi Kiran, Senthil Yogamani, Abhinav Valada2026-03-11🤖 cs.AI

CERES: A Probabilistic Early Warning System for Acute Food Insecurity

CERES is a novel, open-access, and continuously running probabilistic forecasting system that fuses six global data streams to generate weekly, machine-readable 90-day ahead risk estimates for acute food insecurity across 43 high-risk countries, with a unique commitment to public prospective verification of all predictions.

Tom Danny S. Pedersen2026-03-11🤖 cs.AI

Common Sense vs. Morality: The Curious Case of Narrative Focus Bias in LLMs

This paper introduces the CoMoral benchmark to reveal that current Large Language Models exhibit a critical limitation where they prioritize moral reasoning over commonsense understanding, particularly struggling to detect contradictions involving primary characters due to a pervasive narrative focus bias.

Saugata Purkayastha, Pranav Kushare, Pragya Paramita Pal, Sukannya Purkayastha2026-03-11🤖 cs.AI

AI Act Evaluation Benchmark: An Open, Transparent, and Reproducible Evaluation Dataset for NLP and RAG Systems

This paper introduces an open, transparent, and reproducible dataset and methodology for evaluating NLP and RAG systems on EU AI Act compliance, featuring tasks like risk classification and obligation generation that leverage large language models to address regulatory ambiguities and achieve high performance scores.

Athanasios Davvetas, Michael Papademas, Xenia Ziouvelou, Vangelis Karkaletsis2026-03-11🤖 cs.AI

A Guideline-Aware AI Agent for Zero-Shot Target Volume Auto-Delineation

This paper introduces OncoAgent, a novel guideline-aware AI agent that achieves zero-shot, training-free auto-delineation of clinical target volumes by converting textual clinical guidelines into 3D contours, demonstrating superior adaptability and physician preference over traditional supervised deep learning models.

Yoon Jo Kim, Wonyoung Cho, Jongmin Lee, Han Joo Chae, Hyunki Park, Sang Hoon Seo, Noh Jae Myung, Kyungmi Yang, Dongryul Oh, Jin Sung Kim2026-03-11🤖 cs.AI

Variational Routing: A Scalable Bayesian Framework for Calibrated Mixture-of-Experts Transformers

This paper introduces Variational Mixture-of-Experts Routing (VMoER), a scalable Bayesian framework that confines uncertainty quantification to the expert-selection stage of Mixture-of-Experts Transformers, achieving significant improvements in calibration, stability, and out-of-distribution detection with negligible computational overhead.

Albus Yizhuo Li, Matthew Wicker2026-03-11🤖 cs.AI

Declarative Scenario-based Testing with RoadLogic

This paper introduces RoadLogic, an open-source framework that bridges declarative OpenSCENARIO specifications and executable simulations by combining Answer Set Programming, motion planning, and specification-based monitoring to automatically generate diverse, realistic, and compliant autonomous vehicle testing scenarios.

Ezio Bartocci, Alessio Gambi, Felix Gigler, Cristinel Mateis, Dejan Ničkovic2026-03-11🤖 cs.AI

An Empirical Study and Theoretical Explanation on Task-Level Model-Merging Collapse

This paper identifies and theoretically explains "task-level merging collapse," a phenomenon where incompatible task representations cause catastrophic performance degradation in merged LLMs, demonstrating that representational incompatibility—not parameter-space conflicts—is the primary driver of failure and establishing fundamental limits on task mergeability via rate-distortion theory.

Yuan Cao, Dezhi Ran, Yuzhe Guo, Mengzhou Wu, Simin Chen, Linyi Li, Wei Yang, Tao Xie2026-03-11🤖 cs.AI

EvoDriveVLA: Evolving Autonomous Driving Vision-Language-Action Model via Collaborative Perception-Planning Distillation

EvoDriveVLA is a novel Vision-Language-Action model for autonomous driving that overcomes perception degradation and planning instability through a collaborative distillation framework combining self-anchored visual constraints and oracle-guided trajectory optimization to achieve state-of-the-art performance.

Jiajun Cao, Xiaoan Zhang, Xiaobao Wei, Liyuqiu Huang, Wang Zijian, Hanzhen Zhang, Zhengyu Jia, Wei Mao, Hao Wang, Xianming Liu, Shuchang Zhou Liu, Yang Wang, Shanghang Zhang2026-03-11🤖 cs.AI

Telogenesis: Goal Is All U Need

This paper proposes and validates "Telogenesis," an endogenous attention mechanism that generates adaptive priorities from internal epistemic gaps (ignorance, surprise, and staleness) without external rewards, demonstrating superior coverage and detection latency compared to fixed strategies while spontaneously recovering latent environmental volatility structures.

Zhuoran Deng, Yizhi Zhang, Ziyi Zhang, Wan Shen2026-03-11🤖 cs.AI

GenePlan: Evolving Better Generalized PDDL Plans using Large Language Models

GenePlan is a novel framework that leverages large language models to evolve domain-dependent generalized planners in Python, achieving state-of-the-art performance on PDDL benchmarks while significantly outperforming other LLM-based approaches in both accuracy and efficiency.

Andrew Murray, Danial Dervovic, Alberto Pozanco, Michael Cashmore2026-03-11🤖 cs.AI

← Previous Next →