cs.LG papers | Gist.Science

Jr. AI Scientist and Its Risk Report: Autonomous Scientific Exploration from a Baseline Paper

This paper introduces "Jr. AI Scientist," an autonomous system that mimics a novice researcher's workflow to generate novel, scientifically valuable papers building on real academic works, while simultaneously evaluating its performance through rigorous automated and human assessments to identify both its capabilities and the significant risks and limitations of current AI-driven scientific exploration.

Atsuyuki Miyai, Mashiro Toyooka, Takashi Otonari, Zaiying Zhao, Kiyoharu Aizawa2026-03-10🤖 cs.LG

Distributionally Robust Self Paced Curriculum Reinforcement Learning

The paper proposes Distributionally Robust Self-Paced Curriculum Reinforcement Learning (DR-SPCRL), a method that adaptively schedules the robustness budget as a continuous curriculum to overcome the performance-robustness trade-off inherent in fixed-budget approaches, thereby achieving superior stability and an 11.8% improvement in episodic return under perturbations compared to existing strategies.

Anirudh Satheesh, Keenan Powell, Vaneet Aggarwal2026-03-10🤖 cs.LG

Adaptive Multi-view Graph Contrastive Learning via Fractional-order Neural Diffusion Networks

This paper introduces an augmentation-free multi-view graph contrastive learning framework that leverages learnable fractional-order neural diffusion networks to automatically generate a continuous spectrum of complementary views by adapting the diffusion scale to the data, thereby outperforming state-of-the-art methods in producing robust and expressive embeddings.

Yanan Zhao, Feng Ji, Jingyang Dai, Jiaze Ma, Keyue Jiang, Kai Zhao, Wee Peng Tay2026-03-10🤖 cs.LG

Improving Conditional VAE with Non-Volume Preserving transformations

This paper proposes enhancing Conditional Variational Autoencoders (CVAE) for image generation by treating the decoder's variance as a learnable parameter and employing Non-Volume Preserving (NVP) transformations to better model the conditional latent distribution, thereby significantly improving image quality and diversity compared to existing methods.

Tuhin Subhra De2026-03-10🤖 cs.LG

Tight Robustness Certification Through the Convex Hull of $\ell_0$ Attacks

This paper proposes a novel linear bound propagation method that precisely computes bounds over the convex hull of $\ell_0$ perturbations, significantly improving the scalability and tightness of robustness certification for few-pixel attacks compared to existing state-of-the-art verifiers.

Yuval Shapira, Dana Drachsler-Cohen2026-03-10🤖 cs.LG

Angular Gradient Sign Method: Uncovering Vulnerabilities in Hyperbolic Networks

This paper introduces the Angular Gradient Sign Method, a novel adversarial attack for hyperbolic networks that leverages the geometric decomposition of gradients to apply perturbations solely along angular (semantic) directions, thereby achieving higher fooling rates and revealing unique vulnerabilities in hierarchical embeddings compared to conventional Euclidean-based methods.

Minsoo Jo, Dongyoon Yang, Taesup Kim2026-03-10🤖 cs.LG

Towards Realistic Guarantees: A Probabilistic Certificate for SmoothLLM

This paper introduces a realistic probabilistic framework based on the "(k, $\varepsilon$ )-unstable" assumption to derive data-informed safety certificates for SmoothLLM, overcoming the limitations of strict theoretical guarantees and providing actionable defense guarantees against diverse jailbreaking attacks.

Adarsh Kumarappan, Ayushi Mehrotra2026-03-10🤖 cs.LG

Automating Deception: Scalable Multi-Turn LLM Jailbreaks

This paper introduces an automated pipeline for generating large-scale, psychologically-grounded multi-turn jailbreak datasets using Foot-in-the-Door techniques, revealing that while models like GPT are significantly vulnerable to conversational history, others like Gemini 2.5 Flash demonstrate exceptional resilience against such narrative-based manipulation.

Adarsh Kumarappan, Ananya Mujoo2026-03-10🤖 cs.LG

Shortcut Invariance: Targeted Jacobian Regularization in Disentangled Latent Space

This paper proposes "Shortcut Invariance," a targeted Jacobian regularization method that improves out-of-distribution generalization by injecting anisotropic noise into a disentangled latent space to flatten decision boundaries along shortcut-aligned axes, thereby eliminating the need for explicit shortcut labels or conflicting training samples.

Shivam Pal, Sakshi Varshney, Piyush Rai2026-03-10🤖 cs.LG

Crowdsourcing the Frontier: Advancing Hybrid Physics-ML Climate Simulation via a $50,000 Kaggle Competition

This paper demonstrates that a $50,000 Kaggle competition successfully crowdsourced diverse machine learning architectures for subgrid parameterization, which, when coupled with a full-physics climate model, achieved reproducible online stability and state-of-the-art performance, marking a significant milestone in advancing hybrid physics-ML climate simulations.

Jerry Lin, Zeyuan Hu, Tom Beucler, Katherine Frields, Hannah Christensen, Walter Hannah, Helge Heuer, Peter Ukkonnen, Laura A. Mansfield, Tian Zheng, Liran Peng, Ritwik Gupta, Pierre Gentine, Yusef Al-Naher, Mingjiang Duan, Kyo Hattori, Weiliang Ji, Chunhan Li, Kippei Matsuda, Naoki Murakami, Shlomo Ron, Marec Serlin, Hongjian Song, Yuma Tanabe, Daisuke Yamamoto, Jianyao Zhou, Mike Pritchard2026-03-10🤖 cs.LG

CRAwDAD: Causal Reasoning Augmentation with Dual-Agent Debate

The paper introduces CRAwDAD, a dual-agent debate framework that enhances causal inference in reasoning language models by facilitating structured dialogue and adversarial critique between agents, significantly improving accuracy on the CLadder benchmark across all levels of Pearl's causal ladder.

Finn G. Vamosi, Nils D. Forkert2026-03-10🤖 cs.LG

ForamDeepSlice: A High-Accuracy Deep Learning Framework for Foraminifera Species Classification from 2D Micro-CT Slices

This study introduces ForamDeepSlice, a high-accuracy deep learning framework that combines an ensemble of ConvNeXt-Large and EfficientNetV2-Small models with a rigorous specimen-level split dataset to achieve 95.64% accuracy in classifying foraminifera species from 2D micro-CT slices, while also providing an interactive dashboard for real-time identification and 3D matching.

Abdelghafour Halimi, Ali Alibrahim, Didier Barradas-Bautista, Ronell Sicat, Abdulkader M. Afifi2026-03-10🤖 cs.LG

AltNet: Addressing the Plasticity-Stability Dilemma in Reinforcement Learning

The paper introduces AltNet, a twin-network reinforcement learning framework that restores plasticity through periodic parameter resets without causing performance drops, thereby achieving higher sample efficiency and stability in high-dimensional control tasks compared to existing reset-based methods.

Mansi Maheshwari, John C. Raisbeck, Bruno Castro da Silva2026-03-10🤖 cs.LG

MSPT: Efficient Large-Scale Physical Modeling via Parallelized Multi-Scale Attention

The paper introduces MSPT, a novel architecture that leverages ball trees for efficient spatial partitioning and a dual-scale attention mechanism to enable scalable, memory-efficient, and high-accuracy physical simulations of millions of points on a single GPU across diverse industrial applications.

Pedro M. P. Curvo, Jan-Willem van de Meent, Maksim Zhdanov2026-03-10🤖 cs.LG

Dual Randomized Smoothing: Beyond Global Noise Variance

This paper proposes Dual Randomized Smoothing, a novel framework that overcomes the limitations of global noise variance by introducing input-dependent noise variances via a locally constant variance estimator, thereby achieving superior certified robustness across both small and large perturbation radii on CIFAR-10 and ImageNet.

Chenhao Sun, Yuhao Mao, Martin Vechev2026-03-10🤖 cs.LG

Dual-Robust Cross-Domain Offline Reinforcement Learning Against Dynamics Shifts

This paper introduces DROCO, a novel dual-robust cross-domain offline reinforcement learning algorithm that addresses both train-time and test-time dynamics shifts by employing a robust cross-domain Bellman operator alongside dynamic value penalty and Huber loss to enhance policy robustness and prevent value estimation errors.

Zhongjian Qiao, Rui Yang, Jiafei Lyu, Xiu Li, Zhongxiang Dai, Zhuoran Yang, Siyang Gao, Shuang Qiu2026-03-10🤖 cs.LG

Evolving Diffusion and Flow Matching Policies for Online Reinforcement Learning

The paper introduces GoRL, an algorithm-agnostic framework that stabilizes online reinforcement learning with expressive generative policies by decoupling optimization in a tractable latent space from action synthesis via a conditional generative decoder, achieving superior performance on challenging continuous-control tasks.

Chubin Zhang, Zhenglin Wan, Feng Chen, Fuchao Yang, Lang Feng, Yaxin Zhou, Xingrui Yu, Yang You, Ivor Tsang, Bo An2026-03-10🤖 cs.LG

Beyond Additivity: Sparse Isotonic Shapley Regression toward Nonlinear Explainability

This paper introduces Sparse Isotonic Shapley Regression (SISR), a unified framework that simultaneously learns a monotonic transformation to restore additivity and enforces sparsity constraints to provide robust, efficient, and theoretically grounded feature attributions for nonlinear, high-dimensional Explainable AI.

Jialai She2026-03-10🤖 cs.LG

Two-Step Data Augmentation for Masked Face Detection and Recognition: Turning Fake Masks to Real

This paper presents a two-step generative data augmentation framework combining rule-based mask warping and unpaired image-to-image translation to address the scarcity of masked face datasets, achieving performance improvements with minimal training data while explicitly noting its origins as a resource-constrained coursework project that lacked downstream quantitative evaluation.

Yan Yang, George Bebis, Mircea Nicolescu2026-03-10🤖 cs.LG

SALVE: Sparse Autoencoder-Latent Vector Editing for Mechanistic Control of Neural Networks

The paper introduces SALVE, a unified framework that combines sparse autoencoders and feature-level saliency mapping to discover, validate, and precisely edit neural network weights, enabling interpretable and robust control over both convolutional and transformer-based models.

Vegard Flovik2026-03-10🤖 cs.LG

← Previous Next →

cs.LG