cs.AI papers | Gist.Science

Balancing Interpretability and Performance in Motor Imagery EEG Classification: A Comparative Study of ANFIS-FBCSP-PSO and EEGNet

This study compares a transparent ANFIS-FBCSP-PSO model with the deep-learning benchmark EEGNet on motor imagery EEG data, revealing that the fuzzy-neural approach offers superior within-subject performance and interpretability while EEGNet demonstrates stronger cross-subject generalization, thereby providing practical guidance for selecting BCI systems based on specific design priorities.

Farjana Aktar, Mohd Ruhul Ameen, Akif Islam, Md Ekramul HamidTue, 10 Ma🤖 cs.LG

Towards Efficient Federated Learning of Networked Mixture-of-Experts for Mobile Edge Computing

This paper proposes a Networked Mixture-of-Experts (NMoE) system and a hybrid federated learning framework that enable collaborative inference and efficient, privacy-preserving training of large AI models on resource-constrained mobile edge devices by leveraging neighbor expertise and balancing personalization with generalization.

Song Gao, Songyang Zhang, Shusen Jing, Shuai Zhang, Xiangwei Zhou, Yue Wang, Zhipeng CaiTue, 10 Ma🤖 cs.LG

FATE: A Formal Benchmark Series for Frontier Algebra of Multiple Difficulty Levels

The paper introduces FATE, a new formal algebra benchmark series spanning from undergraduate exercises to PhD-level research problems, which reveals that current state-of-the-art LLMs struggle significantly with formalizing advanced mathematical reasoning, achieving near-zero accuracy on the most difficult tasks despite stronger natural-language performance.

Jiedong Jiang, Wanyi He, Yuefeng Wang, Guoxiong Gao, Yongle Hu, Jingting Wang, Nailin Guan, Peihao Wu, Chunbo Dai, Liang Xiao, Bin DongTue, 10 Ma🤖 cs.LG

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 AizawaTue, 10 Ma🤖 cs.LG

HatePrototypes: Interpretable and Transferable Representations for Implicit and Explicit Hate Speech Detection

This paper introduces HatePrototypes, a parameter-free method using class-level vector representations derived from as few as 50 examples per class to enable efficient, interpretable, and transferable detection of both explicit and implicit hate speech without requiring repeated fine-tuning.

Irina Proskurina, Marc-Antoine Carpentier, Julien VelcinTue, 10 Ma💬 cs.CL

Think, Speak, Decide: Language-Augmented Multi-Agent Reinforcement Learning for Economic Decision-Making

The paper proposes LAMP, a language-augmented multi-agent reinforcement learning framework that employs a "Think-Speak-Decide" pipeline to integrate unstructured language with numerical data, significantly outperforming existing baselines in economic decision-making through improved cumulative returns, robustness, and interpretability.

Heyang Ma, Qirui Mi, Qipeng Yang, Zijun Fan, Bo Li, Haifeng ZhangTue, 10 Ma💻 cs

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 MehrotraTue, 10 Ma🤖 cs.LG

Enhancing low energy reconstruction and classification in KM3NeT/ORCA with transformers

This paper proposes enhancing low-energy neutrino reconstruction and classification in the KM3NeT/ORCA telescope by utilizing transformer models with physics-informed attention masks to incorporate explicit detector and physical knowledge, thereby improving performance and cross-configuration fine-tuning capabilities.

Iván Mozún Mateo (on behalf of the KM3NeT collaboration)Tue, 10 Ma🔭 astro-ph

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 MujooTue, 10 Ma🤖 cs.LG

RadDiff: Retrieval-Augmented Denoising Diffusion for Protein Inverse Folding

This paper introduces RadDiff, a novel retrieval-augmented denoising diffusion model that effectively integrates up-to-date protein knowledge into the inverse folding process, significantly outperforming existing methods in sequence recovery rate and foldability while offering greater parameter efficiency and scalability.

Jin Han, Tianfan Fu, Wu-Jun LiTue, 10 Ma💻 cs

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. AfifiTue, 10 Ma🤖 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 SilvaTue, 10 Ma🤖 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 VechevTue, 10 Ma🤖 cs.LG

Process-Centric Analysis of Agentic Software Systems

This paper introduces Graphectory, a graph-based framework for analyzing the stochastic execution trajectories of agentic software systems, which reveals that richer prompts and stronger models yield more complex reasoning patterns while enabling real-time monitoring and intervention that significantly improves problem resolution rates and efficiency.

Shuyang Liu, Yang Chen, Rahul Krishna, Saurabh Sinha, Jatin Ganhotra, Reyhan JabbarvandTue, 10 Ma💬 cs.CL

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 SheTue, 10 Ma🤖 cs.LG

Parallel Decoder Transformer: Planner-Seeded Latent Coordination for Synchronized Parallel Decoding

The Parallel Decoder Transformer (PDT) introduces a frozen-trunk architecture that enables synchronized parallel decoding by integrating a planner-seeded latent workspace and a dynamic notes bus, allowing multiple output streams to internally coordinate, resolve ownership, and synchronize generation without external orchestration.

Logan RobbinsTue, 10 Ma💬 cs.CL

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 FlovikTue, 10 Ma🤖 cs.LG

Adaptation of Agentic AI: A Survey of Post-Training, Memory, and Skills

This survey proposes a unified four-paradigm framework to categorize and analyze the fragmented landscape of agentic AI adaptation, distinguishing between agent-side improvements (A1/A2) and tool-side enhancements (T1/T2) to systematically review post-training methods, memory architectures, and skill systems while evaluating their trade-offs and outlining future challenges.

Pengcheng Jiang, Jiacheng Lin, Zhiyi Shi, Zifeng Wang, Luxi He, Yichen Wu, Ming Zhong, Peiyang Song, Qizheng Zhang, Heng Wang, Xueqiang Xu, Hanwen Xu, Pengrui Han, Dylan Zhang, Jiashuo Sun, Chaoqi Yang, Kun Qian, Tian Wang, Changran Hu, Manling Li, Quanzheng Li, Hao Peng, Sheng Wang, Jingbo Shang, Chao Zhang, Jiaxuan You, Liyuan Liu, Pan Lu, Yu Zhang, Heng Ji, Yejin Choi, Dawn Song, Jimeng Sun, Jiawei HanTue, 10 Ma💬 cs.CL

Meta-RL Induces Exploration in Language Agents

The paper introduces LaMer, a Meta-RL framework that enhances language agents' ability to actively explore and adapt to novel environments at test time through cross-episode training and in-context policy reflection, significantly outperforming standard RL baselines across diverse tasks.

Yulun Jiang, Liangze Jiang, Damien Teney, Michael Moor, Maria BrbicTue, 10 Ma🤖 cs.LG

ReDepth Anything: Test-Time Depth Refinement via Self-Supervised Re-lighting

Re-Depth Anything is a test-time self-supervised framework that enhances monocular depth estimation by fusing foundation models with large-scale 2D diffusion priors to perform label-free refinement via generative re-lighting and Score Distillation Sampling, achieving state-of-the-art results without direct depth tensor optimization.

Ananta R. Bhattarai, Helge RhodinTue, 10 Ma🤖 cs.LG

← Previous Next →