cs.AI papers | Gist.Science

Repurposing Backdoors for Good: Ephemeral Intrinsic Proofs for Verifiable Aggregation in Cross-silo Federated Learning

This paper proposes a lightweight, backdoor-based "Intrinsic Proofs" framework that ensures verifiable aggregation in cross-silo federated learning by embedding ephemeral verification signals into model parameters, thereby achieving high detection rates against malicious servers with over 1000x speedup compared to traditional cryptographic methods while preserving client anonymity and final model utility.

Xian Qin, Xue Yang, Xiaohu Tang2026-03-12🤖 cs.AI

RandMark: On Random Watermarking of Visual Foundation Models

This paper proposes RandMark, a random watermarking method that embeds digital watermarks into the internal representations of visual foundation models using a small encoder-decoder network to enable robust ownership verification with low false detection and misdetection rates.

Anna Chistyakova, Mikhail Pautov2026-03-12🤖 cs.AI

EvoSchema: Towards Text-to-SQL Robustness Against Schema Evolution

This paper introduces EvoSchema, a comprehensive benchmark featuring a novel taxonomy of ten schema perturbation types to evaluate and enhance the robustness of text-to-SQL models against real-world database schema evolution, revealing that table-level changes significantly impact performance and demonstrating that training on diverse schema designs improves model resilience.

Tianshu Zhang, Kun Qian, Siddhartha Sahai, Yuan Tian, Shaddy Garg, Huan Sun, Yunyao Li2026-03-12💬 cs.CL

Structured Linked Data as a Memory Layer for Agent-Orchestrated Retrieval

This paper demonstrates that replacing flat text with structured linked data, specifically enhanced entity pages featuring agent instructions and navigational affordances, significantly improves retrieval accuracy and answer quality in both standard and agentic Retrieval-Augmented Generation systems across multiple domains.

Andrea Volpini, Elie Raad, Beatrice Gamba, David Riccitelli2026-03-12🤖 cs.AI

AlphaFlowTSE: One-Step Generative Target Speaker Extraction via Conditional AlphaFlow

AlphaFlowTSE is a one-step conditional generative model for target speaker extraction that utilizes a JVP-free AlphaFlow objective and interval-consistency training to achieve high-fidelity speech recovery with low latency and improved generalization for downstream ASR tasks.

Duojia Li, Shuhan Zhang, Zihan Qian, Wenxuan Wu, Shuai Wang, Qingyang Hong, Lin Li, Haizhou Li2026-03-12🤖 cs.AI

Probabilistic Verification of Voice Anti-Spoofing Models

This paper introduces PV-VASM, a model-agnostic probabilistic framework that provides formal robustness guarantees and estimates misclassification probabilities for voice anti-spoofing models against various speech synthesis attacks and unseen perturbations.

Evgeny Kushnir, Alexandr Kozodaev, Dmitrii Korzh, Mikhail Pautov, Oleg Kiriukhin, Oleg Y. Rogov2026-03-12🤖 cs.AI

UAV traffic scene understanding: A cross-spectral guided approach and a unified benchmark

This paper proposes CTCNet, a novel cross-spectral guided network featuring a Prototype-Guided Knowledge Embedding module and a Quality-Aware Spectral Compensation module to enhance UAV traffic scene understanding under adverse conditions, accompanied by the introduction of Traffic-VQA, the first large-scale optical-thermal benchmark for cognitive traffic analysis.

Yu Zhang, Zhicheng Zhao, Ze Luo, Chenglong Li, Jin Tang2026-03-12🤖 cs.AI

Towards Robust Speech Deepfake Detection via Human-Inspired Reasoning

This paper introduces HIR-SDD, a novel speech deepfake detection framework that leverages Large Audio Language Models and a human-annotated dataset to achieve robust generalization across audio domains while providing interpretable, human-like reasoning for its predictions.

Artem Dvirniak, Evgeny Kushnir, Dmitrii Tarasov, Artem Iudin, Oleg Kiriukhin, Mikhail Pautov, Dmitrii Korzh, Oleg Y. Rogov2026-03-12🤖 cs.AI

CUPID: A Plug-in Framework for Joint Aleatoric and Epistemic Uncertainty Estimation with a Single Model

CUPID is a novel, plug-in framework that enables joint estimation of aleatoric and epistemic uncertainty in pretrained deep learning models without requiring retraining or architectural modifications, thereby enhancing interpretability and trust in high-stakes AI applications.

Xinran Xu, Xiuyi Fan2026-03-12🤖 cs.LG

Deep Randomized Distributed Function Computation (DeepRDFC): Neural Distributed Channel Simulation

This paper proposes a deep learning-based autoencoder architecture for the Randomized Distributed Function Computation (RDFC) framework that minimizes the total variation distance to an unknown target distribution using only data samples, demonstrating superior communication efficiency compared to traditional data compression methods, particularly under limited common randomness.

Didrik Bergström, Onur Günlü2026-03-12🔢 math

Taking Shortcuts for Categorical VQA Using Super Neurons

This paper introduces "Super Neurons," a training-free method that leverages scalar activations from the first generated token to create highly accurate classifiers for categorical VQA, enabling extreme early exiting from the first layer and achieving up to a 5.10x speedup while improving performance over the original network.

Pierre Musacchio, Jaeyi Jeong, Dahun Kim, Jaesik Park2026-03-12🤖 cs.AI

AI-Enhanced Spatial Cellular Traffic Demand Prediction with Contextual Clustering and Error Correction for 5G/6G Planning

This paper proposes an AI-driven framework that improves 5G/6G traffic demand prediction accuracy and spatial generalization by employing a context-aware two-stage splitting strategy and residual error correction to mitigate neighborhood leakage, as validated by experiments across five Canadian cities.

Mohamad Alkadamani, Colin Brown, Halim Yanikomeroglu2026-03-12⚡ eess

Towards Intelligent Spectrum Management: Spectrum Demand Estimation Using Graph Neural Networks

This paper proposes a hierarchical Graph Attention Network (HR-GAT) model that leverages public deployment records to accurately estimate fine-grained spectrum demand across multiple cities, significantly outperforming existing baselines and providing regulators with actionable insights for efficient spectrum sharing and allocation.

Mohamad Alkadamani, Amir Ghasemi, Halim Yanikomeroglu2026-03-12⚡ eess

Risk-Adjusted Harm Scoring for Automated Red Teaming for LLMs in Financial Services

This paper introduces a risk-aware evaluation framework for Large Language Models in financial services, featuring a domain-specific taxonomy, an automated multi-round red-teaming pipeline, and a Risk-Adjusted Harm Score (RAHS) metric to better capture and quantify severe, operationally actionable security failures that traditional domain-agnostic benchmarks miss.

Fabrizio Dimino, Bhaskarjit Sarmah, Stefano Pasquali2026-03-12💰 q-fin

Nurture-First Agent Development: Building Domain-Expert AI Agents Through Conversational Knowledge Crystallization

This paper proposes Nurture-First Development (NFD), a paradigm that shifts AI agent creation from static engineering to a continuous, conversational co-evolution process with domain experts, utilizing a Knowledge Crystallization Cycle to progressively transform tacit operational dialogue into structured, reusable expertise.

Linghao Zhang2026-03-12🤖 cs.AI

Protein Counterfactuals via Diffusion-Guided Latent Optimization

This paper introduces MCCOP, a framework that leverages a pretrained diffusion model within a joint sequence-structure latent space to generate minimal, biologically plausible protein mutations that flip predictive model outcomes to desired states, thereby bridging the gap between deep learning predictions and actionable protein engineering.

Weronika Kłos, Sidney Bender, Lukas Kades2026-03-12🤖 cs.LG

Speaker Verification with Speech-Aware LLMs: Evaluation and Augmentation

This paper evaluates the weak speaker verification capabilities of existing speech-aware large language models and proposes a lightweight augmentation method using frozen ECAPA-TDNN embeddings and LoRA adapters to significantly enhance speaker discrimination while preserving natural language interfaces.

Thomas Thebaud, Yuzhe Wang, Laureano Moro-Velazquez, Jesus Villalba-Lopez, Najim Dehak2026-03-12🤖 cs.AI

BALD-SAM: Disagreement-based Active Prompting in Interactive Segmentation

This paper introduces BALD-SAM, a principled framework that adapts Bayesian Active Learning by Disagreement to spatial prompt selection in interactive segmentation, enabling a lightweight uncertainty estimation head on frozen foundation models to significantly outperform human and oracle prompting across diverse domains.

Prithwijit Chowdhury, Mohit Prabhushankar, Ghassan AlRegib2026-03-12🤖 cs.AI

On the Reliability of Cue Conflict and Beyond

This paper critiques the instability and ambiguity of current cue-conflict benchmarks for measuring neural network shape-texture bias and introduces REFINED-BIAS, a new framework with balanced cue pairs and ranking-based metrics to enable reliable, interpretable, and fair cross-model comparisons.

Pum Jun Kim, Seung-Ah Lee, Seongho Park, Dongyoon Han, Jaejun Yoo2026-03-12🤖 cs.AI

Human Presence Detection via Wi-Fi Range-Filtered Doppler Spectrum on Commodity Laptops

This paper introduces a novel, low-complexity Human Presence Detection system for commodity laptops that utilizes the built-in Wi-Fi hardware and a new Range-Filtered Doppler Spectrum technique to achieve privacy-preserving, calibration-free occupancy sensing without requiring external sensors or infrastructure.

Jessica Sanson, Rahul C. Shah, Valerio Frascolla2026-03-12⚡ eess

← Previous Next →