#model robustness

try —

11 papers match

cs.AI2026

A Cross-Architecture Audit of Direction-Based Inference-Time Defences in Vision-Language Models

Xiangyu Yin, Tora Bodin, Rohan Menon +1

The paper evaluates five direction‑based inference‑time defenses for vision‑language models across multiple architectures, finding that no single method works best for all models a…

#vision-language models#inference-time defenses#direction-based interventions#model robustness
cs.CV2026

Prior Directions: Why GUI Grounding Gets Locked in the Past

Weile Gong, Zijian Lu, Mingcai Chen +3

The paper investigates how vision-language models can become locked onto outdated textual priors, causing incorrect visual grounding, and identifies recurring latent directions—cal…

#visual grounding#vision-language models#representation analysis#model robustness
cs.CL2026

Pangram 4 Technical Report

Ben Glickenhaus, Katherine Thai, Jenna Russell +4

The paper introduces Pangram 4, a deep‑learning model for detecting AI‑generated text that achieves high accuracy, strong out‑of‑distribution robustness, and improved detection of…

#ai text detection#deep learning#model robustness#adversarial attacks
cs.CL2026

Evaluation of Adversarial Robustness in Arabic Language Models

Anwar Alajmi, Ayed Salman, Imtiaz Ahmad

The paper evaluates how vulnerable five Arabic language models are to various adversarial attacks at character, word, and sentence levels, and examines how adversarial training can…

#adversarial attacks#arabic language models#model robustness#defense techniques
cs.LG2026

Empirical Evaluation of Out-Of-Distribution Performance of Tabular Foundation Models

Malena Loza, David Chushig-Muzo, Eva Milara +3

The paper empirically evaluates how nine tabular foundation models perform under various out-of-distribution shifts using real-world datasets, finding systematic performance degrad…

#tabular data#foundation models#out-of-distribution#distribution shift
cs.LG2026

Random Logit Scaling: Defending Deep Neural Networks Against Black-Box Score-Based Adversarial Example Attacks

Hamid Dashtbani, Mehdi Dousti Gandomani, AmirMahdi Sadeghzadeh

The paper introduces Random Logit Scaling, a plug‑and‑play post‑processing defense that randomly rescales model logits to thwart black‑box score‑based adversarial attacks while kee…

#adversarial attacks#black-box defense#logit scaling#randomization
cs.SE2026

UniCode: Augmenting Evaluation for Code Reasoning

Xinyue Zheng, Haowei Lin, Shaofei Cai +3

The paper presents UniCode, a generative evaluation framework that augments seed coding problems and automatically generates tests to more rigorously assess large language models'…

#code reasoning#large language model evaluation#problem augmentation#automated test generation
cs.CV2026

Barnamala: Parameter-Efficient Handwritten Devanagari Recognition at Benchmark Saturation

Ashish Thapa, Samrat Karki

The paper presents a compact 1.11 M‑parameter convolutional network for handwritten Devanagari character recognition that achieves 99.73% accuracy, matching larger models while bei…

#handwritten character recognition#devanagari script#parameter-efficient models#knowledge distillation
cs.CL2026

Implicit Reasoning Steering via Concept Chaining

Xiao Ye, Sanika Chavan, Yuxi Huang +4

The paper introduces Concept Chaining, a method that creates short natural-language paragraphs linking question entities to a target answer via intermediate concepts, and uses cont…

#language model steering#implicit reasoning#concept chaining#bias amplification
cs.CR2026

Silent Alarm: A J-Space Protocol for Comparing Danger Recognition Across Models and Quantization Levels

Roman Prosvirnin, Victor Minchenkov, Alexey Soldatov +1

The paper introduces JADR, a protocol that examines a language model's internal Jacobian representations (J-space) to assess danger recognition before any response is generated, en…

#safety evaluation#large language models#jacobian analysis#quantization
physics.ao-ph2026

Robustness of Deep Learning Models for PV Power Forecasting under NWP Forecast Errors: A Spatiotemporal and Physically Interpretable Analysis

Dandan Chen, Yan Zhao, Xuepeng Chen

The paper evaluates how deep learning and machine‑learning models for photovoltaic power forecasting behave when faced with realistic, temporally correlated errors in numerical wea…

#photovoltaic forecasting#model robustness#numerical weather prediction errors#deep sequence models

One search, two signals: results blend meaning (embedding similarity, so papers that never use your words still surface) with keyword matches on titles, abstracts and summaries. Free, no sign-in needed.