English
Related papers

Related papers: Geometry-Lite: Interpretable Safety Probing via La…

200 papers

As generative large language models (LLMs) grow more performant and prevalent, we must develop comprehensive enough tools to measure and improve their fairness. Different prompt-based datasets can be used to measure social bias across…

Multi-step zoom-in pipelines are widely used for GUI grounding, yet the intermediate predictions they produce are typically discarded after coordinate remapping. We observe that these intermediate outputs contain a useful confidence signal…

Computer Vision and Pattern Recognition · Computer Science 2026-04-20 Keon Kim , Krish Chelikavada

With the integration of an additional modality, large vision-language models (LVLMs) exhibit greater vulnerability to safety risks (e.g., jailbreaking) compared to their language-only predecessors. Although recent studies have devoted…

Machine Learning · Computer Science 2025-01-07 Ziwei Zheng , Junyao Zhao , Le Yang , Lijun He , Fan Li

Large reasoning models (LRMs) increasingly expose chain-of-thought-like reasoning for transparency, verification, and deliberate problem solving. This creates a safety blind spot: harmful or policy-violating content may appear in reasoning…

Artificial Intelligence · Computer Science 2026-05-08 Xiaomin Li , Jianheng Hou , Zheyuan Deng , Zhiwei Zhang , Taoran Li , Binghang Lu , Bing Hu , Yunhan Zhao , Yuexing Hao

Large Reasoning Models (LRMs) leverage transparent reasoning traces, known as Chain-of-Thoughts (CoTs), to break down complex problems into intermediate steps and derive final answers. However, these reasoning traces introduce unique safety…

Computation and Language · Computer Science 2025-10-16 Changyi Li , Jiayi Wang , Xudong Pan , Geng Hong , Min Yang

Sharpness-aware and gradient-alignment methods have been shown to improve generalization, however each family of methods targets a single geometric property of the loss landscape, while ignoring the other. In this paper, we show that this…

Machine Learning · Computer Science 2026-05-11 Aristotelis Ballas , Christos Diou

Comprehensive situational awareness is essential for autonomous vehicles operating in safety-critical environments, as it enables the identification and mitigation of potential risks. Although recent Multimodal Large Language Models (MLLMs)…

Computer Vision and Pattern Recognition · Computer Science 2026-05-19 Sainithin Artham , Shankar Gangisetty , Avijit Dasgupta , C. V. Jawahar

Large Multimodal Models (LMMs) often struggle with geometric reasoning due to visual hallucinations and a lack of mathematically precise Chain-of-Thought (CoT) data. To address this, we propose the GeoSym Engine, an automated and scalable…

Computer Vision and Pattern Recognition · Computer Science 2026-05-19 Jinhao Jing , Zheng Ma , Jinwei Liang , Qiannian Zhao , Shawn Chen , Jing Yang , Por Lip Yee , Prayag Tiwari , Jingjing Bai , Benyou Wang , Lewei Lu , Zhan Su

Most of the current boundary detection systems rely exclusively on low-level features, such as color and texture. However, perception studies suggest that humans employ object-level reasoning when judging if a particular pixel is a…

Computer Vision and Pattern Recognition · Computer Science 2015-09-22 Gedas Bertasius , Jianbo Shi , Lorenzo Torresani

Despite advancements in splicing detection, practitioners still struggle to fully leverage forensic tools from the literature due to a critical issue: deep learning-based detectors are extremely sensitive to their trained instances. Simple…

Signal Processing · Electrical Eng. & Systems 2024-09-09 Julien Simon de Kergunic , Rony Abecidan , Patrick Bas , Vincent Itier

We introduce a new method to study mixed characteristic deformation of line bundles. In particular, for sufficiently large smooth projective families $f : \mathscr{X} \to \mathscr{S}$ defined over the ring of $N$-integers…

Algebraic Geometry · Mathematics 2026-02-11 David Urbanik , Ziquan Yang

Reliable deployment of language models requires two capabilities that appear distinct but share a common geometric foundation: predicting whether a model will accept targeted behavioral control, and detecting when its internal structure…

Machine Learning · Computer Science 2026-04-30 Prashant C. Raju

Topological methods for comparing weighted graphs are valuable in various learning tasks but often suffer from computational inefficiency on large datasets. We introduce RTD-Lite, a scalable algorithm that efficiently compares topological…

Machine Learning · Computer Science 2025-03-18 Eduard Tulchinskii , Daria Voronkova , Ilya Trofimov , Evgeny Burnaev , Serguei Barannikov

In the rapidly evolving field of Large Language Models (LLMs), ensuring safety is a crucial and widely discussed topic. However, existing works often overlook the geo-diversity of cultural and legal standards across the world. To…

Computation and Language · Computer Science 2024-12-10 Da Yin , Haoyi Qiu , Kung-Hsiang Huang , Kai-Wei Chang , Nanyun Peng

Recent research shows that pre-trained language models (PLMs) suffer from "prompt bias" in factual knowledge extraction, i.e., prompts tend to introduce biases toward specific labels. Prompt bias presents a significant challenge in…

Computation and Language · Computer Science 2024-03-27 Ziyang Xu , Keqin Peng , Liang Ding , Dacheng Tao , Xiliang Lu

Deep generative models can create remarkably photorealistic fake images while raising concerns about misinformation and copyright infringement, known as deepfake threats. Deepfake detection technique is developed to distinguish between real…

Computer Vision and Pattern Recognition · Computer Science 2024-08-22 You-Ming Chang , Chen Yeh , Wei-Chen Chiu , Ning Yu

Fine-tuning continuous prompts for target tasks has recently emerged as a compact alternative to full model fine-tuning. Motivated by these promising results, we investigate the feasibility of extracting a discrete (textual) interpretation…

Recent ObjectNav systems credit large language models (LLMs) for sizable zero-shot gains, yet it remains unclear how much comes from language versus geometry. We revisit this question by re-evaluating an instruction-guided pipeline,…

Robotics · Computer Science 2026-05-07 Matin Aghaei , Lingfeng Zhang , Mohammad Ali Alomrani , Mahdi Biparva , Yingxue Zhang

Large language models (LLMs) employ safety mechanisms to prevent harmful outputs, yet these defenses primarily rely on semantic pattern matching. We show that encoding harmful prompts as coherent mathematical problems -- using formalisms…

Cryptography and Security · Computer Science 2026-05-06 Haoyu Zhang , Mohammad Zandsalimy , Shanu Sushmita

Safe landing is essential in robotics applications, from industrial settings to space exploration. As artificial intelligence advances, we have developed PEACE (Prompt Engineering Automation for CLIPSeg Enhancement), a system that…

Robotics · Computer Science 2025-07-01 Haechan Mark Bong , Rongge Zhang , Antoine Robillard , Giovanni Beltrame