Search: “concepts”

arXiv:2606.07034v1 Announce Type: new Abstract: AI-generated image detectors achieve high accuracy on in-distribution data but often fail on unseen generators. A key obstacle to understanding this fai

arXiv:2609.22174v1 Announce Type: new Abstract: Anticipating emerging research directions is a critical goal of AI-assisted science. Existing methods mainly predict which concepts will co-occur in fut

arXiv:2609.24554v1 Announce Type: new Abstract: Concepts are commonly defined as abstract, compact representations of knowledge and treated as basic units of intelligent behavior. Yet, cognition, psyc

arXiv:2608.28733v1 Announce Type: cross Abstract: Indoor 3D Scene Graphs (3DSGs) represent environments as multi-layer hierarchies that connect observed geometric primitives (e.g., planes) to higher-l

arXiv:2608.15698v1 Announce Type: new Abstract: Visual document retrieval is a critical component of multimodal retrieval-augmented generation, aiming to identify query-relevant pages from document co

arXiv:2606.23312v1 Announce Type: new Abstract: Operating in complex real-world environments requires robots to understand their surroundings on a functional semantic level. This demands a detailed mu

arXiv:2605.09591v1 Announce Type: new Abstract: Segmentation is a fundamental vision task underlying numerous downstream applications. Recent promptable segmentation models, such as Segment Anything M

arXiv:2605.01609v1 Announce Type: new Abstract: We test whether the causal inner product of itet{park2024linear} -- defined by the unembedding covariance Sigma -- enables cross-lingual concept transpo

arXiv:2609.34742v1 Announce Type: new Abstract: Recent studies suggest that large language models encode emotion concepts as structured internal representations, but most existing work focuses on text

arXiv:2503.10547v3 Announce Type: replace Abstract: Concept-based explanations help users understand vision models through recognizable visual patterns. However, existing methods often rely on correla

arXiv:2609.06020v1 Announce Type: new Abstract: Conservation increasingly relies on camera traps that collect more wildlife imagery than experts can manually analyze, making animal re-identification (

arXiv:2407.00966v3 Announce Type: replace Abstract: In traditional models of supervised learning, the goal of a learner-- given examples from an arbitrary joint distribution on R^d imes {pm 1}-- is to

arXiv:2608.10251v1 Announce Type: new Abstract: A transformer's answer lives on one axis: the direction its unembedding reads. Its intermediate states largely do not, and that off-axis position is usu

arXiv:2603.09787v2 Announce Type: replace Abstract: Explainable artificial intelligence (XAI) aims to provide human-interpretable insights into the behavior of deep neural networks (DNNs), typically b

arXiv:2602.17605v2 Announce Type: replace-cross Abstract: In environmental monitoring, data collection is often costly, sparse, and shaped by urgent public-health needs. This is particularly true for

arXiv:2605.08837v1 Announce Type: cross Abstract: Abstract concepts - justice, theory, availability - have no single perceivable referent; in the human brain, their meaning emerges from a web of exper

arXiv:2604.07729v1 Announce Type: cross Abstract: Large language models (LLMs) sometimes appear to exhibit emotional reactions. We investigate why this is the case in Claude Sonnet 4.5 and explore imp

arXiv:2604.07886v1 Announce Type: new Abstract: We investigate how and to what extent hierarchical relations (e.g., Japan subset Eastern Asia subset Asia) are encoded in the internal representat

arXiv:2606.18328v2 Announce Type: replace Abstract: Intelligent robots should not only recover from failures, but also acquire the abstract knowledge needed to avoid them in the future. While reinforc

arXiv:2609.32671v1 Announce Type: cross Abstract: Cross-modal retrieval has been advanced by vision-language pre-trained models that encode images and texts into a shared dense embedding space. While

arXiv:2609.08879v1 Announce Type: new Abstract: Cancer segmentation models can fail silently, generating plausible but incorrect masks that risk missed findings or unnecessary biopsies. A critical que

arXiv:2608.25347v1 Announce Type: new Abstract: The Jacobian lens (J-lens) has been proposed as a way to read verbalizable representations from language models. However, its principle and meaning lack

arXiv:2607.24425v1 Announce Type: new Abstract: Large language models place structured concepts on geometrically faithful manifolds: weekdays lie on a circle, months on another, usually taken to be a

arXiv:2606.28643v1 Announce Type: new Abstract: The widespread adoption of generative AI models has intensified concerns about misuse, including the creation of unsafe or disturbing imagery. To mitiga

arXiv:2606.16196v2 Announce Type: replace-cross Abstract: Deep neural networks have achieved remarkable performance across medical imaging tasks, yet their tendency to overgeneralize under distributio

arXiv:2606.04118v1 Announce Type: new Abstract: This article situates large language models (LLMs) within the longer history of computational approaches to concept analysis in the history, philosophy,

arXiv:2603.29123v2 Announce Type: replace Abstract: The next-token prediction (NTP) objective trains language models to predict a single token at each step, even though many continuations can express

arXiv:2605.10180v1 Announce Type: new Abstract: The rise of text-to-image (T2I) models has increasingly raised concerns regarding the generation of risky content, such as sexual, violent, and copyrigh

arXiv:2510.08638v3 Announce Type: replace-cross Abstract: DINOv2 is routinely deployed to recognize objects, scenes, and actions; yet the nature of what it perceives remains unknown. As a working base

arXiv:2604.19775v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly deployed as autonomous agents capable of reasoning, planning, and acting within interactive environments.

arXiv:2610.08303v1 Announce Type: new Abstract: Current evaluation of multilingual Large Language Models (LLMs) rests on an implicit Translation-Isomorphism Assumption (TIA): that semantic structures

arXiv:2608.22930v1 Announce Type: new Abstract: Agentic AI is a fascinating new tool for software development. It is a huge step forward compared to 'conventional' AI assisted coding, which in turn wa

arXiv:2608.16924v1 Announce Type: cross Abstract: This work-in-progress (WIP) innovative practice category paper presents LLM Odyssey, an open source, browser-based serious gaming platform comprising

arXiv:2608.15323v1 Announce Type: new Abstract: Understanding a model and its learning mechanisms in depth requires identifying when its internal structures become useful, rather than simply looking a

arXiv:2608.11367v1 Announce Type: cross Abstract: Estimating human gaze targets from images in-the-wild is an important and formidable task. Existing approaches primarily employ brittle, multi-stage p

arXiv:2608.04030v1 Announce Type: cross Abstract: Generative artificial intelligence (AI) has transformed text-to-image synthesis, yet its ability to represent specialized engineering domains remains

arXiv:2607.24645v1 Announce Type: cross Abstract: The wide-scale use of sparse autoencoders (SAEs) as interpretability tools is limited by inconsistent links between SAE features and model behavior. F

arXiv:2607.00620v1 Announce Type: cross Abstract: Generalized Category Discovery (GCD) aims to recognize known classes while autonomously discovering novel ones in open-world settings. However, curren

arXiv:2508.14483v4 Announce Type: replace Abstract: We present Vivid-VR, a DiT-based generative video restoration method built upon an advanced T2V foundation model, where ControlNet is leveraged to c

arXiv:2601.22943v2 Announce Type: replace Abstract: Graph coarsening reduces the size of a graph while preserving certain properties. Most existing methods preserve either spectral or spatial characte

arXiv:2604.21511v1 Announce Type: cross Abstract: Learned Sparse IR models, such as SPLADE, offer an excellent efficiency-effectiveness tradeoff. However, they rely on the underlying backbone vocabula

arXiv:2604.11373v1 Announce Type: cross Abstract: Robots are increasingly entering human-interactive scenarios that require understanding of quantity. How intelligent systems acquire abstract numerica

arXiv:2511.19046v2 Announce Type: replace-cross Abstract: Medical image segmentation is fundamental for biomedical discovery. Existing methods lack generalizability and demand extensive, time-consumin

arXiv:2202.06853v2 Announce Type: cross Abstract: To help facilitate a variety of simulations related to healthcare facilities in North Carolina, we have developed an agent-based model (ABM) to accura

arXiv:2608.05558v1 Announce Type: cross Abstract: This paper examines Turing's 1948 report, 'Intelligent Machinery', as an important conceptual source for the later imitation games. Its first contribu

arXiv:2607.10285v2 Announce Type: replace Abstract: We study how unsupervised autoencoders trained on microscopic spin configurations from the Ising model learn macroscopic, theory-relevant variables