Search: “concepts”

arXiv:2506.18141v3 Announce Type: replace Abstract: We identify semantically coherent, context-consistent network components in large language models (LLMs) using coactivation of sparse autoencoder (S

arXiv:2604.15339v1 Announce Type: cross Abstract: Uncertainty, vagueness, and ambiguity are closely related and often confused concepts in human-robot interaction (HRI). In earlier studies, these conc

arXiv:2604.06172v1 Announce Type: cross Abstract: Cold-start cross-domain recommender (CDR) systems predict a user's preferences in a target domain using only their source-domain behavior, yet existin

arXiv:2604.08295v1 Announce Type: cross Abstract: As AI models grow more complex, explainability is essential for building trust, yet concept-based counterfactual methods still face a trade-off betwee

https://preview.redd.it/3ekngxk224vh1.png?width=1080&format=png&auto=webp&s=9bfe5c92033e17d5b2fb4529f1320c99455a138b I built a GPU compiler and wrote an article about it, focusing on concepts shared b

arXiv:2610.09889v1 Announce Type: new Abstract: Human learning is a dissipative dynamical process: mastery accumulates through practice, decays through forgetting, and propagates across interdependent

arXiv:2610.07270v1 Announce Type: new Abstract: Internal features in LLMs are often interpreted as mechanisms when they track a concept and their manipulation changes a related behavior. Yet steering

arXiv:2610.07583v1 Announce Type: cross Abstract: While AI weather models now rival operational forecasts, how they represent the atmosphere internally remains an open question: feature attribution re

arXiv:2610.06503v1 Announce Type: new Abstract: Text-to-image generative models can produce highly realistic imagery but also raise concerns about harmful misuse. While safety mechanisms exist, system

arXiv:2610.03425v1 Announce Type: new Abstract: Suspicion is an important, yet elusive concept in anti-money laundering and counter-terrorist financing (AML/CFT), which allows for intervention below t

arXiv:2610.03273v1 Announce Type: new Abstract: Reinforcement learning (RL) for learning path recommendation (LPR) faces two coupled obstacles. First, the policy must commit to a sequence of L concept

Auto-generated synthesis of 21430 entries about arxiv-cs-lg

arXiv:2610.00647v1 Announce Type: new Abstract: The representations that language models learn for concepts such as months, weekdays, and places display consistent geometric structure: circles and sad

arXiv:2606.12420v2 Announce Type: replace-cross Abstract: Our concepts of survival and self-interest were built for single, continuous biological lives. These ideas break down when applied to artifici

arXiv:2609.36620v1 Announce Type: new Abstract: Structural reasoning, the ability to recognize and make inferences over the relational structure between objects and concepts, is a hallmark of human co

arXiv:2609.38073v1 Announce Type: cross Abstract: We study exact learning with membership queries for concept classes mathcal Csubseteq{0,1}^N, focusing on the relationships among their deterministic,

arXiv:2609.35599v2 Announce Type: replace Abstract: When recalling lists of concepts (e.g., animals) during the semantic fluency task (SFT), both humans and large language models (LLMs) organise their

arXiv:2609.34451v1 Announce Type: new Abstract: Due to the gigapixel-scale nature of whole-slide images (WSIs), weakly supervised WSI analysis is commonly formulated as a multiple instance learning (M

arXiv:2407.08983v2 Announce Type: replace-cross Abstract: Trustworthiness and interpretability are inextricably linked concepts for LLMs. The more interpretable an LLM is, the more trustworthy it beco

arXiv:2609.29551v1 Announce Type: new Abstract: Sparse autoencoders (SAEs) decompose LLM activations into sparse dictionary atoms, so that each distinct concept gets its own feature. One recurring beh

arXiv:2609.25088v1 Announce Type: cross Abstract: Survival prediction for glioblastoma multiforme (GBM) demands models that are both accurate and interpretable, yet existing approaches treat these obj

arXiv:2609.26352v1 Announce Type: cross Abstract: Concept drift, driven by the rapid evolution of Android malware, severely degrades the performance of machine learning detectors. Current adaptation s

arXiv:2609.24209v1 Announce Type: new Abstract: The Platonic Representation Hypothesis (PRH) claims that independently trained models converge on a shared statistical model of reality, yet recent work

arXiv:2602.01654v2 Announce Type: replace Abstract: Steering vectors (SVs) offer a lightweight way to control large language models (LLMs) at inference time by shifting hidden activations, providing a

arXiv:2609.24782v1 Announce Type: new Abstract: A new concept, termed virtual neural networks, is introduced, where the count of trainable parameters is kept constant, and scalability is attained pure

arXiv:2609.18262v1 Announce Type: new Abstract: Precise retrieval of scientific information is fundamentally constrained by long-tailed concepts and high fact-sensitivity of scientific corpora. These

arXiv:2609.14652v1 Announce Type: cross Abstract: Large Language Model (LLM) applications often transfer domain concepts into the model's context informally, through prompt prose, schema dumps, and ex

arXiv:2609.13948v1 Announce Type: cross Abstract: A central tenet of human cognition is systematicity, the principle that understanding one concept is inherently tied to understanding close variations

arXiv:2607.17768v2 Announce Type: replace Abstract: Camouflage image generation (CIG) focuses on generating visually concealed objects that seamlessly blend into their backgrounds. Existing methods ty

arXiv:2609.10855v1 Announce Type: new Abstract: Vision-language models (VLMs) enable robotic per- ception by associating visual observations with natural-language concepts. Yet their performance in co

arXiv:2609.09432v1 Announce Type: new Abstract: Real-world datasets often exhibit evolving distributions, known as concept drift. Ignoring drift degrades predictive performance, while reliance on fixe

arXiv:2609.06094v1 Announce Type: new Abstract: Red-teaming Text-to-Image (T2I) models is essential for safe deployment, yet it remains particularly challenging against implicit adversarial prompts. U

arXiv:2609.06826v1 Announce Type: cross Abstract: This paper examines the theory of Invariant Structural Learning (ISL), which proposes a non-optimization approach to concept formation. Learning is in

arXiv:2609.04276v1 Announce Type: new Abstract: Vision-language models (VLMs), such as CLIP, have achieved strong performance across multimodal tasks by aligning visual and textual representations in

arXiv:2609.03878v1 Announce Type: cross Abstract: Reconstruction-based anomaly detectors are accurate but opaque: a deep autoencoder flags a sample without telling a practitioner which feature ranges

arXiv:2609.01878v1 Announce Type: new Abstract: Activation steering suppresses undesired behaviors in language models by adding a steering vector to the hidden state during generation. Recent conditio

arXiv:2609.02089v1 Announce Type: new Abstract: Steering aligns large language models (LLMs) by injecting a bias into selected activations at inference time, offering a far cheaper alternative to weig

arXiv:2609.01194v1 Announce Type: new Abstract: Major life events have proven difficult to predict. Does this reflect limits of theory, data, and algorithms, or the large role of chance? We examine on

arXiv:2608.28237v1 Announce Type: new Abstract: Predictive Process Monitoring (PPM) models are increasingly deployed in dynamic environments where concept drift causes the underlying process distribut

arXiv:2608.26176v1 Announce Type: new Abstract: AI systems whose outputs inform real decisions, and increasingly consequential ones, require something that current documentation practice does not prov

arXiv:2608.20810v1 Announce Type: cross Abstract: Multimodal information systems increasingly route generated visual content back through the same vision-language index that informed its production, s

arXiv:2608.19871v1 Announce Type: new Abstract: Compositional Zero-Shot Learning (CZSL) aims to recognize unseen attribute-object compositions by leveraging knowledge of primitive concepts learned fro

arXiv:2604.05853v3 Announce Type: replace Abstract: Modern text-to-image (T2I) models can now render legible, paragraph-length text, enabling a fundamentally new class of misuse. We identify and forma

arXiv:2608.18185v1 Announce Type: cross Abstract: Fine-grained recognition often involves hierarchical label spaces, where a model may be confident about a coarse semantic concept while remaining unce

arXiv:2507.22423v3 Announce Type: replace Abstract: To engineer AGI, we should first capture the essence of intelligence in a species-agnostic form that can be evaluated, while being sufficiently gene

arXiv:2608.10295v1 Announce Type: cross Abstract: Frozen foundation-model (FM) embeddings are increasingly used as off-the-shelf brain-MRI representations, on the assumption that they capture anatomy.