Search: “concepts”

arXiv:2609.39625v1 Announce Type: cross Abstract: Sparse autoencoders (SAEs) reveal visual structure in diffusion transformers (DiTs), but interpreting a feature does not establish whether it can be u

arXiv:2609.38448v1 Announce Type: new Abstract: Open-ended LLM homogeneity can create false plurality when several systems appear to offer independent perspectives while returning the same familiar de

arXiv:2609.39807v1 Announce Type: cross Abstract: Lie detection probes aim to predict from a language model's internal states whether its output is truthful or dishonest. However, role-play complicate

arXiv:2504.14015v2 Announce Type: replace-cross Abstract: We introduce 'causal pieces', a novel concept for analysing spiking neural networks (SNNs), inspired by 'linear pieces' used to study expressi

arXiv:2609.37458v1 Announce Type: new Abstract: Industrial standards often encode the same engineering concept through incompatible hierarchies, identifiers, roles, and structural constraints, so the

arXiv:2604.05468v3 Announce Type: replace Abstract: Temporal knowledge graph (TKG) extrapolation is an important task that aims to predict future facts through historical interaction information withi

arXiv:2609.37680v1 Announce Type: cross Abstract: One of the current premises of mechanistic interpretability research is that detailed accounts of the geometry of neural network representations can t

arXiv:2609.34475v1 Announce Type: new Abstract: LLMs cannot forget the way we delete a file. Strangely, we are asked to remove something that was never put anywhere in particular. What the model took

arXiv:2609.32328v1 Announce Type: new Abstract: Data unlearning in diffusion models aims to remove the influence of specific training examples without suppressing the broader concepts they represent.

arXiv:2609.34408v1 Announce Type: new Abstract: Large Vision-Language Models (LVLMs) have shown strong promise for multimodal reasoning, yet often struggle with tasks requiring concepts beyond what is

arXiv:2609.34058v1 Announce Type: new Abstract: AI systems often feel brittle and fragmented. A large language model (LLM) may correctly explain a concept but fail to apply it, or follow safety instru

arXiv:2609.33490v1 Announce Type: cross Abstract: Conditional independence (CI) is a fundamental concept in statistics and machine learning. Recent advances in conditional generative modeling provide

arXiv:2609.35341v1 Announce Type: new Abstract: Evaluating semantic similarity between videos is a fundamental challenge in computer vision, essential for tasks ranging from out-of-distribution (OOD)

arXiv:2609.35020v1 Announce Type: new Abstract: Vision Sparse Autoencoders (SAEs) have become a popular tool in Mechanistic Interpretability due to their presumed ability to disentangle complex featur

arXiv:2609.30980v1 Announce Type: cross Abstract: Text-to-image diffusion models enable data-efficient 'mimicry' attacks, wherein adversaries fine-tune the model on a handful of public photos to synth

arXiv:2609.31469v1 Announce Type: cross Abstract: Shapley values, a solution concept from cooperative game theory, have recently become a standard tool for feature credit allocation in machine learnin

arXiv:2609.29474v1 Announce Type: cross Abstract: Public software repositories, like GitHub and Software Heritage Archive, store billions of files, yet extracting their implicit engineering knowledge

arXiv:2501.09223v3 Announce Type: replace-cross Abstract: This is a book about large language models. As indicated by the title, it primarily focuses on foundational concepts rather than comprehensive

arXiv:2609.27356v1 Announce Type: new Abstract: A region can overlap a target object yet contribute more to another class. We test regions selected by Cluster-based Concept Importance (CCI) in frozen

arXiv:2609.27593v1 Announce Type: cross Abstract: Concept erasure methods that operate via linear projection assume that features occupy separable subspaces. We show this assumption fails under dense

arXiv:2609.22135v1 Announce Type: new Abstract: Omni-modal large language models integrate text, audio, and image signals into a shared residual stream, where concepts such as emotion can be linearly

arXiv:2609.22208v1 Announce Type: new Abstract: Sofroniew et al. (2026) report that emotion concepts in Claude Sonnet 4.5 are represented as vectors whose geometry mirrors human affect psychology. We

arXiv:2609.19451v1 Announce Type: new Abstract: The Mobile Unified Multimodal Understanding (MUMU) Challenge requires a single efficient model to jointly perform multi-concept image tagging, open-voca

arXiv:2609.19588v1 Announce Type: new Abstract: Mechanical intelligence, loosely defined as the reduction in control burden afforded by a robot's physical form, has become a prominent concept in robot

arXiv:2609.18080v1 Announce Type: new Abstract: Linear probes can decode safety-relevant concepts such as truthfulness from language-model activations, but probe accuracy may show only decodability, n

arXiv:2609.18444v1 Announce Type: new Abstract: Weakly supervised class-incremental semantic segmentation (WILSS) aims to train a segmentation model over multiple steps, each introducing new concepts

arXiv:2609.17655v1 Announce Type: cross Abstract: In an important recent work, Blanc (2026) gave an algorithm for robustly learning Boolean concept classes with respect to a fixed distribution that ou

arXiv:2609.19074v1 Announce Type: cross Abstract: Reinforcement learning (RL) is an exciting concept as well as a remarkable success story worth sharing. However, RL builds on rather complex interacti

arXiv:2609.16446v1 Announce Type: new Abstract: Federated learning (FL) in healthcare faces pronounced heterogeneity and temporal concept drift across clinical centers, where evolving patient populati

arXiv:2609.16822v1 Announce Type: new Abstract: This study covers foundational concepts for enhancing plan-execution flexibility, including partial-order planning, the producer-consumer-threat formali

arXiv:2509.07801v5 Announce Type: replace Abstract: Structured information extraction from scientific literature is crucial for capturing core concepts and emerging trends in specialized fields. While

arXiv:2609.14572v1 Announce Type: cross Abstract: Teaching abstract theoretical computer science (TCS) concepts such as algorithm analysis and complexity theory is challenging because students must ha

arXiv:2609.15292v1 Announce Type: new Abstract: Automatic Item Generation (AIG) is pivotal for personalized education, yet guaranteeing the pedagogical value of generated items remains a bottleneck. E

arXiv:2609.15022v1 Announce Type: new Abstract: Defense is a knowledge-intensive domain that requires precise understanding of specialized terminology, doctrinal concepts, operational procedures, and

arXiv:2609.12254v1 Announce Type: new Abstract: The climate literature has grown faster than review teams can read it. That gap matters most for a concept like the environmental social tipping point,

arXiv:2609.12403v1 Announce Type: cross Abstract: Cognitive Diagnosis Models (CDMs) play a pivotal role in personalized online learning. Traditional CDMs rely on discrete, ID-based embeddings to repre

arXiv:2406.06802v4 Announce Type: replace-cross Abstract: Motivated by the concept of satisficing in decision-making, we consider the problem of satisficing regret minimization in bandit optimization.

arXiv:2609.11959v1 Announce Type: cross Abstract: Space is a foundational concept across mathematics, physics, spatial cognition, urban science, and embodied intelligence, yet these fields often treat

arXiv:2310.10092v4 Announce Type: replace Abstract: This paper explores the use of linear aggregation to protect the privacy of sensitive training labels through the concept of label differential priv

arXiv:2609.08254v1 Announce Type: new Abstract: Learning direct current circuit concepts requires learners to connect invisible physical quantities, such as current, voltage, resistance, and power, wi

arXiv:2609.09556v1 Announce Type: cross Abstract: Neural networks can leverage feature superposition to encode more concepts than dimensions, but cross-feature interference constrains the linear acces

arXiv:2609.07483v1 Announce Type: new Abstract: Modus Tollens (MT) is a classical logical inference rule, while counterfactuals are hypothetical statements that are contrary to facts, and counterfactu

arXiv:2609.05800v1 Announce Type: new Abstract: Activation steering controls LLM behavior at inference time by adding learned directions to hidden states, but existing methods handle one concept at a

arXiv:2609.07660v1 Announce Type: cross Abstract: The concept of Markov chain Monte Carlo (MCMC) cycles, an analogy to cyclic processes in heat engines, is presented in order to examine Bayesian infer

arXiv:2609.05583v1 Announce Type: new Abstract: Vision-Language Models (VLMs) are reshaping computer vision by aligning visual and textual embeddings, allowing models to recognize visual concepts and

arXiv:2609.06341v1 Announce Type: new Abstract: Linear algebra provides the framework of concepts (matrix rank, singular value decomposition (SVD), and eigendecomposition) that modern artificial intel