Search: “concepts”

arXiv:2604.06052v2 Announce Type: replace Abstract: Text-to-image diffusion models exhibit remarkable generative capabilities, yet their internal operations remain opaque, particularly when handling p

arXiv:2606.01508v1 Announce Type: cross Abstract: Traditional operating systems were designed around deterministic programs, explicit control flow, and human initiated workflows. Their core abstractio

arXiv:2606.00140v1 Announce Type: cross Abstract: While the rapid adoption of multimodal generative models offers immense potential, it has also increased the risks of harmful content synthesis, deepf

arXiv:2606.01702v1 Announce Type: cross Abstract: Deep learning in computer-aided design (CAD) remains fundamentally constrained by the data scarcity challenge: authentic CAD data is difficult to coll

arXiv:2604.05634v2 Announce Type: replace Abstract: Machine unlearning (MU) has become a critical technique for GenAI models' safe and compliant operation. While existing MU methods are effective, mos

arXiv:2606.00397v1 Announce Type: new Abstract: Soft wearable robotic systems have emerged as a promising solution for assisting individuals with reduced hand function. This paper presents SoFiE, a mo

arXiv:2510.03259v2 Announce Type: replace-cross Abstract: Recent research on reasoning models explores the meta-awareness of language models, including their ability to determine optimal thinking dura

arXiv:2605.31304v1 Announce Type: cross Abstract: Deep neural networks (DNNs) are widely used, but interpreting what they actually learn remains difficult. A major obstacle is that individual neurons

arXiv:2602.04729v2 Announce Type: replace Abstract: We present a large-scale human evaluation benchmark for assessing cultural localisation in machine translation produced by state-of-the-art multilin

arXiv:2605.30232v1 Announce Type: cross Abstract: How does reinforcement learning shape a language model's internal representations? We present evidence that RL recruits a pre-existing representation

arXiv:2605.29358v1 Announce Type: new Abstract: We demonstrate that sparse autoencoders can extract interpretable features from Claude 3 Sonnet, a production-scale language model, addressing the open

arXiv:2605.28883v1 Announce Type: new Abstract: Tropical forests worldwide are under intense deforestation pressure driven by economic and political interests, and scientific evidence suggests this de

arXiv:2605.30076v1 Announce Type: new Abstract: Activation-based control steers large language models (LLMs) by intervening on their internal representations during inference, and has emerged as an ef

arXiv:2504.04540v2 Announce Type: replace-cross Abstract: 3D Large Language Models (LLMs) leveraging spatial information in point clouds for 3D spatial reasoning attract great attention. Despite some

arXiv:2601.08267v3 Announce Type: replace Abstract: While reasoning-enhanced large language models perform strongly on English medical tasks, a persistent multilingual gap remains, with substantially

arXiv:2605.26171v1 Announce Type: new Abstract: Many practical anomalies are not merely rare inputs, but violations of semantic constraints: objects co-occur in structured ways, actions imply precondi

arXiv:2605.25419v1 Announce Type: new Abstract: Effective learning support requires understanding not only what learners know but also how accurately they perceive their own understanding. This metaco

arXiv:2605.23933v1 Announce Type: cross Abstract: Educational Question Generation (EQG) aims to synthesize customized exercise questions that enhance student learning. An effective EQG system should i

arXiv:2605.24910v1 Announce Type: new Abstract: Financial Numerical Entity (FNE) understanding aims to recover the meaning of numerical mentions in financial reports. Existing studies primarily focus

arXiv:2605.23045v1 Announce Type: cross Abstract: Video representation learning has seen tremendous progress in recent years. This has been driven by many factors, including the scale of training and

arXiv:2605.22853v1 Announce Type: cross Abstract: Many modern datasets are large and carry complex structural relationships. Graph-based methods have traditionally been used to represent networked dat

arXiv:2605.20693v1 Announce Type: new Abstract: Interpretable text representations should expose coordinates that are not only predictive, but also meaningful enough for independent auditors to apply.

arXiv:2605.20537v1 Announce Type: new Abstract: Biomedical named entity recognition (NER) and entity linking (EL) strongly depend on annotated corpora, but the utility of these resources for benchmark

arXiv:2605.19735v1 Announce Type: cross Abstract: Graph-structured retrieval-augmented generation (RAG) systems can improve answer quality on multi-hop questions, but many current systems rely on larg

arXiv:2605.19111v1 Announce Type: cross Abstract: Existing text-to-image (T2I) evaluation metrics mainly assess whether generated images align with information explicitly stated in the prompt, but oft

arXiv:2506.18852v2 Announce Type: replace-cross Abstract: Mechanistic interpretability (MI) aims to explain how neural networks work by uncovering their underlying mechanisms. As the field grows in in

arXiv:2605.20158v1 Announce Type: cross Abstract: Large Vision Language Models (LVLMs) show promise in medical applications, but their inability to faithfully ground responses in visual evidence raise

arXiv:2510.08886v3 Announce Type: replace Abstract: Going beyond simple text processing, financial auditing requires detecting semantic, structural, and numerical inconsistencies across large-scale di

arXiv:2605.14403v1 Announce Type: new Abstract: Dermatological diagnosis requires integrating fine-grained visual perception with expert clinical knowledge. Although Multimodal Large Language Models (

arXiv:2605.13930v1 Announce Type: new Abstract: EEG foundation models achieve state-of-the-art clinical performance, yet the internal computations driving their predictions remain opaque: a barrier to

arXiv:2605.14940v1 Announce Type: cross Abstract: Semantic communication systems for goal-oriented transmission must protect task-relevant information not only through source compression but also via

arXiv:2605.13438v1 Announce Type: new Abstract: Existing agent memory remains predominantly reactive and retrieval-based, lacking the capacity to autonomously organize experience into persistent cogni

arXiv:2605.13773v1 Announce Type: cross Abstract: Large Language Models (LLMs) are being employed widely to automate tasks across the software development life-cycle. It is, however, unclear whether t

arXiv:2605.12509v1 Announce Type: cross Abstract: Many real-world phenomena are naturally modeled by graphs and networks. However, classical graph models are often limited to pairwise interactions and

arXiv:2605.11959v1 Announce Type: cross Abstract: Multimodal video summarization requires visual features that align semantically with language generation. Traditional approaches rely on CNN features

arXiv:2602.02280v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) face severe safety risks from jailbreak attacks, yet current safety testing largely relies on static datasets and

arXiv:2605.08188v1 Announce Type: cross Abstract: Human attention is the gateway to conscious perception, memory and decision-making. However, its role in modern transformer models remains largely une

arXiv:2605.07973v1 Announce Type: new Abstract: Text-to-image diffusion models can generate visually stunning images, yet, controlling what appears and how it appears, remains surprisingly difficult,

arXiv:2605.06610v2 Announce Type: replace-cross Abstract: Sparse Autoencoders (SAEs) have become an important tool in mechanistic interpretability, helping to analyze internal representations in both

arXiv:2602.00924v2 Announce Type: replace Abstract: Sparse auto-encoders (SAEs) have re-emerged as a prominent method for mechanistic interpretability, yet they face two significant challenges: the no

arXiv:2605.07922v1 Announce Type: new Abstract: Learning hierarchical features in Sparse Autoencoders (SAEs) is essential for capturing the structured nature of real-world data and mitigating issues l

arXiv:2602.07608v2 Announce Type: replace Abstract: Metastatic Progression remains the leading cause of cancer-related mortality, yet predicting whether a primary tumor will metastasize and where it w

arXiv:2603.22844v4 Announce Type: replace Abstract: Surgical smoke severely degrades intraoperative video quality, obscuring anatomical structures and limiting surgical perception. Existing learning-b

arXiv:2605.01442v1 Announce Type: new Abstract: There has been a growing interest in explaining entailments over description logic (DL) knowledge bases. The existing explanation formalisms focus on ju

arXiv:2605.03936v1 Announce Type: new Abstract: Conceptual analysis -- proposing definitions and refining them through counterexamples -- is central to philosophical methodology. We study whether lang

arXiv:2605.02580v1 Announce Type: new Abstract: Recognizing unknown objects is crucial for safety-critical applications such as autonomous driving and robotics. Open-Set Panoptic Segmentation (OPS) ai