Search: “concepts”

arXiv:2609.13439v1 Announce Type: cross Abstract: As compute scales, models evolve, and training algorithms advance, our ability to explain the increasingly powerful AI systems they enable is eroding.

arXiv:2603.13359v2 Announce Type: replace Abstract: Language models are commonly fine-tuned for safety alignment to refuse harmful prompts. One approach fine-tunes them to generate categorical refusal

arXiv:2609.14441v1 Announce Type: cross Abstract: Parkinson's disease (PD) manifests early neuromotor impairments that become observable in controlled hand-drawn patterns such as spirals and meanders,

arXiv:2609.14917v1 Announce Type: cross Abstract: We introduce document embedding geometry as a quantitative observable of conceptual reorganization and develop a counterfactual ablation framework for

arXiv:2609.13771v1 Announce Type: new Abstract: In this paper, I formulate a Continual Learning problem and propose a method named 'Homeostatic Continual Learning' that enables an AI agent to learn co

arXiv:2609.13879v1 Announce Type: new Abstract: An acquired representation can enlarge a system's cognitive repertoire without transferring the capacities exercised in producing that representation. T

arXiv:2609.15695v1 Announce Type: new Abstract: Vision-language models (VLMs) increasingly power consumer-facing AI search, yet evaluating them on the diversity of everyday visual questions remains ch

arXiv:2609.13152v1 Announce Type: new Abstract: Large language models (LLMs) perform strongly on static science benchmarks, yet their ability to reason about the physical world through active experime

arXiv:2609.13657v1 Announce Type: new Abstract: Traditional recommender systems are typically trained to predict what item users will interact with next, but not why. However, offering personalized ev

arXiv:2609.13148v1 Announce Type: cross Abstract: Large language models are increasingly deployed as synthetic consumer panels, promising 97% cost reductions over traditional surveys. Yet aggregate va

arXiv:2607.01630v2 Announce Type: replace Abstract: Dynamic expansion methods for class-incremental learning (CIL) protect task-specific knowledge by growing dedicated tokens or subnetworks, yet our a

arXiv:2609.12179v1 Announce Type: new Abstract: Algorithmic recourse methods typically assume that a predictive model has access to all features of an individual. In practice, decisions are often made

arXiv:2609.12915v1 Announce Type: new Abstract: Large-scale multi-label text classification assigns a small subset of relevant labels to each document from a vocabulary containing thousands or tens of

arXiv:2609.12552v1 Announce Type: new Abstract: Open-vocabulary detection accepts any class list at inference, and promptable segmentation returns regions without class names: the taxonomy has left th

arXiv:2609.12537v1 Announce Type: new Abstract: AI-assisted writing can flatten meaning in human storytelling, enabling the production of homogeneous outputs without the intentional effort and sense-m

arXiv:2609.11341v1 Announce Type: new Abstract: Multimodal brain state decoding has largely focused on fusing paired modalities for prediction, but has rarely explored how their correspondence can be

arXiv:2609.11240v1 Announce Type: new Abstract: The larval stage of Drosophila melanogaster is a compact model system for neuroscience whose genetic toolkit allows fluorescent markers to be expressed

arXiv:2609.11477v1 Announce Type: new Abstract: Brain metastases exhibit high inter-lesion variability in size, enhancement pattern, and post-treatment appearance, making volumetric segmentation of bo

arXiv:2609.06579v1 Announce Type: cross Abstract: Machine learning methods, and especially neural networks, are now routinely used for malware detection in network traffic. Though very effective, syst

arXiv:2609.10196v1 Announce Type: new Abstract: Attias, Hanneke and Ramaswami (NeurIPS 2025) asked whether randomization provably reduces the oracle calls needed for online learning when the class is

arXiv:2609.09902v1 Announce Type: new Abstract: Reading a transformer's internal states in token space is easy to do and hard to trust: a logit lens on a single hidden state is dominated, at intermedi

arXiv:2609.07139v1 Announce Type: new Abstract: A transformer can make an attribute linearly decodable in its residual stream at a depth where that attribute does not yet influence the output. This ga

arXiv:2609.06155v1 Announce Type: cross Abstract: Neural models, including dense retrievers, have been widely adopted in Information Retrieval (IR), often delivering state-of-the-art performance. Desp

arXiv:2609.05834v1 Announce Type: new Abstract: World models promise a general route to embodied intelligence: learn predictive dynamics once, then reason, plan, and act with them. Increasingly, the r

arXiv:2609.08174v1 Announce Type: new Abstract: We introduce OntologyBench, a tiered biomedical retrieval benchmark comprising 471,854 training and 125,744 evaluation query-document relevance pairs ac

arXiv:2609.07910v1 Announce Type: new Abstract: Multi-agent federations need governance that answers three questions under adversarial conditions: who participated (identity), did they conform (enforc

arXiv:2601.09721v2 Announce Type: replace-cross Abstract: Consumer artificial intelligence chatbots are now accessed by hundreds of millions of users seeking health information, yet systematic evaluat

arXiv:2609.09561v1 Announce Type: new Abstract: Surveys remain the primary way researchers grasp the lineage of methods within an AI subfield, but they scale poorly against the current rate of publica

arXiv:2609.05730v1 Announce Type: new Abstract: Contrastive Language-Image Pretraining (CLIP) is a building block of many machine learning applications. Scaling laws have guided resource allocation fo

arXiv:2609.07037v1 Announce Type: new Abstract: Activation steering has emerged as a lightweight, inference-time approach to control the behavior of Large Language Models (LLMs). However, traditional

arXiv:2602.02914v3 Announce Type: replace Abstract: Privacy-preserving face recognition (PPFR) hides facial appearance while retaining machine recognition, whereas perception-preserving face de-identi

arXiv:2609.05876v1 Announce Type: new Abstract: AI-generated image detection is increasingly open-world: new image generators produce highly realistic images that make visual artifacts harder to ident

arXiv:2609.07137v1 Announce Type: new Abstract: Recent image-to-3D generation models built on flow-matching diffusion Transformers (DiT) can produce high-fidelity meshes, yet their post-training strat

arXiv:2609.07061v1 Announce Type: new Abstract: Physics-Informed Neural Networks (PINNs) embed PDE residuals into neural network training, but their internal representations remain opaque: it is unkno

arXiv:2609.05521v1 Announce Type: cross Abstract: The limitations of on-board sensors and blind spots caused by occlusion cause the reduction of perception quality in autonomous vehicles. In such case

arXiv:2601.10324v3 Announce Type: replace Abstract: Synthetic aperture radar (SAR) imagery exhibits intrinsic information sparsity due to its unique electromagnetic scattering mechanism. Despite the w

arXiv:2609.05968v1 Announce Type: new Abstract: Aligning a text-to-image generation flow model with a reward makes it follow objectives that the training data alone does not provide. Alignment fine-tu

arXiv:2511.03272v2 Announce Type: replace Abstract: Diffusion-based text-to-video models are increasingly capable, but mask-based editing over hundreds of frames remains challenging: naive long-video

arXiv:2609.04343v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used for consequential decisions, making their explanations an important tool for auditing model behavior.

arXiv:2510.12368v2 Announce Type: replace-cross Abstract: Shallow Recurrent Decoder networks are a novel data-driven methodology able to provide accurate state estimation in engineering systems, such

arXiv:2609.05262v1 Announce Type: new Abstract: Computational phylogenetics has become an essential tool in historical linguistics, yet its application at a global scale remains constrained by two fac

arXiv:2609.03742v1 Announce Type: cross Abstract: Video lectures are valuable educational resources, but their dense and lengthy formats often overwhelm novice learners. This difficulty stems from a f

arXiv:2609.03619v1 Announce Type: cross Abstract: Multi-agent debate (MAD) improves the reasoning capabilities of large language models by having multiple agents iteratively refine their responses thr

arXiv:2609.04022v1 Announce Type: cross Abstract: Aligning large language models (LLMs) is essential for their safe deployment. Current alignment methods mainly optimize observable responses, yet mode

arXiv:2609.01757v1 Announce Type: new Abstract: Vision-Language Pretrained Models (VLPMs) offer a scalable path to open-vocabulary chest radiology understanding, yet two aspects remain underexplored:

arXiv:2609.02796v1 Announce Type: new Abstract: Sign language processing systems have traditionally operated at the sentence level, ignoring critical discourse phenomena fundamental to sign language c