arXiv:2602.16746v3 Announce Type: replace-cross Abstract: Grokking — the delayed transition from memorization to generalization in small algorithmic tasks — remains poorly understood. We present a geometric analysis of optimization dynamics in transformers trained on modular arithmetic. PCA of attention weight trajectories reveals that training evolves predominantly within a low-dimensional execution subspace, with a single principal […]
LumaFlux: Lifting 8-Bit Worlds to HDR Reality with Physically-Guided Diffusion Transformers
arXiv:2604.02787v1 Announce Type: cross Abstract: The rapid adoption of HDR-capable devices has created a pressing need to convert the 8-bit Standard Dynamic Range (SDR) content into perceptually and physically accurate 10-bit High Dynamic Range (HDR). Existing inverse tone-mapping (ITM) methods often rely on fixed tone-mapping operators that struggle to generalize to real-world degradations, stylistic variations, […]
Infusion: Shaping Model Behavior by Editing Training Data via Influence Functions
arXiv:2602.09987v4 Announce Type: replace-cross Abstract: Influence functions are commonly used to attribute model behavior to training documents. We explore the reverse: crafting training data that induces model behavior. Our framework, Infusion, uses scalable influence-function approximations to compute small perturbations to training documents that induce targeted changes in model behavior through parameter shifts. We evaluate Infusion […]
Disrupting Cognitive Passivity: Rethinking AI-Assisted Data Literacy through Cognitive Alignment
arXiv:2604.02783v1 Announce Type: cross Abstract: AI chatbots are increasingly stepping into roles as collaborators or teachers in analyzing, visualizing, and reasoning through data and domain problem. Yet, AI’s default assistant mode with its comprehensive and one-off responses may undermine opportunities for practitioners to develop literacy through their own thinking, inducing cognitive passivity. Drawing on evidence […]
Autonomous Computational Catalysis Research via Agentic Systems
arXiv:2601.13508v2 Announce Type: replace-cross Abstract: Fully automating the scientific process is a transformative ambition in materials science, yet current artificial intelligence masters isolated workflow fragments. In computational catalysis, a system autonomously navigating the entire research lifecycle from conception to a scientifically meaningful manuscript remains an open challenge. Here we present CatMaster, a catalysis-native multi-agent framework […]
Analysis of Invasive Breast Cancer in Mammograms Using YOLO, Explainability, and Domain Adaptation
arXiv:2512.00129v2 Announce Type: replace-cross Abstract: Deep learning models for breast cancer detection from mammographic images have significant reliability problems when presented with Out-of-Domain (OOD) inputs such as other imaging modalities (CT, MRI, X-ray) or equipment variations, leading to unreliable detection and misdiagnosis. The current research mitigates the fundamental OOD issue through a comprehensive approach integrating […]
Escaping the BLEU Trap: A Signal-Grounded Framework with Decoupled Semantic Guidance for EEG-to-Text Decoding
arXiv:2603.03312v2 Announce Type: replace-cross Abstract: Decoding natural language from non-invasive EEG signals is a promising yet challenging task. However, current state-of-the-art models remain constrained by three fundamental limitations: Semantic Bias (mode collapse into generic templates), Signal Neglect (hallucination based on linguistic priors rather than neural inputs), and the BLEU Trap, where evaluation metrics are artificially […]
OSCAR: Orchestrated Self-verification and Cross-path Refinement
arXiv:2604.01624v2 Announce Type: replace Abstract: Diffusion language models (DLMs) expose their denoising trajectories, offering a natural handle for inference-time control; accordingly, an ideal hallucination mitigation framework should intervene during generation using this model-native signal rather than relying on an externally trained hallucination classifier. Toward this, we formulate commitment uncertainty localization: given a denoising trajectory, identify […]
Size-structured populations with growth fluctuations: Feynman–Kac formula and decoupling
arXiv:2508.14680v2 Announce Type: replace-cross Abstract: We study a size-structured population model in which individual cells grow at a rate determined by a fluctuating internal variable (e.g., gene expression levels). Many previous models of phenotypically heterogeneous populations can be viewed as special cases of this model, and it has previously been observed that the internal variable […]
Can VLMs Truly Forget? Benchmarking Training-Free Visual Concept Unlearning
arXiv:2604.03114v1 Announce Type: cross Abstract: VLMs trained on web-scale data retain sensitive and copyrighted visual concepts that deployment may require removing. Training-based unlearning methods share a structural flaw: fine-tuning on a narrow forget set degrades general capabilities before unlearning begins, making it impossible to attribute subsequent performance drops to the unlearning procedure itself. Training-free approaches […]
Neural correlates of perceptual consciousness from within: a narrative review of human intracranial research
arXiv:2510.08736v2 Announce Type: replace Abstract: Despite many years of research, the quest to identify neural correlates of perceptual consciousness (NCC) remains unresolved. One major obstacle lies in methodological limitations: most studies rely on non-invasive neural measures with limited spatial or temporal resolution making it difficult to disentangle proper NCCs from concurrent cognitive processes. Additionally, the […]
Domain-Adapted Retrieval for In-Context Annotation of Pedagogical Dialogue Acts
arXiv:2604.03127v1 Announce Type: cross Abstract: Automated annotation of pedagogical dialogue is a high-stakes task where LLMs often fail without sufficient domain grounding. We present a domain-adapted RAG pipeline for tutoring move annotation. Rather than fine-tuning the generative model, we adapt retrieval by fine-tuning a lightweight embedding model on tutoring corpora and indexing dialogues at the […]