Knowledge catalogue
arXiv:2604.19765v1 Announce Type: cross Abstract: Recent work identifies a sparse set of 'hallucination neurons' (H-neurons), less than 0.1% of feed-forward network neurons, that reliably predict when
arXiv:2603.26747v2 Announce Type: replace Abstract: Recent text-driven motion generation methods span both discrete token-based approaches and continuous-latent formulations. MotionGPT3 exemplifies th
arXiv:2604.20047v1 Announce Type: new Abstract: Vision Transformers (ViTs) have achieved remarkable success across vision tasks, yet recent studies show they remain vulnerable to backdoor attacks. Exi
arXiv:2604.19810v1 Announce Type: new Abstract: Can scientific discovery be made arbitrarily easy by choosing the right representation, collecting enough data, and deploying sufficiently powerful algo
arXiv:2604.19724v1 Announce Type: cross Abstract: Despite the remarkable success of Vision Transformers (ViTs) across a wide range of vision tasks, recent studies have revealed that they remain vulner
arXiv:2604.18957v1 Announce Type: new Abstract: Extracting standardized metallurgical metrics from microscopy images remains challenging due to complex grain morphology and the data demands of supervi
arXiv:2604.19309v1 Announce Type: cross Abstract: Qualitative coding relies on a researcher's application of codes to textual data. As coding proceeds across large datasets, interpretations of codes o
arXiv:2503.07259v2 Announce Type: replace-cross Abstract: The goal of creating intelligent, human-centered wearable systems for continuous activity understanding faces a fundamental trade-off: Egocent
arXiv:2604.19135v1 Announce Type: new Abstract: This paper presents the first exploration of text-to-image diffusion models for zero-shot sketch-based 3D shape retrieval (ZS-SBSR). Existing sketch-bas
arXiv:2604.19355v1 Announce Type: cross Abstract: High-fidelity measurements of continuum physical fields are essential for scientific discovery and engineering design but remain challenging under spa
arXiv:2604.19536v1 Announce Type: new Abstract: Recent navigation systems achieve strong benchmark results, yet real-world deployment often remains visibly stop-and-go. This bottleneck arises because
arXiv:2604.19720v1 Announce Type: new Abstract: Human video generation remains challenging due to the difficulty of jointly modeling human appearance, motion, and camera viewpoint under limited multi-
arXiv:2604.19587v1 Announce Type: new Abstract: Traditional photographic image editing typically requires users to possess sufficient aesthetic understanding to provide appropriate instructions for ad
arXiv:2604.19591v1 Announce Type: new Abstract: Fine-grained high-resolution remote sensing mapping typically relies on localized visual features, which restricts cross-domain generalizability and oft
arXiv:2501.04410v2 Announce Type: replace Abstract: User simulation is an emerging interdisciplinary topic with multiple critical applications in the era of Generative AI. It involves creating an inte
arXiv:2604.19335v1 Announce Type: new Abstract: The rapid growth of chemical literature has generated vast amounts of unstructured data, where reaction information is particularly valuable for applica
arXiv:2509.24478v2 Announce Type: replace Abstract: Modern neural networks have greatly improved performance across speech recognition benchmarks. However, gains are often driven by frequent words wit
arXiv:2604.16622v1 Announce Type: new Abstract: Backchannels (e.g., `yeah', `mhm', and `right') are short, non-interruptive feedback signals whose lexical form and prosody jointly convey pragmatic mea
arXiv:2604.17818v1 Announce Type: new Abstract: Reconstructing 3D human motion and human-object interactions (HOI) from Internet videos is a fundamental step toward building large-scale datasets of hu
arXiv:2604.05983v2 Announce Type: replace-cross Abstract: We present Arch (AI-native Register-transfer Clocked Hardware), a hardware description language for micro-architecture specification and AI-as
arXiv:2604.16514v1 Announce Type: new Abstract: Autoregressive vision-language models (VLMs) deliver strong multimodal capability, but their token-by-token decoding imposes a fundamental inference bot
arXiv:2604.16680v1 Announce Type: new Abstract: We introduce C-GenReg, a training-free framework for 3D point cloud registration that leverages the complementary strengths of world-scale generative pr
arXiv:2601.05543v2 Announce Type: replace Abstract: Although Speech Large Language Models have achieved notable progress, a substantial modality reasoning gap remains: their reasoning performance on s
arXiv:2507.06056v4 Announce Type: replace Abstract: Large Language Models (LLMs) are known to memorize portions of their training data, sometimes even reproduce content verbatim when prompted appropri
arXiv:2505.15353v3 Announce Type: replace Abstract: Log-likelihood vectors define a common space for comparing language models as probability distributions, enabling unified comparisons across heterog
arXiv:2603.26475v2 Announce Type: replace Abstract: Electrocardiograms (ECGs) are among the most widely available clinical signals and play a central role in cardiovascular diagnosis. While recent fou
arXiv:2604.16588v1 Announce Type: new Abstract: Penalty kicks in soccer are decided under extreme time constraints, where goalkeepers benefit from anticipating shot direction from the kickers motion b
arXiv:2604.18477v1 Announce Type: new Abstract: Biological classification with interpretability remains a challenging task. For this, we introduce a novel encoding framework, Multi-Scale Reversible Ch
arXiv:2604.16878v1 Announce Type: new Abstract: Early prediction of severe clinical deterioration and remaining length of stay can enable timely intervention and better resource allocation in high-acu
arXiv:2503.21248v3 Announce Type: replace Abstract: Large language models (LLMs) have shown potential in assisting scientific research, yet their ability to discover high-quality research hypotheses r
arXiv:2603.18361v2 Announce Type: replace Abstract: Conversational agents are required to respond to their users not only with high quality (i.e. commonsense bearing) responses, but also considering m
arXiv:2603.02972v2 Announce Type: replace Abstract: Vision-Language Navigation (VLN) presents a unique challenge for Large Vision-Language Models (VLMs) due to their inherent architectural mismatch: V
arXiv:2603.24434v2 Announce Type: replace Abstract: Frailty is a condition in aging medicine characterized by diminished physiological reserve and increased vulnerability to stressors. However, frailt
arXiv:2509.16621v2 Announce Type: replace-cross Abstract: Learned Sparse Retrieval (LSR) such as SPLADE has growing interest for effective semantic 1st stage matching while enjoying the efficiency of
arXiv:2604.18539v1 Announce Type: new Abstract: This paper studies how empirical dialogue-flow statistics can be incorporated into Next Dialogue Act Prediction (NDAP). A KL regularization term is prop
arXiv:2604.18389v1 Announce Type: new Abstract: Prompt sensitivity, which refers to how strongly the output of a large language model (LLM) depends on the exact wording of its input prompt, raises con
arXiv:2510.17001v2 Announce Type: replace Abstract: Large language models (LLMs) often encode word-form variation (e.g., walk vs. walked) as linear directions in the embedding space. However, standard
arXiv:2604.18249v1 Announce Type: new Abstract: Speech encoder models are known to model members of some speaker groups (SGs) better than others. However, there has been little work in establishing wh
arXiv:2501.05281v2 Announce Type: replace Abstract: Continuous monitoring of glacier calving fronts is essential for sea level rise projections. This study benchmarks Deep Learning systems for front d
arXiv:2604.03444v3 Announce Type: replace-cross Abstract: Recent work has demonstrated the potential of non-transformer language models, especially linear recurrent neural networks (RNNs) and hybrid m
arXiv:2604.15374v1 Announce Type: cross Abstract: Recent progress in visual brain decoding from fMRI has been enabled by large-scale datasets such as the Natural Scenes Dataset (NSD) and powerful diff
arXiv:2604.15711v1 Announce Type: cross Abstract: Pathological diagnosis is highly reliant on image analysis, where Regions of Interest (ROIs) serve as the primary basis for diagnostic evidence, while
arXiv:2604.15416v1 Announce Type: cross Abstract: Sign-based optimization algorithms, such as SignSGD, have garnered significant attention for their remarkable performance in distributed learning and
arXiv:2604.15827v1 Announce Type: cross Abstract: Conventional information retrieval is concerned with identifying the relevance of texts for a given query. Yet, the conventional definition of relevan
arXiv:2510.08480v2 Announce Type: replace Abstract: Multimodal large language models (MLLMs) have demonstrated remarkable potential in bridging visual and textual reasoning, yet their reliance on text
This article outlines Sebastian Raschka's systematic approach to learning and understanding Large Language Model (LLM) architectures, likely covering foundational concepts, key components, and methodo
arXiv:2604.14191v1 Announce Type: new Abstract: State Space Models (SSMs) such as Mamba have become a popular alternative to Transformer models, due to their reduced memory consumption and higher thro
arXiv:2604.14519v1 Announce Type: cross Abstract: Catastrophic forgetting remains a fundamental challenge in continual learning, in which models often forget previous knowledge when fine-tuned on a ne
arXiv:2604.14720v1 Announce Type: new Abstract: Myotubes are multinucleated muscle fibers serving as key model systems for studying muscle physiology, disease mechanisms, and drug responses. Mechanist
arXiv:2603.17512v4 Announce Type: replace Abstract: Large language models (LLMs) exhibit strong general intelligence, yet their multilingual performance remains highly imbalanced. Although LLMs encode
arXiv:2604.14175v1 Announce Type: new Abstract: We present a unified system addressing both Subtask 3 (answer generation) and Subtask 4 (evidence sentence alignment) of the ArchEHR-QA Shared Task. For
arXiv:2603.16869v2 Announce Type: replace Abstract: We introduce SegviGen, a framework that repurposes native 3D generative models for 3D part segmentation. Existing pipelines either lift strong 2D pr
arXiv:2604.13286v1 Announce Type: new Abstract: Despite the widespread multilingual deployment of large language models, post-training pipelines remain predominantly English-centric, contributing to p
arXiv:2512.10877v4 Announce Type: replace Abstract: Discrete diffusion models (DMs) have achieved strong performance in language and other discrete domains, offering a compelling alternative to autore
arXiv:2604.13988v1 Announce Type: new Abstract: Objective: Investigate whether hypnogram 'realism' can be used to guide an unsupervised method for handling arbitrary types of signal degradation in mob
arXiv:2604.12506v1 Announce Type: new Abstract: Recent Audio Large Language Models (AudioLLMs) exhibit a striking performance inversion: while excelling at complex reasoning tasks, they consistently u
arXiv:2409.06679v3 Announce Type: replace Abstract: Processing long contexts is increasingly important for Large Language Models (LLMs) in tasks like multi-turn dialogues, code generation, and documen
arXiv:2604.12905v1 Announce Type: cross Abstract: Force and torque (F/T) sensing is critical for robot-environment interaction, but physical F/T sensors impose constraints in size, cost, and fragility
arXiv:2604.12978v1 Announce Type: new Abstract: Optical character recognition (OCR) has advanced rapidly with the rise of vision-language models, yet evaluation has remained concentrated on a small cl
arXiv:2506.01256v4 Announce Type: replace-cross Abstract: Forced alignment is a common tool to align audio with orthographic and phonetic transcriptions. Most forced alignment tools provide only point