Knowledge catalogue
arXiv:2605.20854v1 Announce Type: new Abstract: We study a stochastic bandit algorithm motivated by retry-aware objectives that value the best outcome among multiple attempts, such as pass@k and max@k
arXiv:2602.16813v3 Announce Type: replace Abstract: Language models based on discrete diffusion have attracted widespread interest for their potential to provide faster generation than autoregressive
arXiv:2605.20199v1 Announce Type: new Abstract: We present FlowLM, a flow matching language model transformed from pre-trained diffusion language models via efficient fine-tuning. By re-aligning the c
arXiv:2605.20910v1 Announce Type: new Abstract: Extending the generation horizon of video diffusion models to long sequences remains a long-standing and important challenge. Existing training-free app
arXiv:2503.19708v2 Announce Type: replace-cross Abstract: Urban microclimate, encompassing wind and temperature fields shaped by building geometry, significantly impacts energy consumption, pedestrian
arXiv:2605.20950v1 Announce Type: new Abstract: Vision-Language Models (VLMs) face a bottleneck of prohibitive computational costs arising from massive visual token sequences during inference. Existin
arXiv:2605.20911v1 Announce Type: cross Abstract: Fighting games such as Street Fighter II present unique challenges to reinforcement learning (RL) agents due to their fast-paced, real-time nature. In
arXiv:2510.14737v3 Announce Type: replace Abstract: Hierarchical image recognition seeks to predict class labels along a semantic taxonomy, from broad categories to specific ones, typically under the
arXiv:2605.21303v1 Announce Type: new Abstract: Mechanistic interpretability produces circuit-level causal analyses of neural network behaviour, but discovered circuits often remain isolated experimen
arXiv:2605.21398v1 Announce Type: new Abstract: Accurate registration between a prior model and the real scene is essential for high-precision robotic manipulation, yet optical methods suffer from lon
arXiv:2605.21312v1 Announce Type: cross Abstract: Modern LLM serving is no longer homogeneous or monolithic. Production systems now combine disaggregated execution, complex parallelism, runtime optimi
arXiv:2605.20892v1 Announce Type: new Abstract: Fine-grained fruit classification is a critical yet challenging task in agricultural computer vision, primarily hindered by a severe shortage of high-qu
arXiv:2603.01712v2 Announce Type: replace-cross Abstract: Fine-tuning large language models for vertical domains remains labor-intensive, requiring practitioners to curate data, configure training, an
arXiv:2605.21171v1 Announce Type: new Abstract: Ternary Vision Transformers offer substantial model compression, however state-of-the-art methods only ternarize the encoder layers, leaving patch embed
arXiv:2605.20316v1 Announce Type: new Abstract: Modern text-to-image diffusion models encode rich visual priors, but expose them only through one-way text-conditioned generation. Existing unified visi
arXiv:2605.21439v1 Announce Type: cross Abstract: This paper presents a low-complexity, model-free, output-feedback controller for a class of unknown time-varying nonlinear systems with unknown input
arXiv:2605.20287v1 Announce Type: cross Abstract: Standard cells form the building blocks of digital circuits, so their delay and power critically influence chip-level performance; yet characterizatio
arXiv:2605.20727v1 Announce Type: new Abstract: Deep neural networks (DNNs) experience significant performance degradation when processing noisy labels, primarily due to overfitting on mislabeled data
arXiv:2602.10408v2 Announce Type: replace-cross Abstract: Normalization layers are standard in transformers, but it is not clear whether their sample-dependent computations are necessary throughout bo
arXiv:2605.21435v1 Announce Type: new Abstract: Graph Neural Networks (GNNs) have become the de facto standard for learning on relational data. While traditional GNNs' message passing is well suited f
arXiv:2605.20752v1 Announce Type: new Abstract: Vision-language-action (VLA) policies have advanced language-conditioned robotic manipulation by transferring semantic priors from pretrained vision-lan
arXiv:2605.20651v1 Announce Type: new Abstract: Existing deep learning frameworks for Optical Coherence Tomography Angiography (OCTA) vessel segmentation are largely derived from the U-Net architectur
arXiv:2605.20896v1 Announce Type: cross Abstract: Defending against today's increasingly sophisticated cyberattacks requires security analysts to continuously translate evolving attacker tradecraft in
arXiv:2605.20267v1 Announce Type: new Abstract: Synthetic PET images are valuable for quantitative imaging workflow development, scalable virtual imaging trials, and deep learning model training, but
arXiv:2512.03671v2 Announce Type: replace Abstract: The rise of generative AI (GenAI) chatbots accessible via conversational interfaces is transforming digital interactions and holds economic promise.
arXiv:2605.21055v1 Announce Type: cross Abstract: A recent trend is to leverage machine learning models to improve the evolutionary design and optimization process. We propose a novel transformer-base
arXiv:2605.20241v1 Announce Type: cross Abstract: Prompt-level safety probes for large language models use hidden-state representations to separate safe from unsafe prompts, but strong average detecti
arXiv:2602.20399v2 Announce Type: replace Abstract: Neural simulators promise efficient surrogates for physics simulation, but scaling them is bottlenecked by the prohibitive cost of generating high-f
arXiv:2605.20476v1 Announce Type: new Abstract: Long-horizon video generation suffers from two intertwined issues. First, there is drift, where video quality degrades over time. Second, there are cont
arXiv:2605.21076v1 Announce Type: new Abstract: Grading German legal exam solutions faces growing volumes and a shortage of qualified graders, delaying feedback and creating a bottleneck. At the same
arXiv:2507.06344v3 Announce Type: replace-cross Abstract: Variational Quantum Algorithms are promising candidates for near-term quantum computing, yet they face scalability challenges due to barren pl
arXiv:2505.24275v3 Announce Type: replace Abstract: We propose GradPower, a lightweight gradient-transformation technique for accelerating language model pre-training. Given a gradient vector g=(g_i)_
arXiv:2602.03004v2 Announce Type: replace Abstract: To improve the reliability and interpretability of industrial process monitoring, this article proposes a Causal Graph Spatial-Temporal Autoencoder
arXiv:2605.21247v1 Announce Type: new Abstract: Graph Neural Networks (GNNs) have emerged as a cornerstone of deep learning, with most existing methods rooted in graph signal processing and diffusion
arXiv:2605.20248v1 Announce Type: new Abstract: In the transductive setting, where the full graph is observed but node labels are only partially available, progress in semi-supervised node classificat
arXiv:2509.10308v2 Announce Type: replace Abstract: In the aftermath of disasters, many institutions worldwide face challenges in monitoring changes in disaster risk, limiting assessment of progress t
arXiv:2605.20188v1 Announce Type: new Abstract: Recommending safe and effective medication combinations from electronic health records (EHRs) is a core clinical AI problem, yet it remains difficult be
arXiv:2605.20815v1 Announce Type: new Abstract: Graph-based Retrieval Augmented Generation (GraphRAG) extends retrieval-augmented generation to support structured reasoning over complex corpora, but i
arXiv:2605.21061v1 Announce Type: new Abstract: Existing Driving VLAs predict trajectories while largely ignoring their visual tokens -- a phenomenon we trace not to insufficient training but to a str
arXiv:2605.20440v1 Announce Type: new Abstract: We introduce the star_G tensor algebra, in which any finite group G defines the multiplication rule, making equivariance an intrinsic algebraic property
arXiv:2605.20559v1 Announce Type: cross Abstract: Modern matrix completion problems often involve heterogeneous data whose rows simultaneously belong to many meta-categories, such as demographic and a
arXiv:2605.20246v1 Announce Type: new Abstract: Recently, vision-language model (VLM) agents have shown promising progress in open-world tasks, where successful task completion often requires multiple
arXiv:2605.20669v1 Announce Type: new Abstract: X-ray security inspection requires accurate real-time detection of prohibited items, but existing models often struggle to balance the challenges of sev
arXiv:2605.20744v1 Announce Type: new Abstract: Aligning autonomous agents with human intent remains a central challenge in modern AI. A key manifestation of this challenge is reward hacking, whereby
arXiv:2605.20536v1 Announce Type: new Abstract: Accurate classification of breast ultrasound images into benign, malignant, and normal categories is a critical clinical task complicated by speckle noi
arXiv:2605.20469v1 Announce Type: new Abstract: Vision-language models (VLMs) are increasingly used for medical image interpretation, yet they frequently hallucinate, generating clinically plausible b
arXiv:2605.20362v1 Announce Type: new Abstract: Virtual staining of histopathology images (e.g., H&E-IHC) is an emerging tool in digital pathology, enabling faster and cheaper workflows by synthesizin
arXiv:2605.20891v1 Announce Type: new Abstract: Multimodal survival prediction, a crucial yet challenging task, demands the integration of multimodal medical data (eg Whole Slide Images (WSIs) and Gen
arXiv:2605.20600v1 Announce Type: new Abstract: Autoregressive (AR) visual generation has achieved remarkable performance but suffers from high memory usage and low throughput, as it requires caching
arXiv:2605.20435v1 Announce Type: cross Abstract: Make America Healthy Again (MAHA) is a national health movement that encompasses a striking mix of beliefs, from broadly accepted concerns about good
arXiv:2605.21420v1 Announce Type: new Abstract: Reaction condition recommendation sits immediately after retrosynthetic disconnection selection, and in practice, chemists require both accurate predict
arXiv:2605.21460v1 Announce Type: new Abstract: Autonomous manipulation systems have achieved remarkable capabilities, yet the integration of human expertise with diffusion-based policies in shared co
arXiv:2605.20725v1 Announce Type: new Abstract: Learning with noisy labels in multimedia classification often combines external annotations and model predictions into a single reliability weight, even
arXiv:2605.21104v1 Announce Type: new Abstract: Sparsifying transformers remains a fundamental challenge, as standard optimizers fail to simultaneously encourage sparsity and maintain training stabili
arXiv:2502.17773v5 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly used to simulate survey responses, but synthetic data can be misaligned with the human populatio
arXiv:2605.21266v1 Announce Type: new Abstract: Reinforcement Learning from Verifiable Rewards (RLVR) has emerged as a powerful paradigm for reasoning in language models, with GRPO as its primary exam
arXiv:2603.26539v2 Announce Type: replace Abstract: How does the extent to which a model is open or closed impact the scientific inferences that can be drawn from research that involves it? In this pa
arXiv:2604.06750v2 Announce Type: replace Abstract: Vision-Language Models (VLMs) are increasingly proposed for autonomous driving tasks, yet their performance on sequential driving scenes remains poo
arXiv:2605.20388v1 Announce Type: new Abstract: Predicting how a person's first-person view will evolve (what action will follow, what plan completes a task, whether an in-progress shot will score) is
arXiv:2605.20613v1 Announce Type: new Abstract: The current pretraining paradigm for large language models relies on massive compute and internet-scale raw text, creating a significant barrier to foun