arXiv:2602.08913v3 Announce Type: replace-cross Abstract: In underdetermined regression and classification problems, multiple feature subsets often yield equivalent predictive performance. In applied settings, especially with $n ll…
arXiv:2512.08022v2 Announce Type: replace Abstract: We propose a novel diffusion-based posterior sampling method within a plug-and-play framework. Our approach constructs a probability transport from an easy-to-sample…
arXiv:2607.01982v2 Announce Type: replace-cross Abstract: Using molecular large language models (LLMs) as a unified framework for understanding molecular structures and functions is emerging as a new…
arXiv:2601.02854v2 Announce Type: replace Abstract: As an agent-level reasoning and coordination paradigm, Multi-Agent Debate (MAD) orchestrates multiple agents through structured debate to improve answer quality and…
arXiv:2607.28640v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) should generate consistent responses given semantically equivalent inputs across modalities. However, we observe a systematic discrepancy…
arXiv:2607.29613v1 Announce Type: cross Abstract: Reinforcement learning (RL) post-training of Vision-Language-Action (VLA) models has shown strong promise for robotic manipulation. Among RL methods, critic-based approaches rely…
arXiv:2607.28950v1 Announce Type: new Abstract: This paper proposes an automated classification method of chest CT volumes based on likelihood of COVID-19 cases. Novel coronavirus disease 2019…
arXiv:2607.28693v1 Announce Type: new Abstract: Industrial NILM remains challenging because measurement noise and widespread concurrent machine operation reduce the generalization of models tuned on residential data.…
arXiv:2601.20533v2 Announce Type: replace Abstract: Survival analysis has become a standard approach for modelling time to default by time-varying covariates in credit risk. Unlike most existing…
arXiv:2607.28981v1 Announce Type: cross Abstract: Testing independence or conditional independence is fundamental to statistical inference, yet existing methods for non-Euclidean random objects often face a difficult…
arXiv:2510.12953v4 Announce Type: replace-cross Abstract: Recent medical vision-language models have shown promise on tasks such as VQA, report generation, and anomaly detection. However, most are adapted…
arXiv:2607.28679v1 Announce Type: new Abstract: Multi-agent planning problems arise in a variety of engineering applications, such as multi-robot wildfire fighting and unmanned aerial inspection in factories.…
arXiv:2607.28638v1 Announce Type: new Abstract: As large language model (LLM) agents increasingly learn from experience, they primarily rely on trajectory-level reflection to extract insights. Viewed through…
arXiv:2607.28695v1 Announce Type: cross Abstract: Here is the plain text version optimized for arXiv's submission form. Custom macros (like CV and SI) have been converted to…
arXiv:2607.29302v1 Announce Type: cross Abstract: Reliable robot learning requires a world simulator that can predict action consequences before execution on physical hardware, including risky and failure-prone…
arXiv:2607.29674v1 Announce Type: cross Abstract: SignMuon compresses the Muon update to one bit per parameter by taking its elementwise sign, providing the most direct way to…
arXiv:2607.29675v1 Announce Type: cross Abstract: Density modes provide a localized and interpretable summary of multimodal distributions, but their estimation under rigorous differential privacy constraints remains largely…
arXiv:2605.26000v2 Announce Type: replace Abstract: Stochastic gradient descent (SGD) is foundational to large-scale statistical learning and stochastic optimization. However, in some modern statistical learning problems, stochastic…
While recent image editing models have made rapid progress, multi-reference editing remains challenging, particularly in maintaining visual consistency across references and ensuring overall visual harmony. Reinforcement…
Enterprise workflows increasingly rely on agents for schema-guided extraction: given a document and a user-defined schema, the agent faithfully follows the schema to produce the correct…
Polygonal meshes are the standard surface representation of modern 3D pipelines, and generating high-quality meshes with artist-style topology is essential for film, gaming, and interactive 3D…
We study empirical scaling properties for text conditioning in visual generation. Such properties have rarely been measured because diffusion loss does not scale with the number…
Latent world models enable efficient planning by predicting future states in a compact representation space, but their performance depends critically on the quality of the learned…
We present N_0-VTLA, a vision-tactile-language-action (VTLA) foundation model capable of (1) fine-grained contact-rich manipulation with tactile perception and tactile-feedback control, and (2) offline policy improvement from…