arXiv:2604.00536v1 Announce Type: new
Abstract: Large language models (LLMs) achieve strong downstream performance largely due to abundant supervised fine-tuning (SFT) data. However, high-quality SFT data in knowledge-intensive domains such as humanit…
arXiv:2603.20391v2 Announce Type: replace
Abstract: Multi-view human mesh recovery (HMR) is broadly deployed in diverse domains where high accuracy and strong generalization are essential. Existing approaches can be broadly grouped into geometry-based…
arXiv:2510.25770v2 Announce Type: replace-cross
Abstract: While generative models, especially large language models (LLMs), are ubiquitous in today’s world, principled mechanisms to assess their (in)correctness are limited. Using the conformal predict…
arXiv:2604.01116v1 Announce Type: new
Abstract: For continual learning, text-prompt-based methods leverage text encoders and learnable prompts to encode semantic features for sequentially arrived classes over time. A common challenge encountered by ex…
arXiv:2510.16082v4 Announce Type: replace-cross
Abstract: Interpreting gene clusters derived from RNA sequencing (RNA-seq) remains a persistent challenge in functional genomics, particularly in antimicrobial resistance studies where mechanistic contex…
arXiv:2604.01082v1 Announce Type: new
Abstract: Human behaviors in real-world environments are inherently interactive, with an individual’s motion shaped by surrounding agents and the scene. Such capabilities are essential for applications in virtual …
arXiv:2510.00512v2 Announce Type: replace-cross
Abstract: The transcriptional response to genetic perturbation reveals fundamental insights into complex cellular systems. While current approaches have made progress in predicting genetic perturbation r…
arXiv:2603.10495v2 Announce Type: replace
Abstract: End-to-end In-Image Machine Translation (IIMT) aims to convert text embedded within an image into a target language while preserving the original visual context, layout, and rendering style. However,…
arXiv:2604.00505v1 Announce Type: cross
Abstract: Overparameterized neural networks often show a benign overfitting property in the sense of achieving excellent generalization behavior despite the number of parameters exceeding the number of training …
arXiv:2604.01081v1 Announce Type: new
Abstract: 3D semantic occupancy prediction is central to autonomous driving, yet current methods are vulnerable to long-tailed class bias and out-of-distribution (OOD) inputs, often overconfidently assigning anoma…