…View arXiv page View PDF Project page GitHub 1 Add to collection Community In-context learning (ICL) is the standard method for low-resource classification, yet its efficacy in specialized domains remains…
…Injecting 3D Spatial Priors into Vision-Language Models for Enhanced Geometric Reasoning Published on May 28 Submitted by Chun-Hsiao Yeh on May 29 Authors: Chun-Hsiao Yeh , , , , , Abstract Training Vision-Language…
…Building upon the Spectrum-to-Signal post-training paradigm , we systematically enhance the model through an optimized pipeline that includes curriculum-based supervised fine-tuning , multi-domain reinforcement learning , and offline self…
…Can Synthetic Linguistic Reasoning Traces Enhance Low-Resource Machine Translation? Published on Jun 2 Submitted by Shaoxiong on Jun 9 Omni Language AI Research Authors: , , , , Abstract Large language models can improve translation…
…Enhancing Gaussian Splatting Using Primitives with Spatially Varying Colors Published on May 4 Submitted by Rui Xu on May 6 University of Hong Kong Authors: , , , , , , , , , Abstract Spatially varying Gaussian splatting improves multi…
…Rather than expanding the training corpus indiscriminately, PaddleOCR-VL-1.6 introduces a region-aware data optimization framework that identifies weak regions from the previous model, applies targeted enhancement to these regions…
…Zhuohan Liu , , , Abstract BiDPO enhances text-to-image models for complex compositional prompts through preference-based fine-tuning and region-level guidance. Generated by Qwen/Qwen2.5-Coder-32B-Instruct Despite the…
…To tackle the convergence challenges of high-dimensional latent space, we implement an enhanced semantic alignment strategy to make the latent space highly amenable to diffusion modeling. To optimize computational efficiency, we…
…to collection Community Multimodal Large Language Models (MLLMs) have demonstrated remarkable success in visual understanding, yet their performance degrades significantly under real-world visual corruptions. While existing robustness enhancement approaches exist, they…
…View arXiv page View PDF Project page Add to collection Community Lumos-Nexus is a training-efficient unified video generation framework that uses Unified Progressive Frequency Bridging to enhance visual fidelity while…