…with over 10-point average improvements across seven benchmarks, and achieves results comparable to proprietary commercial models on several tasks. We will release all data, code, and models to support open research…
…Memory Organization and Retrieval via Adaptive Graph Intelligence for LLM Conversational Agents (2026) CodeTracer: Towards Traceable Agent States (2026) Please give a thumbs up to this comment if you found it helpful…
…Our code and models are available at https://github.com/compass-group-tue/arxiv2026_evaluation_meta_knowledge. View arXiv page View PDF Project page GitHub 1 Add to collection Community Parametric knowledge…
…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…
…SANA-WM achieves visual quality comparable to large-scale industrial baselines such as LingBot-World and HY-WorldPlay, while significantly improving efficiency. Four core designs drive our architecture: (1) Hybrid Linear Attention…
…Fine-tuning language models on our dataset yields substantial improvements, with relative gains often exceeding 100%, particularly for claim and proposal extraction tasks. Our error analysis reveals that extracted claims exhibit high…
…Stefanos Pasios Abstract A hybrid approach combining diffusion-based and image-to-image translation methods improves photorealism in synthetic datasets while maintaining semantic consistency. AI-generated summary Video game engines have been…
…Ming Qian , , , , Wen Wang , , , , Abstract Sat3DGen addresses the challenge of generating street-level 3D scenes from satellite images by employing a geometry-first approach that improves both geometric accuracy and photorealism through…
…Yanbiao Ji , , , , , , , , , Abstract EnergyFlow unifies generative action modeling with inverse reinforcement learning by parameterizing an energy function whose gradient serves as a denoising field, enabling reward extraction without adversarial training while improving…
…On the LIFEBench exact length matching task, applying LenVM to a 7B model improves the length score from 30.9 to 64.8, significantly outperforming frontier closed-source models. Furthermore, LenVM enables…