New Era

Follow this topic Ask about this topic

Momentum

3 papers in the last four weeks, against 2 the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28

Latest papers 19

All topics

After a Decade: Bringing Shadow Removal into the Real World with Agentic Training Data
Sep 29, 2026Shilin Hu, Jingyi Xu, Dimitris Samaras +1Diverse Occlusion-And-Revelation Scenarios Training Data
Department of Computer Science Stony Brook University · Department of Computer Science University of North Carolina at Charlotte
Tracing the Evolution of Oracle Bone Characters Across Three Millennia
Sep 28, 2026Tianhao Fu, Xinxin Xu, Spike Wang +3Historical Manuscripts Oracles
Peking University · Independent
Write on Paper and Get the Online Digital Trace:\newline A New Era for Handwriting
Sep 14, 2026Florent Imbert, Yann Soullard, Eric Anquetil +5Handwriting Traces
IRISA, Universit´e de Rennes, INSA Rennes, France · LTU, Machine Learning Group, Lule˚a University of Technology, Sweden · IRISA, Universit´e Rennes 2, France +2
Measuring Cross-Cultural Style Diffusion Through Era Classification: US and Korean Popular Music
Aug 11, 2026Dasol Lee, Minhee Lee, Seonguk Ju +3Cross-Cultural Variation New Era
Music & Arts Learning (MALer) Lab, Sogang University, South Korea · University of Cambridge
What We Know about Responsible AI Practices in Industry: A Half Decade of Empirical Research
Aug 11, 2026Wesley Hanwen Deng, Agathe Balayn, Andrew Selbst +6Organizational Research Empirical Study
Microsoft Research, USA · University of California, Los Angeles, USA · Carnegie Mellon University, USA
From Cheap Fakes to Pure Synthesis: Addressing the New Era of T2V Fake News Videos
Aug 7, 2026Yifeng Luo, Yupeng Li, Liang Lan +1Fake News Detection Fake News
Department of Interactive Media Hong Kong Baptist University AI and Social Good Lab, AI Media Centre Hong Kong Baptist University Hong Kong, China · Department of Interactive Media Hong Kong Baptist University AI Media Centre Hong Kong Baptist University Hong Kong, China · Institute of Artificial Intelligence and Future Networks Beijing Normal University Zhuhai, China
Modeling Stylistic Co-evolution in Symbolic Music Heritage Collections
Jul 27, 2026Yulong He, Ivan Smirnov, Yanming LiSymbolic Music Generation Harmonization
St. Petersburg State University, St. Petersburg, Russia · ITMO University, St. Petersburg, Russia · St. Petersburg State Institute of Culture, St. Petersburg, Russia
The Aura in the Machine: Genealogy and the Status of the Work of Art in the Generative Era
Jul 20, 2026Giorgio PrestiGenerative Artificial Intelligence Artistic Ownership
Department of Computer Science, Universit`a degli Studi di Milano, Via G. Celoria, Milan, 20133, Italy.
From Gentlemen to Frontiermen: Masculine Formations in English-Language Fiction (1771--1930)
Jul 3, 2026Rong WangGender New Era
University of Tuebingen
Cross-National Information Attacks: A Two-Decade Analysis of Troll Behavior in Korea
Jun 22, 2026Jaehong Kim, Hyeonseung Kim, Jiseon Kim +4Social Influence Content Moderation
1Korea Advanced Institute of Science and Technology (KAIST), Daejeon, South Korea · 2Max Planck Institute for Security and Privacy (MPI-SP), Bochum, Germany
Economic Transformation and Cultural Change: Evidence from Two Centuries of French Drama
Jun 19, 2026T. D. Oliveira, L. A. Attilio, M. J. Davila-FernandezCultural Evolution Economies
Centre for Digital Humanities, University of Tartu · Federal University of Ouro Preto · Colorado State University
AI4SE and SE4AI Exploration: A Decade Looking Back and Forward
Jun 17, 2026H. Sinan Bank, Daniel R. Herber, Thomas BradleyEngineering Insights
Department of Systems Engineering Colorado State University Fort Collins, CO 80523
Institutions and the transmission of upper-tail human capital: scientific lineages across a millennium
May 29, 2026Hiroyuki Chuma, Kanji Otsuka, Yoichi SatoLineages Institutions
Institute of Innovation Research, Hitotsubashi University, 2-1 Naka, Kunitachi, Tokyo 186-8603, Japan. · Meisei University · Shuhari System
Subcortical Shape Variations and Their Associations with Cognition Across the 8th Decade of Life. A Study in the Lothian Birth Cohort 1936
May 28, 2026Maria del C. Valdes-Hernandez, Wonjung Park, Joanna Moodie +7Brain Age Longitudinal Data
Department of Neuroimaging Sciences, University of Edinburgh, 49 Little France Crescent, Edinburgh, EH164SB, United Kingdom. · Computer Graphics and Visualization Laboratory, Korea Advanced Institute of Science and Technology (KAIST), 291 Daehak-ro, Daejeon, 34141, Republic of Korea. · Department of Psychology, University of Edinburgh, 7 George Square, Edinburgh, EH89JZ, United Kingdom. +1
Visual Generation in the New Era: An Evolution from Atomic Mapping to Agentic World Modeling
Apr 30, 2026Keming Wu, Zuhao Yang, Kaichen Zhang +24Visual Generation World Models
1Tsinghua University · 12LMMs-Lab · 2Nanyang Technological University +9
Post-training is (Massive) Supervised Learning
Apr 20, 2026Michael Hassid, Yossi Adi, Roy SchwartzPost-Training Pretraining
1FAIR, Meta AI · 2The Hebrew University of Jerusalem
Scaling Latent Reasoning via Looped Language Models
Oct 29, 2025Rui-Jie Zhu, Zixuan Wang, Kai Hua +30LLM Reasoning Strategies Efficient Latent Reasoning
1ByteDance Seed · 2UC Santa Cruz · 3Princeton University +8
ArchesClimate: Probabilistic Decadal Ensemble Generation With Flow Matching
Sep 19, 2025Graham Clyne, Guillaume Couairon, Guillaume Gastineau +2Global Climate Models Climate
ARCHES, INRIA, Paris, France · UMR LOCEAN, IPSL, Sorbonne Universit´e, IRD, CNRS, MNHN, Paris, France · Department of Computer Science, University of Colorado Boulder, USA
The evolution of inharmonicity and noisiness in contemporary popular music
Aug 15, 2024Emmanuel Deruty, David Meredith, Stefan LattnerHarmonization New Era
Sony Computer Science Laboratories, 6 rue Amyot, 75005 Paris, France · Department of Architecture, Design and Media Technology, Aalborg University, Rendsburggade 14, 9000 Aalborg, Denmark

Sep 29, 2026, cs.CVJ/K move · Enter open · S save

After a Decade: Bringing Shadow Removal into the Real World with Agentic Training Data

Shilin Hu, Jingyi Xu, Dimitris Samaras, Hieu Le

Department of Computer Science Stony Brook University · Department of Computer Science University of North Carolina at Charlotte

Diverse Occlusion-And-Revelation Scenarios Training Data Real-World Agentic New Era

Open paper AskPDF arXiv

Shadow removal looks nearly solved on established benchmarks, yet remains brittle in the real world. Models have advanced; the paired training data they rely on have barely changed in nearly a decade. The reason is simple: obtaining a shadow-free target requires removing the occluder while keeping the scene, camera, and illumination otherwise unchanged, making diverse paired data difficult to capture. Meanwhile, large shadow detection datasets already contain diverse real-world images and masks, but no shadow-free targets. To turn this abundant but incomplete data into paired supervision, we propose an offline agentic workflow combining physics-motivated generation, failure detection, feedback-driven retry, candidate selection, and deterministic correction. Using this workflow, we construct AgenticShadow, a dataset of 17,138 image-mask-target triplets spanning general scenes, faces, and remote sensing. Our construction workflow reduces Color Distribution Difference by 50.5% over previous shadow removal work, while training existing shadow removal models on AgenticShadow reduces cross-domain LAB RMSE by 19.7-37.5%.

Momentum

Related topics

Latest papers 19