Conditional Generation

Follow this topic Ask about this topic

Momentum

2 papers in the last four weeks, down 33% on the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28

Latest papers 34

All topics

Balancing Reference Guidance and Free Generation in Trajectory Rollouts for Reasoning RL
Oct 8, 2026Hanyu Wang, Nakul Agarwal, Hossein Nourkhiz Mahjoub +4LLM Reasoning RL for Language Model Reasoning
The Pennsylvania State University · Honda Research Institute USA · Honda Research Institute Japan
FACET: Factorized Asymmetric Conditioning for Efficient Transport in High-Fidelity Fluorescence Microscopy Synthesis
Oct 4, 2026Sazan Mahbub, Caleb N. Ellington, Eric P. XingConditional Image Generation Diffusion-Based Image Generation
Carnegie Mellon University · GenBio AI · Mohamed bin Zayed University of AI
When Victorian Becomes a Prompt: Literary Periodization as a Generative Constraint in 100 AI-Generated Novels
Sep 8, 2026Mehdy Sedaghat PayamComputational Literary Studies Controllable Text Generation
Independent Scholar
PragAlign: Feedback-Guided Pragmatic Alignment for Controlled Synthetic Dialogue Generation
Sep 2, 2026Smitha Muthya Sudheendra, Jaideep SrivastavaText Generation Controllable Text Generation
University of Minnesota, Twin Cities
The Missing Temporal Link: Temporal Context Routing for Script-Driven Audio-Video Generation
Sep 2, 2026Yichen Liu, Quanwei Zhang, Haozhe Wang +7Audio-Video Generation Conditional Generation
PKU · Qwen Applications · HKUST +2
Intent Speaks Louder: Controllable User Simulation Beyond Response Imitation
Aug 10, 2026Bo Wang, Ruixing Zhang, Yunqi Liu +4User Simulation Conditional Generation
the State Key Laboratory of Complex and Critical Software Environment, Beihang University
Mitigating Domain Shift in Conditioned Floor Plan Generation: Synthetic Pre-training for Data-Efficient Adaptation
Jul 7, 2026Matthieu Ospici, Arnaud Gueze, Luc Bourrat +1Synthetic Data Pretraining Synthetic-to-Real Domain Adaptation
Homiwoo, 8 rue la Boétie, 75008 Paris, France · École Polytechnique, Route de Saclay, 91128 Palaiseau, France
Property-Constrained 3D Porous Media Reconstruction from 2D Images via Conditional Generative Adversarial Networks
Jul 2, 2026Ali Sadeghkhani, Brandon Bennett, Arash Rabbani3D Reconstruction Conditional Generative Modeling
School of Computer Science, University of Leeds, Leeds, UK
MUSE: Unlocking Timestep as Native Task Steering for One-Step Dense Prediction
Jun 29, 2026Shuo Zhou, Zhaoxin Li, Xiujuan ChaiMonocular Depth Estimation Surface Normal Estimation
Agricultural Information Institute, Chinese Academy of Agricultural Sciences, Beijing, China. · Key Laboratory of Agricultural Big Data, Ministry of Agriculture and Rural Affairs, Beijing, China.
Navigating User Behavior toward Personalized Multimodal Generation
Jun 23, 2026Hengji Zhou, Yufeng Liu, Ye Liu +3Multimodal Generation Conditional Generation
South China University of Technology · Harbin Institute of Technology, Shenzhen
X+Slides: Benchmarking Audience-Conditioned Slide Generation
Jun 17, 2026Haodong Chen, Xuanhe Zhou, Wei Zhou +6Evidence-Grounded Generation Conditional Generation
Shanghai Jiao Tong University · Harbin Institute of Technology · SenseTime
SWE-Future: Forecast-Conditioned Data Synthesis for Future-Oriented Software Engineering Agents
Jun 17, 2026Qiao Zhao, JianYing Qu, Jun Zhang +3Software Engineering Agents Software Engineering Benchmarks
Baidu Inc.
Pre-Training for Simulation-Based Science: A Study on Jet Foundation Model Training Objectives
Jun 12, 2026Ibrahim Elsharkawy, Joschka Birk, Vinicius Mikuni +3Self-Supervised Pre-Training High-Energy Physics
Department of Physics, University of Toronto and Vector Institute, Toronto, ON, Canada · NERSC, Lawrence Berkeley National Laboratory, Berkeley, California, USA · Institut für Experimentalphysik, Universität Hamburg, 22761 Hamburg, Germany +3
Constrained Semantic Decompression in LLMs through Persian Proverb-Conditioned Story Generation
Jun 10, 2026Zahra Habibzadeh, Paria Khoshtab, Amir Mesbah +1LLM Evaluation LLM Grounding
Tehran Institute for Advanced Studies, Khatam University, Iran
Assessing Sample Quality in Conditional Generation under Compositional Shift
Jun 8, 2026Berker Demirel, Valentino Maiorca, Marco Fumero +2Distribution Shift Conditional Generation
Institute of Science and Technology Austria (ISTA) · Pyramidal Inc, San Francisco, CA, USA · Achira Inc, San Francisco, CA, USA
REACT 2026: The Fourth Multiple Appropriate Facial Reaction Generation Challenge: Personalised MAFRG and Appropriate EEG Reaction Prediction
Jun 6, 2026Siyang Song, Micol Spitale, Zijian Wu +11Conditional Image Generation Multimodal Generation
University of Exeter United Kingdom · Politecnico di Milano Milan, Italy · Nanjing University of Science and Technology China +8
Drifting Models for Surrogate Flow Modeling
Jun 5, 2026Chris R. Jung, Markus Dörr, Natalie Jüngling +3PDE Surrogate Modeling Conditional Generative Modeling
Center for Machine Learning (ZML) 2Institute for Flow in Additively Manufactured Porous Structures (ISAPS) Heilbronn University of Applied Sciences, 74081 Heilbronn, Germany
Conditional Hypothesis Generation for LLM-Based Text Analysis with Researcher-Specified Covariates
Jun 2, 2026Paiheng Xu, Jing Liu, Wei AiScientific Hypothesis Generation Computational Social Science
University of Maryland, College Park
GeoSVG-RL: Geometry-Aware Reinforcement Learning for Layout-Constrained Text-to-SVG Diagram Generation
May 25, 2026Sifan Li, Yujun Cai, Hongkai Chen +1RL for Generative Models Conditional Generation
University of California, Merced · The University of Queensland · vivo Mobile Communication Co., Ltd.
Omni-Customizer: End-to-End MultiModal Customization for Joint Audio-Video Generation
May 17, 2026Yuheng Chen, Qingdong He, Teng Hu +4Audio-Video Generation Audio-Visual Synchronization
Shanghai Jiao Tong University · University of Electronic Science and Technology of China · Zhejiang University
Multimodal Alignment and Preference Optimization for Zero-Shot Conditional RNA Generation
May 12, 2026Roman Klypa, Alberto Bietti, Sergei GrudininMolecular Generation Conditional Generation
Univ. Grenoble Alpes, CNRS, Grenoble INP, LJK · Grenoble, France · Center for Computational Mathematics, Flatiron Institute +1
PG-LRF: Physiology-Guided Latent Rectified Flow for Electro-Hemodynamic PPG-to-ECG Generation
May 9, 2026Xiaoda Wang, Minxiao Wang, Kaiqiao Han +10Electrocardiography Physics-Informed ML
Department of Computer Science, Emory University · Department of Computer Science, University of California, Los Angeles · Nell Hodgson Woodruff School of Nursing, Emory University +2
The Garden of Forking Paths: Threading Narrative Archetype as a Semantic Signal Through Gameplay Planning
May 2, 2026Yunge Wen, Chenliang Huang, Hangyu Zhou +6Interactive Storytelling Procedural Content Generation
Massachusetts Institute of Technology · New York University · Nanyang Technological University +1
From LLM-Driven Trading Card Generation to Procedural Relatedness: A Pokémon Case Study
Apr 30, 2026Johannes Pfau, Panagiotis VrettisGenerative Modeling Procedural Content Generation
Utrecht University · Utrecht, Netherlands
Personalized Worked Example Generation from Student Code Submissions Using Pattern-based Knowledge Components
Apr 27, 2026Griffin Pitts, Muntasir Hoq, Peter Brusilovsky +4Computer Science Education Programming Education
North Carolina State University Raleigh, NC, USA · University of Pittsburgh Pittsburgh, PA, USA · University of California, Berkeley Berkeley, CA, USA +1
OccDirector: Language-Guided Behavior and Interaction Generation in 4D Occupancy Space
Apr 24, 2026Zhuding Liang, Tianyi Yan, Dubing Chen +6Diffusion Transformer Multi-Agent Systems
SKL-IOTSC, CIS, University of Macau, Macau, China · Li Auto Inc, Beijing, China
ParetoSlider: Diffusion Models Post-Training for Continuous Reward Control
Apr 22, 2026Shelly Golan, Michael Finkelson, Ariel Bereslavsky +2Multi-Objective Reinforcement Learning RL for Image Generation
Tel Aviv University · Lightricks · Adobe Research
Graph2Counsel: Clinically Grounded Synthetic Counseling Dialogue Generation from Client Psychological Graphs
Apr 22, 2026Aishik Mandal, Hiba Arnaout, Clarissa W. Ong +5Mental Health Counseling Mental Health
UKP Lab, Department of Computer Science and Hessian Center for AI (hessian.AI), Technische Universität Darmstadt · Zuse School · National Research Center for Applied Cybersecurity ATHENE +4
Generative Drifting for Conditional Medical Image Generation
Apr 21, 2026Zirong Li, Siyuan Mei, Weiwen Wu +33D Medical Imaging One-Step Generative Modeling
Department of Orthodontics and Orofacial Orthopedics, Friedrich-Alexander-University Erlangen-Nuremberg, Erlangen, Germany · Department Artificial Intelligence in Biomedical Engineering, Friedrich-Alexander-University Erlangen-Nuremberg, Erlangen, Germany · Pattern Recognition Lab, Friedrich-Alexander-University Erlangen-Nuremberg, Erlangen, Germany +1
Ego-InBetween: Generating Object State Transitions in Ego-Centric Videos
Apr 20, 2026Mengmeng Ge, Takashi Isobe, Xu Jia +7HOI Generation Action-Conditioned Video Generation
Advanced Micro Devices, Inc. · Dalian University of Technology · The Hong Kong University of Science and Technology +2

Oct 8, 2026, cs.AIJ/K move · Enter open · S save

Balancing Reference Guidance and Free Generation in Trajectory Rollouts for Reasoning RL

Hanyu Wang, Nakul Agarwal, Hossein Nourkhiz Mahjoub, Ehsan Moradi Pari+3

The Pennsylvania State University · Honda Research Institute USA · Honda Research Institute Japan

LLM Reasoning RL for Language Model Reasoning Text Generation Conditional Generation

Open paper AskPDF arXiv

A verified reference solution provides a correct trajectory for training a reasoning model. Alternatively, a prefix of the reference can guide the model in generating a trajectory of its own. How much reference guidance should we provide? We study this question through prefix continuation, where the model continues from a reference prefix and keeps the resulting trajectory if it passes verification, falling back to the reference otherwise. Since both procedures produce correct trajectories, we compare their distributions with the ideal distribution, the model's own distribution conditioned on successful verification. For one continuation, we derive the KL divergence in closed form, which, up to a bounded term, decreases with the product of the probability of generating a different correct trajectory and the reference surprisal, the negative log probability of the reference suffix given the prefix. Since a longer prefix tends to raise the former but lowers the latter, continuation success alone does not determine the preferred amount of guidance. From this analysis, we learn a prefix selector shared across training questions from continuation outcomes, without estimating success probabilities or additional generation. The resulting Adaptive Reference Guidance (ARG) constructs correct trajectories within a fixed generation budget, and we apply it to all-failure groups in Group Relative Policy Optimization (GRPO). Experiments on Qwen3-4B and Qwen3-8B across five mathematical reasoning benchmarks show that ARG achieves the highest aggregate pass@12 among the evaluated methods with competitive average sampled accuracy.

Momentum

Related topics

Latest papers 34