Generative Quality

Follow this topic Ask about this topic

Momentum

2 papers in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28

Latest papers 27

All topics

Beyond Semantic Narrowing: Robust and Efficient LLM Watermarking with Hamming Neighborhoods
Sep 29, 2026Zewen Sun, Tongyang Zhao, Liyao Xiang +3Large Language Model Watermarks Watermarks
Shanghai Jiao Tong University · Shanghai Innovation Institute · Northwest Polytechnical University, Xi’an
Flow Duality and Source Geometry for Categorical Generation
Sep 11, 2026Etrit HaxholliConditional Flow Matching Generative Quality
From Local Mismatch to Global Impact: Optimizing Cache Reuse Policy for Efficient Diffusion
Aug 13, 2026Xichen Ye, Yifan Wu, Zhikang Xie +3Diffusion Models Denoising Trajectory
College of Computer Science and Artificial Intelligence, Fudan University · Faculty of Engineering, The Chinese University of Hong Kong · School of Data Science, Fudan University
Noise in Diffusion Models Is a Learnable Input
Aug 3, 2026Shengzhi Deng, Chenqi Ye, Yanze GuoDiffusion Models Generative Quality
School of Mathematics, Harbin Institute of Technology, Harbin, China · Software College, Northeastern University, Shenyang, China
CADIR: A Cross-Backend Editable Intermediate Representation for Agentic CAD Generation
Aug 1, 2026Yu Liu, Jingzhe Ni, Yiming Chen +4Solidworks Generative Quality
Zhejiang University, China
Where Quality Breaks in Compressed Short-Text Generation: Staged Bottleneck Localization
Jul 27, 2026Alexey Gavrilov, Alan-Barsag Gazzaev, Sergey MuravyovGenerative Quality Text Generation
ITMO University Saint-Petersburg, Russia
OmniCache: Multidimensional Hierarchical Feature Caching For Diffusion Models
Jul 26, 2026Zhaoyuan He, Muhammad Muaz, Lili QiuVideo Diffusion Models Diffusion Models
Department of Computer Science, The University of Texas at Austin, Austin, TX, USA
CSD: Content-aware Speculative Decoding for Efficient Image Generation
Jun 26, 2026Mingcheng Wang, Junbo Qiao, Yunchen Li +8Autoregressive Image Generation Speculative Decoding
East China Normal University · Huawei Foundation Model · Key Laboratory of Advanced Theory and Application in Statistics and Data Science-MOE
Bifocal Diffusion Language Models: Asymmetric Bidirectional Context for Parallel Generation
Jun 26, 2026Yuhang Chen, Xianfeng Wu, Jinhao Duan +11Diffusion Language Models Bidirectional
University of North Carolina at Chapel Hill · Meta AI
EntMTP: Accelerating LLM Inference with Entropy Guided Multi Token Prediction
Jun 25, 2026Carrie ChenMulti-Token Prediction LLM Inference Optimization
Cornell University
Data-Forcing Distillation: Restoring Diversity and Fidelity in Few-Step Video Generation
Jun 16, 2026Siyi Chen, Shaowei Liu, Yixuan Jia +4Video Diffusion Models Few-Step Distillation
University of Michigan · NVIDIA · University of Illinois Urbana-Champaign
Hölder++: Improving the Quality-Coherence Trade-off in Multimodal VAEs
Jun 11, 2026Huyen Vo, María Martínez-García, Isabel ValeraConditional Variational Autoencoder Generative Quality
Department of Computer Science, Saarland University, DE · MPI-SWS, Saarland Informatics Campus, DE.
SeamEdit: A Black-Box VLM-Agnostic Pipeline for Large-Image Semantic Editing
Jun 11, 2026Xiangyu Lyu, Dan LeiImage Editing Vision-Language Foundation Models
Technische Universität Darmstadt, Darmstadt, Germany · Fine-Arts Educator, Yuncheng Middle School, Yuncheng, Shanxi, China
LFQ: Logit-aware Final-block Quantization for Boosting the Generation Quality of Low-Bit Quantized LLMs
May 28, 2026Jung Hyun Lee, June Yong Yang, Jungwook Choi +1Large Language Model Quantization Post-Training Quantization
Kim Jaechul Graduate School of AI, KAIST, Daejeon, South Korea · LG AI Research, Seoul, South Korea · Hanyang University, Seoul, South Korea +1
BlazeEdit: Generalist Image Editing on Mobile Devices with Image-to-Image Diffusion Models
May 27, 2026Fei Deng, Yanwu Xu, Zhipeng Bao +4Image Editing Text-To-Image Diffusion Models
Google
Conflict-Aware Additive Guidance for Flow Models under Compositional Rewards
May 20, 2026Xuehui Yu, Fucheng Cai, Meiyi Wang +2Flow Models Geometric Guidance
Smart Systems Institute, National University of Singapore, Singapore · Faculty of Computing, Harbin Institute of Technology, Harbin, China · School of Computing, National University of Singapore, Singapore
SafeDiffusion-R1: Online Reward Steering for Safe Diffusion Post-Training
May 18, 2026Komal Kumar, Ankan Deria, Abhishek Basu +3Text-To-Image Diffusion Models Generative Quality
Mohamed bin Zayed University of Artificial Intelligence (MBZUAI), UAE · Michigan State University (MSU), USA
Roll Out and Roll Back: Diffusion LLMs are Their Own Efficiency Teachers
May 16, 2026Fanqin Zeng, Feng Hong, Geng Yu +6Diffusion Language Models Generative Quality
Shanghai Jiao Tong University, Shanghai, China · Apple MLR, Cupertino, CA, USA · Tongji University, Shanghai, China +2
Mitigating Data Scarcity in Psychological Defense Classification with Context-Aware Synthetic Augmentation
May 14, 2026Hoang-Thuy-Duong Vu, Quoc-Cuong Pham, Huy-Hieu PhamAugmentation LLM Defense Mechanisms
College of Engineering and Computer Science, VinUniversity, Hanoi, Vietnam · VinUni-Illinois Smart Health Center, VinUniversity, Hanoi, Vietnam · Center for Innovations in Health Sciences, VinUniversity, Hanoi, Vietnam
Making AI Drafts Count: A Quality Threshold in Audio Description Workflows
May 6, 2026Lana Do, Shasta Ihorn, Charity M. Pitcher-Cooper +7Generative Quality Agentic Workflow Design
Northeastern University United States · San Francisco State University United States · The Smith-Kettlewell Eye Research Institute United States +1
VS-DDPM: Efficient Low-Cost Diffusion Model for Medical Modality Translation
Apr 24, 2026Nikoo Moradi, Gijs Luijten, Behrus Hinrichs-Puladi +4Medical Image Generation Denoising Diffusion Probabilistic Model
Institute for Artificial Intelligence in Medicine (IKIM), Essen University Hospital (AöR), University of Duisburg-Essen, Essen, Germany · Institute of Computer Graphics and Vision, Graz University of Technology, Inffeldgasse 16, Graz, 8010, Austria · Center for Virtual and Extended Reality in Medicine (ZvRM), University Hospital Essen (AöR), Essen, Germany +7
Where and What: Reasoning Dynamic and Implicit Preferences in Situated Conversational Recommendation
Apr 22, 2026Dongding Lin, Jian Wang, Yongqi Li +1Preference Alignment Learning Multimodal Large Language Models
Department of Computing, The Hong Kong Polytechnic University · College of Computer Science, Sichuan University
When Perplexity Lies: Generation-Focused Distillation of Hybrid Sequence Models
Mar 27, 2026Juan Gabriel Kostelec, Qinghai GuoEffective Distillation Symbolic Distillation
Huawei Switzerland · ACS Lab, Huawei Technologies
Naïve PAINE: Lightweight Text-to-Image Generation Improvement with Prompt Evaluation
Mar 12, 2026Joong Ho Kim, Nicholas Thai, Souhardya Saha Dip +2Text-To-Image Generative Quality
LSU ATHENA Lab, Baton Rouge, LA, U.S.A. · LSU Vision Lab, Baton Rouge, LA, U.S.A.
Training Flow Matching: The Role of Weighting and Parameterization
Mar 6, 2026Anne Gagneux, Ségolène Martin, Rémi Gribonval +1Denoising Diffusion Probabilistic Model Generative Quality
ENS de Lyon, CNRS, Universit´e Claude Bernard Lyon 1, Inria, LIP, UMR 5668, France · Technische Universität Berlin, Germany · Inria, ENS de Lyon, CNRS, Universit´e Claude Bernard Lyon 1, LIP, UMR 5668, France
EMAG: Self-Rectifying Diffusion Sampling with Exponential Moving Average Guidance
Dec 19, 2025Ankit Yadav, Ta Duc Huy, Lingqiao LiuClassifier-Free Guidance Diffusion Sampling
Australian Institute for Machine Learning, Adelaide University, Australia
NABLA: Neighborhood Adaptive Block-Level Attention
Jul 17, 2025Dmitrii Mikhailov, Aleksey Letunovskiy, Maria Kovaleva +6Generative Quality Sparsity
Kandinsky Lab, Moscow, Russia

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

Beyond Semantic Narrowing: Robust and Efficient LLM Watermarking with Hamming Neighborhoods

Zewen Sun, Tongyang Zhao, Liyao Xiang, Mingxuan Ma+2

Shanghai Jiao Tong University · Shanghai Innovation Institute · Northwest Polytechnical University, Xi’an

Large Language Model Watermarks Watermarks Large Language Model Generation Marker Generative Quality Locality-Sensitive Hashing+1

Open paper AskPDF arXiv

Semantic watermarking improves robustness against watermark removal attacks by embedding detectable signals into sentence-level representations. However, existing watermarking methods typically impose watermark-specific semantic preferences on generated sentences without explicitly accounting for the highly non-uniform and context-dependent semantic preference of LLM generation. When these two preferences are poorly aligned, many natural continuations become incompatible with the watermark, causing semantic narrowing: reduced semantic freedom, increased resampling cost, and potential degradation on tasks with strict semantic requirements. To alleviate this problem, we propose HammingMark, which uses the semantic hash of the preceding sentence as a dynamic center and accepts candidates whose hashes fall within its Hamming neighborhood. Defining watermark validity over a Hamming neighborhood in compact hash space retains a larger fraction of naturally likely semantic continuations. The coarse many-to-one hash mapping further allows diverse semantic realizations to remain watermark-valid. Experiments on C4 and BookSum show that HammingMark achieves strong robustness, high detectability, and near-unwatermarked generation quality, requiring only 2.2 sampled candidates per accepted sentence,a 72.8% reduction compared with the most sampling-efficient existing method. On more complex tasks with strict semantic constraints, HammingMark achieves the highest detection rates with the highest or tied-highest ROUGE-L scores, demonstrating its effectiveness in balancing watermark detectability and generation quality under constrained generation settings.

Momentum

Related topics

Latest papers 27