Scores

Follow this topic Ask about this topic

Momentum

23 papers in the last four weeks, up 92% on the four weeks before. 0.3% of all new papers.

Jul 6Week of Sep 21

Latest papers 94

All topics

Improving Text-to-Music Generation with Human Preference Rewards
Jun 19, 2026Yonghyun Kim, Junwon Lee, Haiwen Xia +2Text-To-Music Preference Datasets
Georgia Tech · KAIST · Peking University +2
The Token Is a Group Element: On Lie-Algebra Attention over Matrix Lie Groups
Jun 18, 2026Przemyslaw MusialskiLie Group Scores
New Jersey Institute of Technology
Exact Posterior Score Estimation for Solving Linear Inverse Problems
Jun 15, 2026Abbas Mammadov, Ozgur Kara, Kaan Oktay +5Bayesian Inverse Problems Posterior Sampling
University of Oxford · UIUC · fal +1
ScoreGate: Adaptive Chunk Selection for Retrieval-Augmented Generation via Dual-Score Statistical Fusion
Jun 12, 2026Karamvir Singh, Arvind JainDestination-Only Scoring Scores
HighLevel, Inc.
Leveraging Metric Depth for Relative Depth Prediction
Jun 9, 2026Xiaoyang Bi, Shuaikun Liu, Zhaohong Liu +5Monocular Depth Estimation Dense Prediction
Beijing Key Laboratory of Intelligent Telecommunications Software and Multimedia · Beijing University of Posts and Telecommunications
When Do Local Score Models Extrapolate Across Size? A Diagnostic Theory and Benchmark
Jun 8, 2026Wenjie XiModel Size Extrapolation
Department of Physics and HK Institute of Quantum Science & Technology The University of Hong Kong, Pokfulam Road, Hong Kong, China
Uncertainty-Aware Intention Prediction for Human-to-Robot Assembly Teleoperation
Jun 6, 2026Fnu Heman, Yixuan Wang, Kolin Xu +6Human-Robot Collaboration Teleoperation
Mechanical Engineering, University of California, Riverside, CA, USA · Electrical and Computer Engineering, University of Miami, FL, USA
Where the Score Lives: A Wavelet View of Diffusion
Jun 6, 2026Emma Finn, Binxu Wang, T. Anderson Keller +1Score-Based Diffusion Model Diffusion Models
The Kempner Instutite for the Study of Natural and Artificial Intelligence Harvard University, Cambridge, MA 15213
Diffusion Models Observe Only Gradients: A Geometric Perspective on Score Matching Errors
Jun 4, 2026Naïl B. Khelifa, Richard E. Turner, Ramji VenkataramananScore-Based Diffusion Model Diffusion Models
University of Cambridge
DASH: Dual-Branch Score Distillation for Guidance-Calibrated Compact Diffusion Models
May 30, 2026Abdullah Al Shafi, Kazi Saeed Alam, Sk Imran Hossain +1Dataset Distillation Text-Conditioned Diffusion Model
Khulna University of Engineering & Technology, Bangladesh · University Clermont Auvergne, France
Score $\times$ Decoder: A Unified View of Unsupervised Inference-Time Scaling for Hallucination Mitigation
May 30, 2026Yun-Chen Cheng, Che-Yu Lin, Cheng-Lin YangLarge Language Model Hallucination Inference-Time
CyCraft AI Lab, Taiwan
Score Broadcast and Decorrelation: A General Framework for Broadcast-Based Credit Assignment
May 28, 2026Mustafa Uzun, Mete Erdogan, Cengiz Pehlevan +1Loss Function Credit Assignment
KUIS AI Center, Koc University, Turkey · Electrical and Electronics Engineering, Koc University, Turkey · Department of Electrical Engineering, Stanford University, USA +3
Offloading Score: Measuring AI Reliance Through Counterfactual Workflows
May 28, 2026Vishakh Padmakumar, Lujain Ibrahim, Zora Zhiruo Wang +3Cognitive Load Offloading
Stanford University · University of Oxford · Carnegie Mellon University +1
Score Based Error Correcting Code Decoder
May 27, 2026Alon Helvits, Eliya NachmaniQuantum Error Correction Signal-To-Noise Ratio
School of Electrical and Computer Engineering (ECE), Ben Gurion University, Beer Sheva, Israel.
Smoothed Score Queries and the Complexity of Sampling
May 26, 2026Jingbo LiuOptimal Sample Complexity Scores
Department of Statistics, University of Illinois Urbana–Champaign
From Scores to Gibbs Correctors: Accelerating Uniform-Rate Discrete Diffusion Models
May 26, 2026Yuchen Liang, Ness Shroff, Yingbin LiangDiffusion Sampling Diffusion Dynamics
The Ohio State University
Precise and Simple Audio-to-Score Alignment
May 19, 2026Silvan Peter, Patricia Hu, Gerhard WidmerSpeech-To-Text Alignment Transcription
Institute of Computational Perception, Johannes Kepler University, Linz, Austria · LIT AI Lab, Linz Institute of Technology, Linz, Austria
The Score Kalman Filter
May 15, 2026Kaito Iwasaki, Anthony Bloch, Taeyoung Lee +1Bayesian Filtering Extended Kalman Filter
Department of Mathematics University of Michigan · Department of Mechanical and Aerospace Engineering George Washington University · Department of Naval Architecture & Marine Engineering and Department of Robotics University of Michigan
Is One Score Enough? Rethinking the Evaluation of Sequentially Evolving LLM Memory
May 14, 2026Songwei Dong, Zihan Chen, Chengshuai Shi +3Large Language Model Memory Forgetting
University of Virginia · Princeton University
Does Your Wildfire Prediction Model Actually Work, or Just Score Well?
May 14, 2026Yangshuang Xu, Yuyang Dai, Liling Chang +2Wildfire Prediction Wireless Foundation Models
Florida State University · Northeastern University
Training-Free Generative Sampling via Moment-Matched Score Smoothing
May 14, 2026Zhenyu Yao, Daniel PaulinScore-Based Diffusion Model Diffusion Models
College of Computing and Data Science Nanyang Technological University
Finite Sample Bounds for Learning with Score Matching
May 13, 2026Devin Smedira, Abhijith Jayakumar, Sidhant Misra +2Optimal Sample Complexity Exponential Family
Operations Research Center, Massachusetts Institute of Technology · Theoretical division, Los Alamos National Lab
Keeping Score: Efficiency Improvements in Neural Likelihood Surrogate Training via Score-Augmented Loss Functions
May 12, 2026Alexander Shen, Mikael KuuselaSurrogates Uncertainty Score
Department of Statistics and Data Science Carnegie Mellon University Pittsburgh, PA 15213
Zero-Shot Neural Network Evaluation with Sample-Wise Activation Patterns
May 8, 2026Yameng Peng, Andy Song, HaythamM. Fayek +2Zero-Shot Convolutional Neural Networks
School of Computing Technologies, RMIT University, Australia · Department of Electronic Engineering and Information Science, University of Science and Technology of China
MIRA: A Score for Conditional Distribution Accuracy and Model Comparison
May 3, 2026Sammy Sharief, Justine Zeghal, Gabriel Missael Barco +3Conditional Distribution Bayesian Inference
Mila – Québec AI Institute, Montreal, Quebec, Canada · Ciela Institute, Montreal, Quebec, Canada · Université de Montréal, Montreal, Quebec, Canada +4
VLM Judges Can Rank but Cannot Score: Task-Dependent Uncertainty in Multimodal Evaluation
Apr 28, 2026Divake Kumar, Sina Tayebati, Devashri Naik +2Multimodal Evaluation Large Language Model Judges
University of Illinois at Chicago · 2AI Labs at Capital One
A Kernel Nonconformity Score for Multivariate Conformal Prediction
Apr 23, 2026Louis Meyer, Wenkai XuNonconformity Scores Online Conformal Prediction
University of Warwick
What Does a Sharing Question Add? Auditing LLM Survey Scores for Misinformation
Apr 8, 2026Zonghuan Xu, Xiang Zheng, Yutao Wu +1Misinformation Credibility
Shanghai Key Laboratory of Multimodal Embodied AI, Shanghai, China · City University of Hong Kong, Hong Kong SAR, China · Deakin University, Australia
MultiwayPAM: Multiway Partitioning Around Medoids for LLM-as-a-Judge Score Analysis
Mar 11, 2026Chihiro Watanabe, Jingyu SunLlm-As-A-Judge Scores
NTT Computer and Data Science Laboratories, 3-9-11, Midori-cho, Musashino-shi, Tokyo, Japan
Control Variate Score Matching for Diffusion Models
Dec 23, 2025Khaled Kahouli, Romuald Elie, Klaus-Robert Müller +3Score-Based Diffusion Model Diffusion Models
1Google DeepMind · 2BIFOLD – Berlin Institute for the Foundations of Learning and Data · 3Machine Learning Group, Technische Universität Berlin +2
Rethinking Reward Signals in Video GRPO: When Scores Become Targets
Nov 24, 2025Rui Li, Yuanzhi Liang, Ziqi Ni +3Repair-Based Group-Relative Policy Optimization Reward Signal
University of Science and Technology of China, Hefei, China · Institute of Artificial Intelligence (TeleAI), China Telecom, Shanghai, China · Southeast University, Nanjing, China
Multi-Channel Uncertainty-Weighted Score Matching for Conditional Diffusion in Medical UDA
Sep 26, 2025Chen Li, Meilong Xu, Xiaoling Hu +2Text-Conditioned Diffusion Model Semi-Supervised Medical Image Segmentation
Stony Brook University, Stony Brook, NY, USA · Massachusetts General Hospital and Harvard Medical School, MA, USA
Protect Your Score: Contact Tracing With Differential Privacy Guarantees
Date pendingRob Romijnders, Christos Louizos, Yuki M. Asano +1Δ)$-Differential Privacy Covid-19
University of Amsterdam · Qualcomm AI research
'Ghaib in Translation' aka Unseen Harm: Measuring Cross-Script Safety Inconsistency with 'Missed-in-Urdu' Scores in LLM Hate Speech Detection
Date pendingFawzia Zehra (Fuzzy), Kara-Isitt, Sonal Khosla +1Urdu Multilingual Safety
Brunel University of London, UK · Hasso Plattner Institute Potsdam, Germany

Jun 19, 2026, cs.SDJ/K move · Enter open · S save

Improving Text-to-Music Generation with Human Preference Rewards

Yonghyun Kim, Junwon Lee, Haiwen Xia, Yinghao Ma+1

Georgia Tech · KAIST · Peking University+2

Text-To-Music Preference Datasets Tuning Preference Alignment Learning Scores

Open paper AskPDF arXiv

We describe our entry to the efficiency track of the Academic Text-to-Music (ATTM) Grand Challenge at ICME 2026. Beyond the challenge protocol's FAD-CLAP and CLAP score, we add a learned human-preference reward from TuneJury, a twin pairwise ranker trained over open music-preference datasets. The reward serves both as a training-time conditioning signal and as a sample-selection criterion. The pipeline combines five engineering decisions on a 120M-parameter FluxAudio-S backbone, four at training time and one at inference: (i) training-time reward conditioning that doubles as an inference-time CFG axis, (ii) a sweep over five score-conditioning architectures, where training and inference use different variants, (iii) expert iteration on the top decile, (iv) a short preference-tuning pass (CRPO) for audio-text alignment, and (v) inference post-processing via joint CFG, source separation, and loudness normalization. Per-stage decomposition on 100 Song Describer prompts shows training-time reward conditioning as a functional conditioning axis, expert iteration as the dominant contributor, the preference-tuning pass adding only noise-level gain, and the inference-time score scalar already saturated by the end of the chain.

Momentum

Related topics

Latest papers 94