Copertina

Learning to Think in Physics: Breaking Shortcut Learning in Scientific Diffusion via Representation Alignment

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Jia, Haozhe, Yin, Pengyu, Chen, Wenshuo, Liang, Shaofeng, Wang, Lei, Tian, Bowen, Wang, Xiucheng, Jia, Nanqian, Yue, Yutao
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Physics-Informed Representation Alignment for Sparse Radio-Map Reconstruction
di: Jia, Haozhe, et al.
Pubblicazione: (2025)

Oracle Noise: Faster Semantic Spherical Alignment for Interpretable Latent Optimization
di: Li, Haosen, et al.
Pubblicazione: (2026)

LUMA: Low-Dimension Unified Motion Alignment with Dual-Path Anchoring for Text-to-Motion Diffusion Model
di: Jia, Haozhe, et al.
Pubblicazione: (2025)

Guided Path Sampling: Steering Diffusion Models Back on Track with Principled Path Guidance
di: Li, Haosen, et al.
Pubblicazione: (2025)

POLARIS: Projection-Orthogonal Least Squares for Robust and Adaptive Inversion in Diffusion Models
di: Chen, Wenshuo, et al.
Pubblicazione: (2025)

$Z^2$-Sampling: Zero-Cost Zigzag Trajectories for Semantic Alignment in Diffusion Models
di: Li, Haosen, et al.
Pubblicazione: (2026)

Delta Score Matters! Spatial Adaptive Multi Guidance in Diffusion Models
di: Li, Haosen, et al.
Pubblicazione: (2026)

RadioFlow: Efficient Radio Map Construction Framework with Flow Matching
di: Jia, Haozhe, et al.
Pubblicazione: (2025)

Before the Body Moves: Learning Anticipatory Joint Intent for Language-Conditioned Humanoid Control
di: Jia, Haozhe, et al.
Pubblicazione: (2026)

Free-T2M: Robust Text-to-Motion Generation for Humanoid Robots via Frequency-Domain
di: Chen, Wenshuo, et al.
Pubblicazione: (2025)

Neural Electromagnetic Fields for High-Resolution Material Parameter Reconstruction
di: Chen, Zhe, et al.
Pubblicazione: (2026)

Breaking Scale Anchoring: Frequency Representation Learning for Accurate High-Resolution Inference from Low-Resolution Training
di: Wang, Wenshuo, et al.
Pubblicazione: (2025)

ANT: Adaptive Neural Temporal-Aware Text-to-Motion Model
di: Chen, Wenshuo, et al.
Pubblicazione: (2025)

AnyEdit++: Adaptive Long-Form Knowledge Editing via Bayesian Surprise
di: Tian, Bowen, et al.
Pubblicazione: (2026)

Latent Diffusion Model Based Denoising Receiver for 6G Semantic Communication: From Stochastic Differential Theory to Application
di: Wang, Xiucheng, et al.
Pubblicazione: (2025)

ECHO: Edge-Cloud Humanoid Orchestration for Language-to-Motion Control
di: Jia, Haozhe, et al.
Pubblicazione: (2026)

Text2Weight: Bridging Natural Language and Neural Network Weight Spaces
di: Tian, Bowen, et al.
Pubblicazione: (2025)

Super-Resolution Enhancement of Medical Images Based on Diffusion Model: An Optimization Scheme for Low-Resolution Gastric Images
di: Jia, Haozhe
Pubblicazione: (2025)

RadioDiff-FS: Physics-Informed Manifold Alignment in Few-Shot Diffusion Models for High-Fidelity Radio Map Construction
di: Wang, Xiucheng, et al.
Pubblicazione: (2026)

RadioMamba: Breaking the Accuracy-Efficiency Trade-off in Radio Map Construction via a Hybrid Mamba-UNet
di: Jia, Honggang, et al.
Pubblicazione: (2025)

AlignDiff: Learning Physically-Grounded Camera Alignment via Diffusion
di: Xie, Liuyue, et al.
Pubblicazione: (2025)

Improving the Classification Effect of Clinical Images of Diseases for Multi-Source Privacy Protection
di: Bowen, Tian, et al.
Pubblicazione: (2024)

Point-SRA: Self-Representation Alignment for 3D Representation Learning
di: Wei, Lintong, et al.
Pubblicazione: (2026)

SLAP: Shortcut Learning for Abstract Planning
di: Liu, Y. Isabel, et al.
Pubblicazione: (2025)

Conditional Information Bottleneck for Multimodal Fusion: Overcoming Shortcut Learning in Sarcasm Detection
di: Wang, Yihua, et al.
Pubblicazione: (2025)

RadioMapMotion: A Dataset and Baseline for Proactive Spatio-Temporal Radio Environment Prediction
di: Jia, Honggang, et al.
Pubblicazione: (2025)

Step-level Denoising-time Diffusion Alignment with Multiple Objectives
di: Zhang, Qi, et al.
Pubblicazione: (2026)

Mixture of Group Experts for Learning Invariant Representations
di: Kang, Lei, et al.
Pubblicazione: (2025)

Model-Free Robust Reinforcement Learning with Sample Complexity Analysis
di: Wang, Yudan, et al.
Pubblicazione: (2024)

Wolf2Pack: The AutoFusion Framework for Dynamic Parameter Fusion
di: Tian, Bowen, et al.
Pubblicazione: (2024)

Multimodal Representation Alignment for Image Generation: Text-Image Interleaved Control Is Easier Than You Think
di: Chen, Liang, et al.
Pubblicazione: (2025)

PointDico: Contrastive 3D Representation Learning Guided by Diffusion Models
di: Li, Pengbo, et al.
Pubblicazione: (2025)

Learn for Variation: Variationally Guided AAV Trajectory Learning in Differentiable Environments
di: Wang, Xiucheng, et al.
Pubblicazione: (2026)

Reinforcement Learning with Physics-Informed Symbolic Program Priors for Zero-Shot Wireless Indoor Navigation
di: Li, Tao, et al.
Pubblicazione: (2025)

ShortFT: Diffusion Model Alignment via Shortcut-based Fine-Tuning
di: Guo, Xiefan, et al.
Pubblicazione: (2025)

Demonstrating and Reducing Shortcuts in Vision-Language Representation Learning
di: Bleeker, Maurits, et al.
Pubblicazione: (2024)

Achieving the Asymptotically Optimal Sample Complexity of Offline Reinforcement Learning: A DRO-Based Approach
di: Wang, Yue, et al.
Pubblicazione: (2023)

Emotion-Director: Bridging Affective Shortcut in Emotion-Oriented Image Generation
di: Jia, Guoli, et al.
Pubblicazione: (2025)

Reasoning Physical Video Generation with Diffusion Timestep Tokens via Reinforcement Learning
di: Lin, Wang, et al.
Pubblicazione: (2025)

Break the Chain: Large Language Models Can be Shortcut Reasoners
di: Ding, Mengru, et al.
Pubblicazione: (2024)