Cover Image

Rethinking Losses for Diffusion Bridge Samplers

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Sanokowski, Sebastian, Gruber, Lukas, Bartmann, Christoph, Hochreiter, Sepp, Lehner, Sebastian
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

A Diffusion Model Framework for Unsupervised Neural Combinatorial Optimization
by: Sanokowski, Sebastian, et al.
Published: (2024)

Scalable Discrete Diffusion Samplers: Combinatorial Optimization and Statistical Physics
by: Sanokowski, Sebastian, et al.
Published: (2025)

Diffusion-Augmented Markov Decision Processes for Maximum Entropy Reinforcement Learning
by: Sanokowski, Sebastian, et al.
Published: (2025)

Addressing Pitfalls in the Evaluation of Uncertainty Estimation Methods for Natural Language Generation
by: Ielanskyi, Mykyta, et al.
Published: (2025)

On Information-Theoretic Measures of Predictive Uncertainty
by: Schweighofer, Kajetan, et al.
Published: (2024)

Improving Uncertainty Estimation through Semantically Diverse Language Generation
by: Aichberger, Lukas, et al.
Published: (2024)

FlashRNN: I/O-Aware Optimization of Traditional RNNs on modern hardware
by: Pöppel, Korbinian, et al.
Published: (2024)

Overcoming Saturation in Density Ratio Estimation by Iterated Regularization
by: Gruber, Lukas, et al.
Published: (2024)

MIM-Refiner: A Contrastive Learning Boost from Intermediate Pre-Trained Representations
by: Alkin, Benedikt, et al.
Published: (2024)

Tiled Flash Linear Attention: More Efficient Linear RNN and xLSTM Kernels
by: Beck, Maximilian, et al.
Published: (2025)

Contrastive Abstraction for Reinforcement Learning
by: Patil, Vihang, et al.
Published: (2024)

xLSTM Scaling Laws: Competitive Performance with Linear Time-Complexity
by: Beck, Maximilian, et al.
Published: (2025)

Safe and Certifiable AI Systems: Concepts, Challenges, and Lessons Learned
by: Schweighofer, Kajetan, et al.
Published: (2025)

The Disparate Benefits of Deep Ensembles
by: Schweighofer, Kajetan, et al.
Published: (2024)

Geometry-Informed Neural Networks
by: Berzins, Arturs, et al.
Published: (2024)

Rethinking Uncertainty Estimation in LLMs: A Principled Single-Sequence Measure
by: Aichberger, Lukas, et al.
Published: (2024)

Proximal Diffusion Neural Sampler
by: Guo, Wei, et al.
Published: (2025)

Continuously Tempered Diffusion Samplers
by: Erives, Ezra, et al.
Published: (2025)

Parameter Efficient Fine-tuning via Explained Variance Adaptation
by: Paischer, Fabian, et al.
Published: (2024)

Plasticity Loss in Deep Reinforcement Learning: A Survey
by: Klein, Timo, et al.
Published: (2024)

Retrieval-Augmented Decision Transformer: External Memory for In-context RL
by: Schmied, Thomas, et al.
Published: (2024)

PERP: Rethinking the Prune-Retrain Paradigm in the Era of LLMs
by: Zimmer, Max, et al.
Published: (2023)

Unlocking the Working Memory of Large Language Models for Latent Reasoning
by: Aichberger, Lukas, et al.
Published: (2026)

xLSTM 7B: A Recurrent LLM for Fast and Efficient Inference
by: Beck, Maximilian, et al.
Published: (2025)

VN-EGNN: E(3)-Equivariant Graph Neural Networks with Virtual Nodes Enhance Protein Binding Site Identification
by: Sestak, Florian, et al.
Published: (2024)

On the Collapse Errors Induced by the Deterministic Sampler for Diffusion Models
by: Zhang, Yi, et al.
Published: (2025)

Diffusion Models as Constrained Samplers for Optimization with Unknown Constraints
by: Kong, Lingkai, et al.
Published: (2024)

End-To-End Learning of Gaussian Mixture Priors for Diffusion Sampler
by: Blessing, Denis, et al.
Published: (2025)

MolecularIQ: Characterizing Chemical Reasoning Capabilities Through Symbolic Verification on Molecular Graphs
by: Bartmann, Christoph, et al.
Published: (2026)

Swift Sampler: Efficient Learning of Sampler by 10 Parameters
by: Yao, Jiawei, et al.
Published: (2024)

Vision-LSTM: xLSTM as Generic Vision Backbone
by: Alkin, Benedikt, et al.
Published: (2024)

Adjoint Sampling: Highly Scalable Diffusion Samplers via Adjoint Matching
by: Havens, Aaron, et al.
Published: (2025)

Self-Refining Diffusion Samplers: Enabling Parallelization via Parareal Iterations
by: Selvam, Nikil Roashan, et al.
Published: (2024)

A Large Recurrent Action Model: xLSTM enables Fast Inference for Robotics Tasks
by: Schmied, Thomas, et al.
Published: (2024)

xLSTM: Extended Long Short-Term Memory
by: Beck, Maximilian, et al.
Published: (2024)

Rethinking the Design Space of Reinforcement Learning for Diffusion Models: On the Importance of Likelihood Estimation Beyond Loss Design
by: Choi, Jaemoo, et al.
Published: (2026)

VL Norm: Rethink Loss Aggregation in RLVR
by: He, Zhiyuan, et al.
Published: (2025)

Understanding Sampler Stochasticity in Training Diffusion Models for RLHF
by: Sheng, Jiayuan, et al.
Published: (2025)

SymbolicAI: A framework for logic-based approaches combining generative models and solvers
by: Dinu, Marius-Constantin, et al.
Published: (2024)

Large Language Models Can Self-Improve At Web Agent Tasks
by: Patel, Ajay, et al.
Published: (2024)