ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:

~ similar to 2606.13240· 20 results

cs.CVcs.AIcs.LGRecentMay 30, 2026

DASH: Dual-Branch Score Distillation for Guidance-Calibrated Compact Diffusion Models

Abdullah Al Shafi, Kazi Saeed Alam, Sk Imran Hossain, Engelbert Mephu Nguifo

DASH introduces a dual-branch distillation framework to effectively compress class-conditional diffusion models by independently supervising both score branches, significantly preserving guidance fide…

View →
cs.AIcs.LGRecentMay 29, 2026

From Noise to Control: Parameterized Diffusion Policies

Renhao Zhang, Haotian Fu, Mingxi Jia, George Konidaris +2 more

The Parameterized Diffusion Policy (PDP) framework transforms diffusion models from general stochastic generators into precise, steerable tools for learning and adapting complex robotic behaviors by e…

View →
cs.LGcs.AIEmpiricalRecentJun 16, 2026

Kolmogorov Regression for Robust Diffusion Policies

Lekan Molu

This paper introduces a novel method to improve the performance of finite-dimensional diffusion policies by lifting them to a Cameron-Martin space and using a backward Kolmogorov equation.

View →
cs.LGcs.ITstat.MLTheoreticalRecentJul 24, 2026

From Score Approximation to Distribution Approximation in Score-Based Diffusion Models

Lan V. Truong

This paper establishes a connection between neural network approximation of score functions and approximation of probability distributions generated by reverse diffusion models.

View →
cs.LGcs.AIcs.CVEmpiricalRecentJul 8, 2026

Selective Timestep Weighting and Advantage-Based Replay for Sample-Efficient Diffusion RLHF

Eric Zhu, Abhinav Shrivastava, Soumik Mukhopadhyay

This paper proposes two strategies to improve feedback efficiency of reinforcement learning from human feedback (RLHF) in diffusion models.

View →
stat.MLcs.LGmath.STTheoreticalRecentJun 22, 2026

Diffusion Models Adapt to Low-Dimensional Structure Under Flexible Coefficient Choices

Changxiao Cai, Yuchen Jiao, Gen Li

The paper proves that diffusion models adapt to low-dimensional structure robustly across various update coefficient choices.

View →
cs.CVcs.AIcs.LGEmpiricalRecentJul 27, 2026

Rethinking Classifier-Free Guidance in On-Policy Diffusion Distillation

Bingnan Li, Haozhe Wang, Haozhong Xiong, Fangtai Wu +4 more

This paper introduces Positive--Direction Matching (PDM), a branch-aware on-policy distillation objective to address Negative Branch Asymmetry (NBA) in diffusion models under classifier-free guidance.

View →
cs.LGEmpiricalRecentSep 18, 2026

$λ$-Controlled GRPO: Turning Flow-Matching Ratio Instability into a Budgeted Resource

Yufeng Wang, Parivesh Priye, Meeshawn Marathe, Ramit Pahwa

This paper proposes a method to stabilize training of flow-matching models in reinforcement learning by calibrating importance-ratio behavior based on the predicted path variance.

View →
cs.LGcs.AIRecentMay 27, 2026

ProRL: Effective Reinforcement Learning for Proactive Recommendation via Rectified Policy Gradient Estimation

Hongru Hou, Tiehua Mei, Denghui Geng, Jinhui Huang +4 more

The paper proposes ProRL, an effective Reinforcement Learning framework that rectifies gradient estimation deficiencies to optimize proactive recommendation paths, significantly outperforming existing…

View →
stat.MLcs.LGmath.OCTheoreticalRecentJul 20, 2026

An Adjoint-Sensitivity Framework for Lost-in-the-Middle Phenomena in Causal Residual Transformers

Cheng Huan, Hongwei Yuan

This paper develops an adjoint-sensitivity framework for positional influence in causal residual Transformers and provides theoretical results on the residual-to-depth-flow estimate and finite-token-t…

View →
cs.ROcs.AIcs.LGEmpiricalRecentOct 14, 2026

Modeling and Understanding Neural Weights of Humanoid Policies with Diffusion

Huixuan Cheng, Bike Zhang, Shankar Sastry, Koushil Sreenath

This paper explores generative modeling of humanoid control networks through their weights, enabling the creation of deployable networks for various motions.

View →
stat.MLcs.LGEmpiricalRecentJun 20, 2026

Variance-Tilted Diffusion Models for Diverse Sampling

Iskander Azangulov, Leo Zhang, Kianoosh Ashouritaklimi

This paper introduces a variance-weighted batch distribution to improve the diversity of samples in diffusion models.

View →
cs.LGcs.DSmath.NATheoreticalRecentJun 26, 2026

VGB for Masked Diffusion Model: Efficient Test-time Scaling for Reward Satisfaction and Sample Editing

Kijung Jeon, Thuy-Duong Vuong, Molei Tao

The paper introduces MDM-VGB, a reward-guided sampler for Masked Diffusion Models, which extends the Jerrum-Sinclair backtracking Markov chain to a masked-state graph for effective high-reward generat…

View →
eess.AScs.AIcs.LGEmpiricalRecentJun 18, 2026

Repurposing a Speech Classifier for Guided Diffusion-Based Speech Generation

Rostislav Makarov, Timo Gerkmann

The paper repurposes a pre-trained speech classifier as the backbone for diffusion generation, reducing the need for two separately trained models.

View →
cs.LGcs.AImath.OCRecentMay 29, 2026

Unlearning in Diffusion Models: A Unified Framework with KL Divergence and Likelihood Constraints

Shervin Khalafi, Alejandro Ribeiro, Dongsheng Ding

The paper proposes a unified, constrained optimization framework using KL divergence and likelihood constraints to achieve effective and principled unlearning in diffusion models.

View →
cs.LGstat.MLEmpiricalRecentAug 3, 2026

Pseudorandom Streams within Diffusion Models Act as Learnable Inputs That Affect Generation Quality

Shengzhi Deng, Chenqi Ye, Yanze Guo

This paper investigates the effect of pseudorandom number generator orbits on diffusion models' training and generation, revealing learnable input and significant impact on loss and quality.

View →
cs.ROcs.AIEmpiricalRecentJun 9, 2026

Diffusion Forcing Planner: History-Annealed Planning with Time-Dependent Guidance for Autonomous Driving

Zehan Zhang, Neng Zhang, Yaoyi Li, Jia Cai +1 more

The paper proposes a diffusion-based planning framework called Diffusion Forcing Planner (DFP) to stabilize motion plans in autonomous driving.

View →