Diffusion models

Timeline

1. Oct 8, 2026 · Research paper · 2 sources
   LEGO: A Lifting-Free Approach for Exocentric-to-Egocentric Video Generation
   Generating an egocentric video from a single exocentric recording is a challenging case of novel view synthesis, as the two cameras share little overlap and much of the target view is unobserved.
2. Oct 8, 2026 · Research paper · 1 source
   Control-Ready Uncertainty for Trajectory Diffusion
   We introduce Score-Curvature for Online Precision Estimation (SCOPE), a lightweight module that augments diffusion trajectory models with control-ready uncertainty.
3. Oct 8, 2026 · Research paper · 1 source
   Ambient Discrete Diffusion: Using the Wrong Data at the Right Time for Data Efficient Learning
   We introduce RefineMix, a framework for training discrete diffusion models under severe data scarcity, a common constraint in scientific applications.
4. Oct 8, 2026 · Research paper · 1 source
   Just Weather Scoring: Efficient End-to-end Nowcasting with Distributional Diffusion
   We introduce Just Weather Scoring (JWS), a single-stage, end-to-end diffusion model which addresses both issues by forecasting directly in radar space and enabling few-step generation.
5. Oct 8, 2026 · Open-source release · 1 source
   unslothai/unsloth v0.1.905-beta: Sandboxing is here!
   We're introducing Windows, Mac and Linux sandboxing in Unsloth!
6. Oct 8, 2026 · Research paper · 1 source
   Diffusion Removes Langevin's Conditioning Dependence: A Sharp Gaussian Analysis
   Despite their empirical success, why diffusion models overcome the bottlenecks of classical score-based samplers remains unclear.
7. Oct 8, 2026 · Research paper · 1 source
   REACT: Rolling Denoising and Dual Decoupling for Reactive Robot Control with VLA Models
   Flow-based vision-language-action (VLA) models generate action chunks for temporally coherent robot motion, but chunked control creates a fundamental closed-loop trade-off: long chunks provide smooth execution, whereas frequent replanning improves reactivity at the cost of action discontinuities.
8. Oct 8, 2026 · Research paper · 1 source
   Streaming-Aware Diffusion for Real-Time Video Super-Resolution via Cross-Step Attention
   We propose a streaming-aware framework that adapts pretrained single-image latent diffusion models for efficient video super-resolution (VSR) by exploiting the sequential structure of video streams.
9. Oct 8, 2026 · Research paper · 1 source
   HI3D 3.0 (Twinkle3D): Object-specific 3D Asset Generation with High Resolution
   We present Hi3D 3.0, an image-to-3D generation system targeting object-specific fidelity, with Twinkle3D as its geometry model for generating watertight triangle meshes at $2048^{3}$ resolution.
10. Oct 8, 2026 · Research paper · 1 source
    Early Signatures of Memorization in Diffusion Models via Basin Geometry and Cyclic Denoising
    We show that memorization is encoded in the geometry of the learned energy landscape before it appears in generated samples, a state we call latent memorization.
11. Oct 8, 2026 · Research paper · 1 source
    Stop My Dancing! Understanding, Detecting and Attributing Motion-Aware Deepfake Videos
    Pose-guided diffusion models can now synthesize entire human figures in motion, spawning a new class of deepfakes: Motion Aware Deepfake (MAD) that have already reached hundreds of millions of viewers.
12. Oct 8, 2026 · Research paper · 1 source
    Conditional Residual Prediction: Improving Autoregressive Video Diffusion without a Bidirectional Teacher
    Causal video diffusion models generate video autoregressively, which suits streaming, interactive, and long-video generation.
13. Oct 8, 2026 · Research paper · 1 source
    WAM-Cache: Staleness-Bounded KV Reuse for Efficient World Action Models
    World Action Models (WAMs) enable generalist robot manipulation by conditioning an action expert on representations from a pretrained video Diffusion Transformer (DiT).
14. Oct 8, 2026 · Research paper · 1 source
    Equal Path Cost, Unequal Output Effects: Understanding Perturbation Propagation in Diffusion Models
    To address this question, we develop a theoretical framework to investigate perturbation propagation, combining dynamical analysis of the sampling process with an information-theoretic characterization of output responses.
15. Oct 8, 2026 · Research paper · 1 source
    CRISP: Fixing Flying Pixels in Latent LiDAR Generation via Diffusion Decoding
    Latent LiDAR pipelines suffer from flying pixels: convolutional VAEs blur sharp radial depth discontinuities, yielding edge depths that back-project to points floating between surfaces.
16. Oct 8, 2026 · Research paper · 1 source
    Bernoulli Flow Models: Self-Consistent Generative Modeling for Binary Data
    To address this fundamental limitation and decouple the generative dynamics from fixed discrete time steps, we propose Bernoulli Flow Models (BFM).
17. Oct 8, 2026 · Research paper · 1 source
    Sample-Efficient Generative Conformal Prediction
    Generative conformal prediction builds uncertainty sets from samples of a conditional generator, which are efficient only when the samples represent the response distribution well.
18. Oct 8, 2026 · Research paper · 1 source
    Memorization and Malign Generalization in Conditional Diffusion Models with Random Features
    Conditional diffusion models generate diverse, novel, and high-quality samples under prescribed conditions.
19. Oct 8, 2026 · Research paper · 1 source
    DynaTE: Accelerating Diffusion LLMs via Dynamic Token Execution
    Diffusion-based LLMs (dLLMs) have recently emerged as a promising alternative to autoregressive (AR) LLMs by enabling bidirectional parallel refinement, alleviating the sequential decoding bottleneck of AR generation.
20. Oct 8, 2026 · Research paper · 1 source
    Attributing HOW, Not Just WHICH: Counterfactual Response Trajectories for Diffusion Models
    Diffusion models have achieved remarkable success in image generation, yet tracing their outputs to individual training examples remains challenging.
21. Oct 8, 2026 · Research paper · 2 sources
    The Lattice of Transition Laws
    Diffusion and autoregression (AR) have long been seen as different categories of generative models, with diffusion specialising in continuous fields and AR specialising in discrete tokens.
22. Oct 8, 2026 · Research paper · 1 source
    No Distillation Needed: Single-Pass Real-Time Talking Heads via Acausal Noise Shaping
    Audio-driven facial animation underpins real-time avatars, telepresence, and embodied virtual agents.
23. Oct 8, 2026 · Research paper · 1 source
    Diffusion Meta-Prompting and Steering for Generalizable Foundation Model Adaptation
    In this paper, we introduce a Diffusion Meta-Prompt (DMP) model , a framework that models the distribution of learned prompts using diffusion models.
24. Oct 8, 2026 · Research paper · 1 source
    Transforming Image Editors into Video Editors
    In this paper, we present a simple alternative to end-to-end video editing: instead of training a monolithic video editor, we transform a strong image editor into a video editor through anchor-based generation.
25. Oct 7, 2026 · Research paper · 1 source
    Enabling Preference-driven Unlearning in Few-step Distilled Text-to-Image Diffusion Models
    Text-to-image diffusion models are increasingly distilled into few-step variants and being deployed to enable fast inference.
26. Oct 7, 2026 · Research paper · 1 source
    GRACE: Generation-aware latent compression for efficient video generation
    To address this, we propose Generation-Aware Latent Compression for Efficient Video Generation (GRACE), a two-stage framework that compresses a pretrained video autoencoder while keeping it compatible with the pretrained DiT.
27. Oct 7, 2026 · Research paper · 1 source
    Koopman Observers for Diffusion Acceleration: Correcting Feature Forecasts with Shallow Measurements
    We introduce an observation-corrected Koopman framework for accelerating frozen diffusion models.
28. Oct 7, 2026 · Research paper · 1 source
    Real-Time Joint Audio-Video Generation by Parallel Adapter Composition
    Deploying a joint audio-video diffusion transformer for real-time, interactive generation normally requires two essential modifications: block-autoregressive attention, so frames can be emitted before the whole clip is finished, and few-step sampling, so each block is cheap.
29. Oct 7, 2026 · Research paper · 1 source
    Position Forcing: Self-Conditioning 3D Generation
    Recent single-stage 3D generative models commonly adopt VecSet representations, encoding 3D shapes as unordered sets of latent tokens.
30. Oct 7, 2026 · Research paper · 1 source
    OrthoGen: A Generative Orthogonal Learner for Time-Varying Treatments
    Estimating conditional distributional potential outcomes (CDPOs) over time is important in medicine (e.g., to estimate patient-specific risks under different treatment sequences).

Often appears with