UGG unifies video generation and 4D geometric prediction
One model treats RGB, depth, and camera pose as conditional completion and can search scene hypotheses at inference.
Stories per day · 30 days
6 RSS
Relatedflow-matching4diffusion-models34d-reconstruction2benchmark2sampling2transformers2video-diffusion23d-assets14d-scenes1attestability1audio1audio-codecs1bayes-risk1camera-control1camera-pose1cancer-research1cifar-1001classifier-guidance1
85 stories, newest first · one card per story
Stories tagged #generative-models
Creative Priming separates the creative process from the response
A GRPO-trained priming model writes prompt-specific primers so a response model yields novel, high-quality, diverse outputs.
Energy-Tweedie links Gibbs noise denoising to Stein scores
The identity extends the Gaussian posterior-mean relation to kernel scoring rules and user-chosen noise paths.
arXiv presents biology-informed framework for evaluating synthetic ovarian cancer multi-omics datasets
The framework evaluates paired RNA expression and CNV profiles from the DECIDER cohort using variational autoencoders.
Exponential residual flows give an ODE sampler for discrete diffusion
The construction preserves the original diffusion's marginals and is specialized to masked and uniform diffusion.
TACFormer generates full PROTACs conditioned on target protein sequences
A GPT-style decoder uses ESM-2 embeddings of the protein of interest instead of designing only the linker.
Tutorial covers generative models for music audio
It compares codecs, token models, diffusion, and flow matching, and discusses metrics, listening tests, and legal disputes.
Tutorial on Generative Models for Music Audio
This monograph covers neural audio codecs, autoregressive and diffusion models, sampling, and preference optimization for music generation systems.
LociArt proposes GRNStyle for controllable local video stylization
The method is trained on 100K synthetic pairs and evaluated on 80 videos with a regional style metric.
Hierarchical Cooperative GFlowNets coordinate sampler exploration
A shared classifier partitions the search space so lower-ranked models cover regions higher-ranked ones miss.
Trajectory matching trains discrete flows on structured action sequences
Authors report MOSES validity rising from 92.8% to 99.2% versus factorized discrete flow matching, with transfer without retraining.
GLOW-FM enhances low-light images with one latent flow step
The small variant uses a frozen Tiny-VAE and Terminal Velocity Matching at 34 GFLOPs and one function evaluation.
Velocity Ambiguity Profiles split flow-matching loss by interpolation time
Guided time sampling cuts DINOv2 feature velocity loss 6.78% and Fréchet distance 23.6%, with no class-conditional KID gain.
Orbitol generates crystals constrained to requested space groups
On MP-20, 13.8% of attempts stayed stable or metastable, unique, novel, and in the requested group after relaxation.
RealMe builds 2K 4D-consistent volumetric video from sparse captures
A high-resolution video diffusion model refines limited multi-view captures and beats prior methods on DNA-Rendering and RealVV.
KNOX runs generative models in a TEE regulatory sandbox
An attested monitor allows only matching tool and system calls, with authors reporting overhead under 1%.
Benchmark finds emergent market impact in generative LOB models
Five autoregressive generators showed impact exponents of 0.63 to 1.21 on five NASDAQ stocks, above the square-root law.
Swift trains stronger diffusion models with a frozen weak denoiser
On one ImageNet-256 setup it beat the baseline's best FID with about half the training compute, including guide overhead.
Holo4D steers video diffusion with reconstructed 4D trajectories
Projected source-view trajectories condition a pretrained video model so unseen regions are filled without retraining the generator.
LayerEditor generates reusable RGBA layers during instruction-guided image edits
The method distills a pretrained editing prior into both the canvas and layers composed from LayerEditor-100K.
First-order logic guides graph diffusion toward ontology-valid graphs
Fuzzy, differentiable rule relaxations steer a pre-trained denoiser at inference and raise constraint satisfaction.
Mine, Sample, Render: Test-Time Diversity Alignment Of Generative Models
MSR improves generative-model diversity by sampling corpus-derived attributes and using the model only as a renderer.
Self-Conditioning Enables Deep Sequential Reasoning in Flow Matching
Researchers show self-conditioning lets flow-matching models gain deeper visual reasoning from additional sampling steps.
FLOMSS applies flow matching to four-source music separation
The model separates vocals, bass, drums, and other in full-band stereo and is competitive on MUSDB18-HQ in objective and listening tests.