Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,695 papers · 148 categories

Trend · papers per month

316292123 · May 202619922001200920172026
48 results for 3D diffusion

DreamFusion uses text-to-image diffusion models to create 3D images efficiently.

problem Lack of large-scale 3D datasets and efficient architectures for 3D synthesis.
method Adapting a 2D diffusion model to 3D synthesis using a loss based on probability density distillation.
result A 3D model can be optimized from a 2D diffusion model, allowing for text-to-3D synthesis.

GCDM generates valid large 3D molecules and optimizes existing molecules.

problem Lack of geometric properties in 3D molecule generation models.
method Introduces Geometry-Complete Diffusion Model (GCDM) using equivariant GNNs.
result Significantly outperforms existing models in 3D molecule generation and optimization.

LION generates high-quality 3D shapes using hierarchical latent diffusion models.

problem Creating high-quality 3D shapes for digital artists.
method Hierarchical Latent Point Diffusion Model (LION) with a global shape latent and point-structured latent space.
result LION achieves state-of-the-art generation performance on ShapeNet benchmarks.

CARV reduces compute cost for downstream pipelines using diffusion models.

problem High variance in Monte Carlo estimators from diffusion models limits compute efficiency.
method CARV uses hierarchical MC estimation with amortized upstream computation and stratified-inverse-CDF.
result CARV delivers 2-3x effective compute multipliers without changing the objective.

VecMol generates 3D molecules as continuous vector fields, overcoming modality and geometry constraints.

problem Challenges in generating 3D molecules, especially in drug discovery and materials science.
method VecMol reimagines molecular representation by modeling 3D molecules as continuous vector fields over Euclidean space, parameterized by a neural field and generated using a latent diffusion model.
result Vector-field-based representations show promise for 3D molecular generation, validated on benchmarks.

ED-NeRF efficiently edits 3D scenes using latent space NeRF and improved loss functions.

problem Slow training speeds and inadequate editing loss functions in existing NeRF editing techniques.
method Embedding real-world scenes into latent space of LDM, using a unique refinement layer and an improved loss function.
result ED-NeRF achieves faster editing speed and improved output quality compared to state-of-the-art models.

DreamPropeller accelerates text-to-3D generation by 4.7x with minimal loss in quality.

problem Long generation times in text-to-3D generation algorithms degrade user experience.
method DreamPropeller uses Picard iterations generalized for non-ODE paths to accelerate parallel sampling.
result Empirically achieves up to 4.7x speedup with negligible quality loss.

RADAR uses diffusion models to detect anomalies without reconstruction, improving accuracy and efficiency.

problem Challenges in anomaly detection and segmentation, especially in real-time applications.
method RADAR uses attention-based diffusion models to directly produce anomaly maps from the diffusion process, bypassing reconstruction.
result RADAR improves F1 score by 7% on MVTec-AD and 13% on 3D-printed material compared to state-of-the-art methods.

AbDiffuser generates full-atom antibodies with sequence and structure fidelity.

problem Generating high-fidelity antibodies with both structure and sequence information.
method Equivariant and physics-informed diffusion model with novel protein structure representation.
result AbDiffuser generates antibodies with sequence and structural properties matching a reference set.

Generates garden paintings from text descriptions using deep learning.

problem Lack of firsthand material for traditional Chinese garden reconstruction.
method Deep learning model trained on text and paintings of Ming Dynasty gardens.
result Model generates garden paintings in Ming Dynasty style based on textual descriptions.

Method optimizes diffusion model generation to meet user preferences.

problem Optimizing diffusion model generation with only black-box target scores.
method Covariance-adaptive sequential optimization algorithm for black-box optimization.
result Proves superior performance in achieving better target scores.

A new diffusion model generates novel protein backbones without relying on pretrained networks.

problem Generating novel protein backbones without relying on pretrained networks.
method Developed a SE(3) invariant diffusion model on multiple frames, called FrameDiff.
result Generated designable protein monomers up to 500 amino acids without pretrained networks.

A 3D almost-Riemannian manifold is a generalized Riemannian manifold defined locally by 3 vector fields that play the role of an orthonormal frame, but could become collinear on some set $\Zz$ called the singular set. Under the Hormander condition, a 3D almost-Riemannian structure still has a metric space structure, wh…

2014-07-02abs ↗pdf ↗

Data assimilation for subsurface flow using latent diffusion models shows that ensemble Kalman methods may overestimate posterior uncertainty, while Monte Carlo sampling is more reliable.

problem Data assimilation for subsurface flow
method Ensemble Kalman smoother and Markov chain Monte Carlo sampling
result Monte Carlo sampling is more reliable than ensemble Kalman methods

A new diffusion sampling method combines Krylov subspace and diffusion models for faster and more efficient inverse problems.

problem Efficiently solving large-scale inverse problems in high-performance computing.
method Proposes a novel diffusion sampling strategy that integrates Krylov subspace methods with diffusion models.
result Demonstrates significant speedup (80x faster inference time) and improved reconstruction quality on real-world medical imaging problems.

Diffuse optical tomography (DOT) has been investigated as an alternative imaging modality for breast cancer detection thanks to its excellent contrast to hemoglobin oxidization level. However, due to the complicated non-linear photon scattering physics and ill-posedness, the conventional reconstruction algorithms are s…

2017-12-04abs ↗pdf ↗

DDMI generates high-quality INRs by adapting positional embeddings.

problem Existing INR generative models fail to produce high-quality representations.
method DDMI uses adaptive positional embeddings and a D2C-VAE to enhance expressive power.
result DDMI outperforms existing models across multiple modalities and datasets.

We study knots in 3d Chern-Simons theory with complex gauge group SL(N,C)SL(N,\mathbb{C}), in the context of its relation with 3d N=2\mathcal{N}=2 theory (the so-called 3d-3d correspondence). The defect has either co-dimension 2 or co-dimension 4 inside the 6d (2,0)(2,0) theory, which is compactified on a 3-manifold M^\hat{M}. …

2015-10-13abs ↗pdf ↗

New method uses PINNs to solve complex PDEs with sparse measurements.

problem Joint estimation of source and parameters in advection-diffusion equations with limited data.
method Weighted adaptive approach based on neural tangent kernel of PINNs.
result Successful estimation of source function, velocity, and diffusion parameters.

Study of 3d-3d correspondence involving qq-Weyl algebra and 3d-index.

problem Understanding the action of a qq-Weyl algebra on the 3d-index of knots.
method Investigation of the qq-Weyl algebra's module action on the 3d-index, conjecturing structural properties.
result Bilinear factorization, pair of linear qq-difference equations, and rational function matrix for the 3d-index determination.

Paper proposes Sinkformers for Transformers with doubly stochastic attention.

problem Improving Transformer models' accuracy in vision and natural language processing.
method Using Sinkhorn's algorithm to make attention matrices doubly stochastic instead of SoftMax normalization.
result Sinkformers enhance model accuracy in vision and natural language processing tasks.

Autonomous driving requires 3D perception of vehicles and other objects in the in environment. Much of the current methods support 2D vehicle detection. This paper proposes a flexible pipeline to adopt any 2D detection network and fuse it with a 3D point cloud to generate 3D information with minimum changes of the 2D d…

2018-02-12abs ↗pdf ↗

The study connects knot complements to 3d theories via half-index calculations.

problem Understanding the relationship between knot complements and 3d theories.
method Using half-index calculations and inverted Habiro series, the study realizes knot complements as homological blocks.
result The colored Jones polynomial is derived from choosing specific poles in the half-index integral expression.