NeurIPS 2025 Past Generative models
NeurIPS 2025 Workshop on Structured Probabilistic Inference & Generative Modeling
SPIGM @ NeurIPS
- Submission deadline
- Aug 31, 2025, 23:59 UTC imported from OpenReview — check the website for extensions
- Submission portal
- OpenReview
- Notes
- Auto-imported from the OpenReview venue record on 2026-06-10 — please verify and enrich (topics are keyword-guessed).
Accepted papers (115)
Fetched from OpenReview (v2) on 2026-06-10.
-
3-Model Speculative Decoding
-
A Connection Between Score Matching and Local Intrinsic Dimension
-
A Multi-Method Interpretability Framework for Probing Cognitive Processing in Deep Neural Networks across Vision and Biomedical Domains
-
A Probabilistic Approach to Pose Synchronization for Multi-Reference Alignment with applications to wireless communication systems
-
A Theory of Multi-Agent Generative Flow Networks
-
Accelerating Diffusion Models in Offline RL via Reward-Aware Consistency Trajectory Distillation
-
Adaptive Frontier Exploration on Graphs with Applications to Network-Based Disease Testing
-
Ambient Diffusion Omni
-
An Information-Theoretic Discrete Poisson Diffusion Framework
-
An Optimal Algorithm for Marginalization in Bayesian Networks
-
Any-Order Flexible Length Masked Diffusion
-
Are We Really Learning the Score Function? Reinterpreting Diffusion Models Through Wasserstein Gradient Flow Matching
-
Bayes-PD: Exploring a Sequence to Binding Bayesian Neural Network model trained on Phage Display data
-
Beyond Linear Diffusions: Improved Representations for Rare Conditional Generative Modeling
-
BioBO: Biology-informed Bayesian Optimization for Perturbation Design
-
Blind Inverse Problem Solving Made Easy by Text-to-Image Latent Diffusion
-
BP-Seg: A graphical model approach to unsupervised and non-contiguous text segmentation using belief propagation
-
Can We Estimate The Entropy Of Arbitrary Distributions Known Up To A Normalization Constant?
-
Constrained Flow Optimization via Sequential Fine-Tuning for Molecular Design
-
Continuous-Token Diffusion for Speaker-Referenced TTS in Multimodal LLMs
-
Contrastive MIM: A Contrastive Mutual Information Framework for Unified Generative and Discriminative Representation Learning
-
CoVAE: Consistency Training of Variational Autoencoders
-
Cross-Lingual Multimodal Retrieval-Augmented Generation for Open Question Answering in Tamil and Yoruba
-
DDS-E-Sim: A Transformer-based Probabilistic Generative Framework for Simulating Error-Prone DNA Sequences for DNA Data Storage
-
DenseMixer: Improving MoE Post-Training with Precise Router Gradient
-
Diffusion Beats Autoregressive in Data-Constrained Settings
-
Divergence Minimization Preference Optimization for Diffusion Model Alignment
-
Effective Diffusion-free Score Matching for Exact Conditional Sampling
-
Efficient Flow Matching using Latent Variables
-
Enhancing Diffusion Model Guidance through Calibration and Regularization
-
Entangled Schrödinger Bridge Matching
-
Entropy Is Not Enough: Uncertainty Quantification for LLMs fails under Aleatoric Uncertainty
-
Entropy-Guided Sampling of Flat Modes in Discrete Spaces
-
Failure Prediction Is a Better Performance Proxy for Early-Exit Networks Than Calibration
-
FlowBack-Adjoint: Energy-Guided Conditional Flow-Matching for Protein Side-Chain Generation
-
Foundations of Top-$k$ Decoding for Language Models
-
From Entropy Rate to Redundancy: Information Dynamics in Large Language Models
-
Generalization of Diffusion Models Arises from a Regularized Representation Space
-
Generative Actor-Critic
-
GenUQ: Predictive Uncertainty Estimates via Generative Hyper-Networks
-
GFlowNets for Learning Better Drug-Drug Interaction Representations
-
Global Resolution: Optimal Multi-Draft Speculative Sampling via Convex Minimization
-
GNN-Guided Block Selection in Gibbs MCMC
-
Graph Random Features for Scalable Gaussian Processes
-
Hold That Exit: Near Optimal Early-Exit Inference via Recall
-
IAGA: Identity-Aware Gaussian Approximation for Efficient 3D Molecular Generation
-
ImmUQBench: A Benchmark on Uncertainty Quantification of Protein Immunogenicity Prediction
-
Improved Sampling from Masked Diffusion Models with Position Contrastive Guidance
-
Improving Generation Quality of Long-Tailed Diffusion via Disentangled Latent Representations
-
Improving Iterative Gaussian Processes via Warm Starting Sequential Posteriors
-
Inception Inference: Nested Probabilistic Reasoning over Story Graphs from Text
-
Inference and Generating Method for Extremely Sparse Networks
-
Inference-time Scaling of Diffusion Models through Classical Search
-
Information-Guided Diffusion Sampling for Dataset Distillation
-
Insertion Language Models: Sequence Generation with Arbitrary-Position Insertions
-
Is Sequence Information All You Need for Bayesian Optimization of Antibodies?
-
ISUM: Inverse Problem Solver via Unbalanced Optimal Transport Map
-
Learning Boltzmann Generators via Constrained Mass Transport
-
Learning to Iteratively Improve 3D Representation with 2D Generative Models
-
Learning Velocity Prior-Guided Hamiltonian-Jacobi Flows with Unbalanced Optimal Transport
-
Leveraging Probabilistic Modeling for Robust End-to-End Autonomous Driving across Domains
-
MMG: Mutual Information Estimation via the MMSE Gap in Diffusion
-
moPPIt-v3: Motif-Specific Peptides Generated via Multi-Objective-Guided Discrete Flow Matching
-
Multi-Objective Nanobody Design via Masked Discrete Diffusion with Simplex Refinement
-
Multi-scale Autoregressive Models are Laplacian, Discrete, and Latent Diffusion Models In Disguise
-
Multimodal Bayesian Network for Robust Assessment of Casualties in Autonomous Triage
-
Myosotis: structured computation for attention like layer
-
Neural Universal Scene Descriptors
-
On Fitting Flow Models with Large Sinkhorn Couplings
-
oPE: Enhanced Transformer with Complex Positional Encoding
-
Personalized English Amharic Medical Image Caption and Speech Generation for Visually Impaired Patients Using Vision Transformer Fused with LLM
-
PolUQBench: A Benchmark Study on Uncertainty Quantification of Polymer Property Prediction
-
Posterior Inference in Latent Space for Scalable Constrained Black-box Optimization
-
Probabilistic Image Generation with LLM Priors via Structured Rectified Flow
-
Probabilistic Soundness Guarantees in LLM Reasoning Chains
-
Probabilistic Variational Contrastive Learning
-
Random Projection Flows for Efficient Manifold Density Estimation
-
Reconsidering Noise for Denoising Diffusion Probabilistic Models
-
Rethinking Direct Preference Optimization in Diffusion Models
-
Robust Transfer for Bayesian Optimization with Prior-Data Fitted Networks
-
Scaffold Diffusion: Sparse Multi-Category Voxel Structure Generation with Discrete Diffusion
-
Scalable Bayesian Monte Carlo: fast uncertainty estimation beyond deep ensembles
-
ScooBDoob: Schrödinger Bridge with Doob’s h-Transform for Molecular Dynamics
-
Score-based Idempotent Distillation of Diffusion Models
-
Score-informed Neural Operator for Enhancing Ordering-based Causal Discovery
-
Selective Underfitting in Diffusion Models
-
Self-Speculative Decoding in Any-Order and Any-Subset Autoregressive Models
-
Semantic Probabilistic Control of Language Models
-
Semantic Volume: Quantifying and Detecting both External and Internal Uncertainty in LLMs
-
Shaping Inductive Bias in Diffusion Models through Frequency-Based Noise Control
-
SLayR: Scene Layout Generation with Rectified Flow
-
Slithering through Gaps: Capturing Discrete Isolated Modes via Logistic Bridging
-
SpecAttn - Speculating Sparse Attention
-
SpectFlow: Long-term forecasting using flow matching with 89k parameters
-
State-Space Architectures for Scalable Diffusion-based 3D Molecule Generation
-
STED and Consistency Scoring: A Framework for Evaluating LLM Structured Output Reliability
-
Steering Pretrained Drafters during Speculative Decoding
-
Temporal Alignment Guidance: On-manifold Sampling in Diffusion Models
-
The Unwinnable Arms Race of AI Image Detection
-
Token-Level Guided Discrete Diffusion for Membrane Protein Design
-
Tokenized Neural Fields: Structured Representations of Continuous Signals
-
Towards Practical Multi-label Causal Discovery in High-Dimensional Event Sequences via One-Shot Graph Aggregation
-
Transformers as Unrolled Inference in Probabilistic Laplacian Eigenmaps
-
Trust Region Constrained Measure Transport in Path Space for Stochastic Optimal Control and Inference
-
TwinTURBO: Semi-Supervised Fine-Tuning of Foundation Models via Mutual Information Decompositions for Downstream Task and Latent Spaces
-
Using maximal information auxiliary variables to improve synthetic data generation based on TabPFN foundation models: preliminary results
-
Value Gradient Guidance for Flow Matching Alignment
-
Value Matching: Scalable and Gradient-Free Reward-Guided Flow Adaptation
-
VarDiU: A Variational Diffusive Upper Bound for One-Step Diffusion Distillation
-
Variational Deep Learning via Implicit Regularization
-
Weighted Conditional Flow Matching
-
When Do LLMs Improve Bayesian Optimization? A Systematic Comparison Across Molecular and Protein Design
-
When rule learning breaks: Diffusion Fails to Learn Parity of Many Bits
-
Where the Score Lives: A Wavelet View of Diffusion
-
Zero-Variance Gradients for Variational Autoencoders