An autoregressive diffusion model with a hybrid explicit-root/latent-body representation generates real-time, controllable 3D human motion from text and spatial constraints.
hub Mixed citations
Advances in neural information processing systems , volume=
Mixed citation behavior. Most common role is method (50%).
95
Pith papers citing it
Method
50% of classified citations
hub tools
citation-role summary
background 4
method 4
citation-polarity summary
claims ledger
- method Interpolation achieves lower entropy, reflecting a sharper distri- bution critical for precise localization. For more details of this analysis, please refer toApp. F. mtext ∈ {0,1} Ly to isolate the target entity within the prompt Ytgt. Let Itgt denote the set of token indices of the target subject (e.g., "violin"). The mask is defined as: mtext i = ( 1,ifi∈ I tgt 0,otherwise (12) Subsequently, a Spatio-Textual Bias MatrixB is synthesized via the outer product of g=Flatten(G)∈R Lz and the token
- method − 1 2 (x−𝜇) ⊤Σ−1 (x−𝜇) .(1) The covariance is optimized via a factored representation Σ= RSS⊤R⊤ to ensure semi-definiteness. To render the scene, 3D Gaussians are projected into 2D image space. The final color 𝐶 of a pixel is computed by alpha-blending 𝑁 ordered Gaussians overlapping the pixel: 𝐶= 𝑁∑︁ 𝑖=1 𝑐𝑖𝛼𝑖𝐺 2𝐷 𝑖 (x) 𝑖−1Ö 𝑗=1 (1−𝛼 𝑗𝐺 2𝐷 𝑗 (x)),(2) where 𝑐𝑖, 𝛼𝑖, and𝐺 2𝐷 𝑖 (x) denote the color, opacity, and the evaluation of the𝑖-th projected 2D Gaussian at pixel positionx, respectively. 3.2
- method M=⟨S,A,Θ,T,R, γ, P Θ⟩, where S is the state space, A is the action space, and Θ is the space of task-specific latent parameters. For each θ∈Θ , the transition and reward functions are given by Tθ :S × A → P(S) and Rθ :S × A →R , respectively. The parameter θ is sampled from a prior distribution PΘ at the beginning of an episode and remains fixed during the episode. The discount factor is denoted by γ∈[0,1) . This framework defines a family of MDPs indexed by the latent parameter θ, with each θ i
- background decoder D, which takes latent tokens L from the Perceiver Resam- pler and outputs head meshes with consistent topology. Given the shared face connectivity F across all training meshes, the mesh structure naturally defines a graphG. Graph Convolution.For vertex 𝑣𝑖 with feature 𝐹𝑖 and neighbors N (𝑖), our graph convolution is defined as: 𝐹 ′ 𝑖 =𝑊 0𝐹𝑖 + Í 𝑗∈ N (𝑖) 𝑊1𝐹 𝑗,(1) , Vol. 1, No. 1, Article . Publication date: May 2026. 4•Bojun Xiong, Zoubin Bi, Xinghui Peng, Yunmu Wang, Junchen Deng, Jun L
- background dynamics in these directions remain diffusive. Although the effective diffusion coefficientηdk turns out to be very small, the large number of these nearly-flat directions leads to a noticeable divergence of individual trajectories. In the directions with large eigenvaluesηnλi ≫1the system reaches the stationary state given by Πii n ≈ ηdi 2λi −ηλ 2 i −ηΓ ii .(39) The behavior in the other (intermediate) directions is in between these two limiting cases. We also observe empirically that, for dire
- background t (see Section 5); for learned ¯vthe residual remains random but acts as a control variate. 4 Path-Coupled Bellman Flows for Distributional Reinforcement Learning Figure 1.The Architecture of Path-Coupled Bellman Flows (PCBF). Using this control variate, we define the PCBF training target as follows: uλ t := (R+γX ′−X0)+λ h vθ−(t, Zs′ t |s ′, a′)−(X ′ −X 0) i . (13) Setting λ= 0 recovers the baseline BCFM estimator (un- biased, high variance). Nonzero λ introduces a variance- reducing correction
co-cited works
representative citing papers
Set diffusion factorizes likelihood over arbitrary token sets and uses a set-causal diffusion architecture to support KV caching and any-order decoding, yielding improved speed-quality tradeoffs versus prior diffusion LMs.
Proposes diffeomorphic optimization for manifold-constrained problems in generative models via flow maps, with Lie-group extensions for protein design showing metric improvements.
FlexiSLM is the first spoken language model supporting dynamic and controllable frame rates on speech input and output, outperforming fixed-rate 7B models at high quality and enabling faster inference at lower rates like 6.25 Hz.
Panel Flow Matching is a generative method to estimate panel densities from longitudinal data with statistical guarantees under irregular sampling, supporting completion, synthetic data, and classification.
JET is a conditional flow matching framework that generates EEG as continuous raw sequences with added constraints for spectral and temporal properties, achieving over 40% lower TS-FID than prior discrete denoising methods on three benchmarks.
Linear-DPO replaces sigmoid utility with linear utility and adds EMA reference to improve preference alignment in diffusion and flow-matching text-to-image models.
CAdam reinterprets densification in generative 3DGS as signal verification via gradient-moment interference, quantile context, and SNR gating to achieve large reductions in primitive count with comparable quality.
Model collapse occurs in structured interactive learning if and only if the directed interaction graph satisfies a specific topological condition, with finite-sample guarantees for linear regression and asymptotic results for M-estimators.
BrepForge factorizes B-rep synthesis into face-aware autoregressive wireframe composition followed by boundary-conditioned surface instantiation using learning-free geometric priors.
Proposes discretized Matérn process noise for triangulation-agnostic flow matching on meshes with PoissonNet denoiser, tested on elastic states and humanoid poses for meshes exceeding one million triangles.
A multimodal diffusion model generates controllable alternative streetscapes from street-view imagery using visual metrics and text, shown on Chicago and Orlando data with gains in semantic consistency.
Using adjoint equations, the paper derives S-independent IPM convergence bounds for masked and uniform discrete diffusion, controlled by score-matching losses.
VMU-Diff improves precipitation nowcasting via coarse multi-source Vision Mamba fusion followed by residual conditional diffusion refinement.
Introduces the task of counterfactual time series forecasting with textual conditions plus a text-attribution mechanism that improves accuracy by distinguishing mutable from immutable factors.
Discrete diffusion models learn data support before frequencies because the exact reverse process decomposes edits into a dominant validity scale and a finer probability coefficient.
A hypernetwork maps style motion embeddings to LoRA updates that stylize text-driven motion diffusion models with improved generalization to unseen styles via contrastive structuring of the style space.
A generative transfer framework using iterative path-wise tilting integrated with conditional flow matching recovers target entropic optimal transport couplings from reference samples, achieving O(δ) convergence in Wasserstein-1 distance.
RSPO interprets reward advantages as targets for relative log-ratios in dLLMs, calibrating noisy estimates to stabilize RLVR training and achieve strong gains on planning tasks with competitive math reasoning performance.
Polyphonia improves zero-shot stem-specific timbre transfer in polyphonic music by 15.5% target alignment via acoustic-informed attention calibration that uses probabilistic priors to set coarse boundaries.
Wasserstein Lagrangian Mechanics formalizes second-order dynamics in Wasserstein space and provides an algorithm to learn them from observed marginals without specifying the Lagrangian, outperforming gradient flows on various dynamics.
TRACE creates valid conformal prediction sets for complex generative models by scoring outputs via averaged denoising or velocity errors along stochastic transport paths instead of likelihoods.
MaMi-HOI counters geometric forgetting in diffusion models via a Geometry-Aware Proximity Adapter for precise contacts and a Kinematic Harmony Adapter for natural whole-body postures in human-object interactions.
DOSER detects OOD actions via diffusion-model denoising error and applies selective regularization based on predicted transitions, proving gamma-contraction with performance bounds and outperforming priors on offline RL benchmarks.
citing papers explorer
-
ARDY: Autoregressive Diffusion with Hybrid Representation for Interactive Human Motion Generation
An autoregressive diffusion model with a hybrid explicit-root/latent-body representation generates real-time, controllable 3D human motion from text and spatial constraints.
-
Set Diffusion: Interpolating Token Orderings Between Autoregression and Diffusion for Fast and Flexible Decoding
Set diffusion factorizes likelihood over arbitrary token sets and uses a set-causal diffusion architecture to support KV caching and any-order decoding, yielding improved speed-quality tradeoffs versus prior diffusion LMs.
-
Diffeomorphic Optimization
Proposes diffeomorphic optimization for manifold-constrained problems in generative models via flow maps, with Lie-group extensions for protein design showing metric improvements.
-
FlexiSLM: A Dynamic and Controllable Frame Rate Spoken Language Model
FlexiSLM is the first spoken language model supporting dynamic and controllable frame rates on speech input and output, outperforming fixed-rate 7B models at high quality and enabling faster inference at lower rates like 6.25 Hz.
-
Panel Flow Matching: A Generative Approach to Learning Distributions of Longitudinal Data
Panel Flow Matching is a generative method to estimate panel densities from longitudinal data with statistical guarantees under irregular sampling, supporting completion, synthetic data, and classification.
-
Let EEG Models Learn EEG
JET is a conditional flow matching framework that generates EEG as continuous raw sequences with added constraints for spectral and temporal properties, achieving over 40% lower TS-FID than prior discrete denoising methods on three benchmarks.
-
Linear-DPO: Linear Direct Preference Optimization for Diffusion and Flow-Matching Generative Models
Linear-DPO replaces sigmoid utility with linear utility and adds EMA reference to improve preference alignment in diffusion and flow-matching text-to-image models.
-
CAdam: Context-Adaptive Moment Estimation for 3D Gaussian Densification in Generative Distillation
CAdam reinterprets densification in generative 3DGS as signal verification via gradient-moment interference, quantile context, and SNR gating to achieve large reductions in primitive count with comparable quality.
-
When Does Model Collapse Occur in Structured Interactive Learning?
Model collapse occurs in structured interactive learning if and only if the directed interaction graph satisfies a specific topological condition, with finite-sample guarantees for linear regression and asymptotic results for M-estimators.
-
BrepForge: Factorized B-rep Synthesis via Wireframe Composition and Boundary-Conditioned Surface Instantiation
BrepForge factorizes B-rep synthesis into face-aware autoregressive wireframe composition followed by boundary-conditioned surface instantiation using learning-free geometric priors.
-
Mat\'ern Noise for Triangulation-Agnostic Flow Matching on Meshes
Proposes discretized Matérn process noise for triangulation-agnostic flow matching on meshes with PoissonNet denoiser, tested on elastic states and humanoid poses for meshes exceeding one million triangles.
-
Designing streetscapes from street-view imagery using diffusion models
A multimodal diffusion model generates controllable alternative streetscapes from street-view imagery using visual metrics and text, shown on Chicago and Orlando data with gains in semantic consistency.
-
Dimension-Free Convergence of Discrete Diffusion Models: Adjoint Equations Induce the Right Space
Using adjoint equations, the paper derives S-independent IPM convergence bounds for masked and uniform discrete diffusion, controlled by score-matching losses.
-
VMU-Diff: A Coarse-to-fine Multi-source Data Fusion Framework for Precipitation Nowcasting
VMU-Diff improves precipitation nowcasting via coarse multi-source Vision Mamba fusion followed by residual conditional diffusion refinement.
-
What if Tomorrow is the World Cup Final? Counterfactual Time Series Forecasting with Textual Conditions
Introduces the task of counterfactual time series forecasting with textual conditions plus a text-attribution mechanism that improves accuracy by distinguishing mutable from immutable factors.
-
Support Before Frequency in Discrete Diffusion
Discrete diffusion models learn data support before frequencies because the exact reverse process decomposes edits into a dominant validity scale and a finer probability coefficient.
-
Stylized Text-to-Motion Generation via Hypernetwork-Driven Low-Rank Adaptation
A hypernetwork maps style motion embeddings to LoRA updates that stylize text-driven motion diffusion models with improved generalization to unseen styles via contrastive structuring of the style space.
-
Generative Transfer for Entropic Optimal Transport with Unknown Costs
A generative transfer framework using iterative path-wise tilting integrated with conditional flow matching recovers target entropic optimal transport couplings from reference samples, achieving O(δ) convergence in Wasserstein-1 distance.
-
Relative Score Policy Optimization for Diffusion Language Models
RSPO interprets reward advantages as targets for relative log-ratios in dLLMs, calibrating noisy estimates to stabilize RLVR training and achieve strong gains on planning tasks with competitive math reasoning performance.
-
Polyphonia: Zero-Shot Timbre Transfer in Polyphonic Music with Acoustic-Informed Attention Calibration
Polyphonia improves zero-shot stem-specific timbre transfer in polyphonic music by 15.5% target alignment via acoustic-informed attention calibration that uses probabilistic priors to set coarse boundaries.
-
A Call to Lagrangian Action: Learning Population Mechanics from Temporal Snapshots
Wasserstein Lagrangian Mechanics formalizes second-order dynamics in Wasserstein space and provides an algorithm to learn them from observed marginals without specifying the Lagrangian, outperforming gradient flows on various dynamics.
-
TRACE: Transport Alignment Conformal Prediction via Diffusion and Flow Matching Models
TRACE creates valid conformal prediction sets for complex generative models by scoring outputs via averaged denoising or velocity errors along stochastic transport paths instead of likelihoods.
-
MaMi-HOI: Harmonizing Global Kinematics and Local Geometry for Human-Object Interaction Generation
MaMi-HOI counters geometric forgetting in diffusion models via a Geometry-Aware Proximity Adapter for precise contacts and a Kinematic Harmony Adapter for natural whole-body postures in human-object interactions.
-
Beyond Penalization: Diffusion-based Out-of-Distribution Detection and Selective Regularization in Offline Reinforcement Learning
DOSER detects OOD actions via diffusion-model denoising error and applies selective regularization based on predicted transitions, proving gamma-contraction with performance bounds and outperforming priors on offline RL benchmarks.
-
Leveraging Pretrained Language Models as Energy Functions for Glauber Dynamics Text Diffusion
Pretrained language models are used as energy functions for Glauber dynamics in discrete text diffusion, improving generation quality over prior diffusion LMs and matching autoregressive models on benchmarks and reasoning tasks.
-
PODiff: Latent Diffusion in Proper Orthogonal Decomposition Space for Scientific Super-Resolution
PODiff performs conditional diffusion in a fixed, variance-ordered POD latent space to enable efficient probabilistic super-resolution of high-dimensional scientific fields with lower memory and better-calibrated uncertainty than pixel-space or dropout baselines.
-
Generative Modeling with Orbit-Space Particle Flow Matching
OGPP is a particle flow-matching method using orbit-space canonicalization and geometric paths that achieves lower error and fewer steps than prior approaches on 3D benchmarks.
-
VAnim: Rendering-Aware Sparse State Modeling for Structure-Preserving Vector Animation
VAnim creates open-domain text-to-SVG animations via sparse state updates on a persistent DOM tree, identification-first planning, and rendering-aware RL with a new 134k-example benchmark.
-
Arbitrarily Conditioned Hierarchical Flows for Spatiotemporal Events
ARCH is a hierarchical flow-based generative model that enables tractable conditional intensity computation and arbitrary conditioning for spatiotemporal event distributions.
-
Watch Your Step: Information Injection in Diffusion Models via Shadow Timestep Embedding
Timestep embeddings in diffusion models function as a separable side channel that can carry dedicated information for adversarial injection or detection.
-
GSCompleter: A Distillation-Free Plugin for Metric-Aware 3D Gaussian Splatting Completion in Seconds
GSCompleter completes 3DGS scenes from sparse viewpoints using a generate-then-register workflow with stereo-anchor view selection and ray-constrained registration to achieve metric-aware results and SOTA performance on benchmarks.
-
Frequency-Forcing: From Scaling-as-Time to Soft Frequency Guidance
Frequency-Forcing guides pixel flow-matching with a data-derived low-frequency auxiliary stream to softly enforce scale-ordered generation, improving FID on ImageNet-256 over baselines.
-
NI Sampling: Accelerating Discrete Diffusion Sampling by Token Order Optimization
NI Sampling accelerates discrete diffusion language models up to 14.3 times by training a neural indicator to select which tokens to sample at each step using a trajectory-preserving objective.
-
One-Step Diffusion with Inverse Residual Fields for Unsupervised Industrial Anomaly Detection
OSD-IRF performs unsupervised industrial anomaly detection with a single diffusion step by evaluating anomalies in inverse residual field space under a Gaussian, delivering SOTA or competitive results with roughly 2x speedup.
-
Long-Text-to-Image Generation via Compositional Prompt Decomposition
PRISM lets pre-trained text-to-image models handle long prompts by breaking them into compositional parts, predicting noise separately, and merging outputs via energy-based conjunction, matching fine-tuned models while generalizing better to prompts over 500 tokens.
-
Your Absorbing Discrete Diffusion Secretly Models the Conditional Distributions of Clean Data
Absorbing discrete diffusion models the conditional distributions of clean data; reparameterizing yields a time-independent RADD that unifies with AO-ARMs and reaches SOTA perplexity among diffusion models on zero-shot language benchmarks.
-
LongE2V: Long-Horizon Event-based Video Reconstruction, Prediction, and Frame Interpolation with Video Diffusion Models
Fine-tuning CogVideoX with autoregressive context management and bidirectional alignment enables a single model to perform event-based video reconstruction, prediction, and zero-shot interpolation with superior temporal stability.
-
WHERE to Generate Matters: Budget-Aware Synthetic Augmentation for Label Skewed Federated Learning
Entropy-adaptive per-class budgets let clients generate far fewer synthetic samples yet still close most of the accuracy gap caused by label skew in federated learning.
-
Unified Audio Intelligence Without Regressing on Text Intelligence
Audex unifies audio understanding and generation on a strong text MoE backbone with multi-stage SFT plus text-only Cascade RL, matching open SOTA audio scores while mostly retaining text capability.
-
Discontinuous Galerkin Neural Operator for Pathology Defocus Deblurring
DGNO parameterizes integral kernels with discontinuous Galerkin elements for heterogeneous defocus deblurring in pathology images and reports superior performance over prior methods.
-
Why SGD is not Brownian Motion: A New Perspective on Stochastic Dynamics
SGD is reformulated via a master equation from discrete updates, producing a discrete Fokker-Planck equation that predicts non-stationary variance growth proportional to learning rate in flat Hessian directions.
-
Simple Approximation and Derivative Free Inference-Time Scaling for Diffusion Models via Sequential Monte Carlo on Path Measures
URGE performs unbiased inference-time scaling for diffusion models by attaching multiplicative path weights from Girsanov estimation and resampling trajectories, with a proven equivalence to prior particle-wise SMC schemes.
-
Structured Neural Marked Point Processes for Interpretable Event Interaction Modeling
SNMPP builds a product-form neural influence kernel from a signed interaction network over event classes and a delay-aware monotonic temporal network to enable explicit discovery of inter-event relationships alongside strong prediction.
-
Self-Supervised On-Policy Distillation for Reasoning Language Models
SSOPD converts intra-group correct-wrong contrast into process supervision by distilling a teacher distribution from the shortest correct completion into prefixes of the longest wrong completion, improving GRPO on AIME and HMMT benchmarks.
-
VoxScene: Anchor-Conditioned Voxel Diffusion for Indoor Scene Arrangement
VoxScene is a new anchor-conditioned voxel diffusion model that synthesizes collision-free 3D indoor scene arrangements via discrete volumetric occupancies and uses the grids for asset retrieval.
-
Ada-Diffuser: Latent-Aware Adaptive Diffusion for Decision-Making
Ada-Diffuser is a causal diffusion model that jointly learns observed interaction structure and underlying latent dynamics from minimal observations for adaptive planning and policy learning.
-
AdaEraser: Training-Free Object Removal via Adaptive Attention Suppression
AdaEraser introduces token-wise adaptive attention suppression in diffusion denoising to enable high-quality training-free object removal by modulating suppression according to evolving self-attention maps.
-
ElasticDiT: Efficient Diffusion Transformers via Elastic Architecture and Sparse Attention for High-Resolution Image Generation on Mobile Devices
ElasticDiT introduces an elastic DiT architecture with adjustable spatial compression and block depth plus Shift Sparse Block Attention and a distilled VAE to enable a single model to cover multiple fidelity-latency points for high-resolution image generation on mobile devices.
-
TOPOS: High-Fidelity and Efficient Industry-Grade 3D Head Generation
TOPOS creates high-fidelity 3D heads with fixed industry topology from single images via a specialized VAE with Perceiver Resampler and a rectified flow transformer.
-
GeoQuery: Geometry-Query Diffusion for Sparse-View Reconstruction
GeoQuery replaces corrupted rendering features with geometry-aligned proxy queries and restricts cross-view attention to local windows, enabling robust diffusion-based refinement under extreme view sparsity.