DiffIML applies score-based generative modeling to image manipulation localization, recovering coherent masks iteratively from noise to improve generalization on unseen manipulation types.
Canonical reference
Title resolution pending
Canonical reference. 100% of citing Pith papers cite this work as background.
30
Pith papers citing it
Background
100% of classified citations
citation-role summary
background 5
citation-polarity summary
roles
background 5polarities
background 5representative citing papers
ZODIAC enables zero-shot inference of conflict-inducing conditions in O-RAN xApps from marginal offline data alone via uncertainty-penalized compositional diffusion reasoning.
OTCA improves GRPO training for visual generation by estimating step importance in trajectories and adaptively weighting multiple reward objectives.
DFAlign uses diffusion-based denoising to generate foreground knowledge prompts that improve cross-modal alignment for detecting unseen actions in untrimmed videos, reporting state-of-the-art results on OV-TAD benchmarks.
UniEditBench unifies image and video editing evaluation with a nine-plus-eight operation taxonomy and cost-effective 4B/8B distilled MLLM evaluators that align with human judgments.
SynHAT uses a novel two-stage spatio-temporal diffusion framework with Latent Spatio-Temporal U-Net to synthesize realistic human activity traces, outperforming baselines by 52% on spatial and 33% on temporal metrics across four cities.
GeoLink uses offline 3D scene reconstruction to guide 2D feature refinement and relation distillation for improved generalization in cross-view geo-localization.
A replay method for continual face forgery detection condenses real-fake distribution discrepancies into compact maps and synthesizes compatible samples from current real faces to reduce forgetting under tight memory budgets without storing historical images.
IAD-Unify unifies industrial anomaly segmentation, region-grounded language understanding, and mask-guided generation in one framework using DINOv2 token injection into Qwen3.5, supported by the new Anomaly-56K dataset of 59,916 images.
SHARP applies a spectrum-aware dynamic RoPE scaling schedule that promotes resolution more strongly in early denoising stages and relaxes it later, outperforming static baselines on quality metrics for remote sensing images.
PhysGen uses video models to learn physics for robots, outperforming baselines by up to 13.8% on Libero and matching specialized models in real-world tasks.
Memorization in diffusion models is detected via latent update norm instability and mitigated on-the-fly, yielding AUC over 0.999 and zero memorization rate on Stable Diffusion 1.4.
SENSE is a controllable diffusion model that jointly generates realistic urban satellite imagery and aligned building energy consumption and height maps from road networks and density inputs, improving downstream tasks with under 20% labeled data.
MAEPose is a masked autoencoder that learns spatiotemporal representations from unlabeled mmWave radar videos to estimate human poses, outperforming baselines by up to 22.1% in MPJPE.
A latent denoising objective with saliency-aware corruption and contrastive distillation improves visual alignment and corruption robustness in large multimodal models.
Task-aware localization via attention cues and feature centroids from source/target streams in IIE models improves non-edit consistency while preserving instruction following.
A two-stage semi-supervised flow matching framework with random voting and conflict-free guidance fuses mosaiced hyperspectral and panchromatic images to generate superior high-resolution hyperspectral results on benchmarks.
Long-CODE isolates long-context video evaluation with a new benchmark dataset and shot-dynamics metric that correlates better with human judgments on narrative richness and global consistency than short-video metrics.
RF-CMG synthesizes high-quality mmWave and RFID signals from WiFi using a diffusion model with Modality-Guided Embedding for high-frequency details and Low-Frequency Modality Consistency to preserve physical structure.
ARGen generates high-fidelity dynamic facial expression videos using affective semantic injection and adaptive reinforcement diffusion to improve emotion recognition models facing data scarcity and long-tail distributions.
VersaVogue unifies garment generation and virtual dressing via trait-routing attention with mixture-of-experts and an automated multi-perspective preference optimization pipeline that uses DPO without human labels.
InsTraj generates realistic, instruction-faithful GPS trajectories by using an LLM to parse natural-language travel intent and a multimodal diffusion transformer to produce the paths.
GTC improves multi-modal recommendation by using user-conditional diffusion-based feature filtering and total correlation optimization, achieving up to 28.3% gains in NDCG@5 on benchmarks.
A diffusion model with dynamic modality gating and cross-modal mutual learning restores missing features in VLMs bi-directionally while preserving the original model's generalization.
citing papers explorer
-
Towards Generalized Image Manipulation Localization via Score-based Model
DiffIML applies score-based generative modeling to image manipulation localization, recovering coherent masks iteratively from noise to improve generalization on unseen manipulation types.
-
ZODIAC: Zero-shot Offline Diffusion for Inferring Multi-xApps Conflicts in Open Radio Access Networks
ZODIAC enables zero-shot inference of conflict-inducing conditions in O-RAN xApps from marginal offline data alone via uncertainty-penalized compositional diffusion reasoning.
-
Learning to Credit the Right Steps: Objective-aware Process Optimization for Visual Generation
OTCA improves GRPO training for visual generation by estimating step importance in trajectories and adaptively weighting multiple reward objectives.
-
Denoise and Align: Diffusion-Driven Foreground Knowledge Prompting for Open-Vocabulary Temporal Action Detection
DFAlign uses diffusion-based denoising to generate foreground knowledge prompts that improve cross-modal alignment for detecting unseen actions in untrimmed videos, reporting state-of-the-art results on OV-TAD benchmarks.
-
UniEditBench: A Unified and Cost-Effective Benchmark for Image and Video Editing via Distilled MLLMs
UniEditBench unifies image and video editing evaluation with a nine-plus-eight operation taxonomy and cost-effective 4B/8B distilled MLLM evaluators that align with human judgments.
-
SynHAT: A Two-stage Coarse-to-Fine Diffusion Framework for Synthesizing Human Activity Traces
SynHAT uses a novel two-stage spatio-temporal diffusion framework with Latent Spatio-Temporal U-Net to synthesize realistic human activity traces, outperforming baselines by 52% on spatial and 33% on temporal metrics across four cities.
-
GeoLink: A 3D-Aware Framework Towards Better Generalization in Cross-View Geo-Localization
GeoLink uses offline 3D scene reconstruction to guide 2D feature refinement and relation distillation for improved generalization in cross-view geo-localization.
-
Direct Discrepancy Replay: Distribution-Discrepancy Condensation and Manifold-Consistent Replay for Continual Face Forgery Detection
A replay method for continual face forgery detection condenses real-fake distribution discrepancies into compact maps and synthesizes compatible samples from current real faces to reduce forgetting under tight memory budgets without storing historical images.
-
IAD-Unify: A Region-Grounded Unified Model for Industrial Anomaly Segmentation, Understanding, and Generation
IAD-Unify unifies industrial anomaly segmentation, region-grounded language understanding, and mask-guided generation in one framework using DINOv2 token injection into Qwen3.5, supported by the new Anomaly-56K dataset of 59,916 images.
-
SHARP: Spectrum-aware Highly-dynamic Adaptation for Resolution Promotion in Remote Sensing Synthesis
SHARP applies a spectrum-aware dynamic RoPE scaling schedule that promotes resolution more strongly in early denoising stages and relaxes it later, outperforming static baselines on quality metrics for remote sensing images.
-
Learning Physics from Pretrained Video Models: A Multimodal Continuous and Sequential World Interaction Models for Robotic Manipulation
PhysGen uses video models to learn physics for robots, outperforming baselines by up to 13.8% on Libero and matching specialized models in real-world tasks.
-
Broken Memories: Detecting and Mitigating Memorization in Diffusion Models with Degraded Generations
Memorization in diffusion models is detected via latent update norm instability and mitigated on-the-fly, yielding AUC over 0.999 and zero memorization rate on Stable Diffusion 1.4.
-
SENSE: Satellite-based ENergy Synthesis for Sustainable Environment
SENSE is a controllable diffusion model that jointly generates realistic urban satellite imagery and aligned building energy consumption and height maps from road networks and density inputs, improving downstream tasks with under 20% labeled data.
-
MAEPose: Self-Supervised Spatiotemporal Learning for Human Pose Estimation on mmWave Video
MAEPose is a masked autoencoder that learns spatiotemporal representations from unlabeled mmWave radar videos to estimate human poses, outperforming baselines by up to 22.1% in MPJPE.
-
Latent Denoising Improves Visual Alignment in Large Multimodal Models
A latent denoising objective with saliency-aware corruption and contrastive distillation improves visual alignment and corruption robustness in large multimodal models.
-
Rethinking Where to Edit: Task-Aware Localization for Instruction-Based Image Editing
Task-aware localization via attention cues and feature centroids from source/target streams in IIE models improves non-edit consistency while preserving instruction following.
-
Semi-Supervised Flow Matching for Mosaiced and Panchromatic Fusion Imaging
A two-stage semi-supervised flow matching framework with random voting and conflict-free guidance fuses mosaiced hyperspectral and panchromatic images to generate superior high-resolution hyperspectral results on benchmarks.
-
Long-CODE: Isolating Pure Long-Context as an Orthogonal Dimension in Video Evaluation
Long-CODE isolates long-context video evaluation with a new benchmark dataset and shot-dynamics metric that correlates better with human judgments on narrative richness and global consistency than short-video metrics.
-
Cross-Modal Generation: From Commodity WiFi to High-Fidelity mmWave and RFID Sensing
RF-CMG synthesizes high-quality mmWave and RFID signals from WiFi using a diffusion model with Modality-Guided Embedding for high-frequency details and Low-Frequency Modality Consistency to preserve physical structure.
-
ARGen: Affect-Reinforced Generative Augmentation towards Vision-based Dynamic Emotion Perception
ARGen generates high-fidelity dynamic facial expression videos using affective semantic injection and adaptive reinforcement diffusion to improve emotion recognition models facing data scarcity and long-tail distributions.
-
VersaVogue: Visual Expert Orchestration and Preference Alignment for Unified Fashion Synthesis
VersaVogue unifies garment generation and virtual dressing via trait-routing attention with mixture-of-experts and an automated multi-perspective preference optimization pipeline that uses DPO without human labels.
-
InsTraj: Instructing Diffusion Models with Travel Intentions to Generate Real-world Trajectories
InsTraj generates realistic, instruction-faithful GPS trajectories by using an LLM to parse natural-language travel intent and a multimodal diffusion transformer to produce the paths.
-
User-Aware Conditional Generative Total Correlation Learning for Multi-Modal Recommendation
GTC improves multi-modal recommendation by using user-conditional diffusion-based feature filtering and total correlation optimization, achieving up to 28.3% gains in NDCG@5 on benchmarks.
-
Enhancing Foundation VLM Robustness to Missing Modality: Scalable Diffusion for Bi-directional Feature Restoration
A diffusion model with dynamic modality gating and cross-modal mutual learning restores missing features in VLMs bi-directionally while preserving the original model's generalization.
-
Generative Bid Shading in Real-Time Bidding Advertising
GBS replaces two-stage bid landscape modeling with an autoregressive generative model plus reward-aligned policy optimization to improve short- and long-term advertiser surplus in real-time bidding.
-
From Snapshots to Trajectories: Learning Single-Cell Gene Expression Dynamics via Conditional Flow Matching
scFM learns bidirectional velocity fields from entropically regularized OT couplings between snapshots, with added alignment and regularization to reduce drift in long-horizon predictions of single-cell trajectories.
-
SubFlow: Sub-mode Conditioned Flow Matching for Diverse One-Step Generation
SubFlow restores full mode coverage in one-step flow matching by conditioning on sub-modes from semantic clustering, yielding higher diversity on ImageNet-256 while preserving FID.
-
Sampling Parallelism for Fast and Efficient Bayesian Learning
Sampling parallelism distributes Bayesian sample evaluations across GPUs for near-perfect scaling, lower memory use, and faster convergence via per-GPU data augmentations, outperforming pure data parallelism in diversity.
-
TIGFlow-GRPO: Trajectory Forecasting via Interaction-Aware Flow Matching and Reward-Guided Optimization
TIGFlow-GRPO uses a Trajectory-Interaction-Graph in conditional flow matching plus Flow-GRPO optimization to produce more accurate, socially compliant, and physically feasible trajectory forecasts on ETH/UCY and SDD datasets.
-
Harnessing AI for Inverse Partial Differential Equation Problems: Past, Present, and Prospects
A survey organizing AI methods for inverse PDE problems into inverse problems, inverse design, and control categories, covering applications and future challenges like physics-informed models and uncertainty quantification.