{"total":12,"items":[{"citing_arxiv_id":"2607.02099","ref_index":12,"ref_count":1,"confidence":0.55,"is_internal_anchor":false,"paper_title":"X-Splat: Gaussian Splatting for 3D CBCT Generation from Single Panoramic Radiograph","primary_cat":"cs.CV","submitted_at":"2026-07-02T12:34:59+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"X-Splat is the first Gaussian Splatting method that reconstructs CBCT-like 3D dental volumes from a single panoramic radiograph by constraining learnable Gaussians to panoramic geometry and adding a residual anatomical refiner.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.15855","ref_index":15,"ref_count":1,"confidence":0.55,"is_internal_anchor":false,"paper_title":"Do Less, Achieve More: Do We Need Every-Step Optimization for RL Fine-tuning of Diffusion Models?","primary_cat":"cs.CV","submitted_at":"2026-05-15T11:14:13+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"AdaScope adaptively selects optimal RL intervention points during diffusion denoising by monitoring structural and semantic changes, delivering 66% higher performance at 59% lower cost than full-trajectory RL baselines.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.10127","ref_index":15,"ref_count":2,"confidence":0.55,"is_internal_anchor":false,"paper_title":"Fashion130K: An E-commerce Fashion Dataset for Outfit Generation with Unified Multi-modal Condition","primary_cat":"cs.CV","submitted_at":"2026-05-11T07:40:03+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Fashion130K dataset and UMC framework align text and visual prompts to generate more consistent fashion outfits than prior state-of-the-art methods.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.02198","ref_index":12,"ref_count":2,"confidence":0.55,"is_internal_anchor":false,"paper_title":"SlimDiffSR: Toward Lightweight and Efficient Remote Sensing Image Super-Resolution via Diffusion Model Distillation","primary_cat":"cs.CV","submitted_at":"2026-05-04T03:54:54+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"SlimDiffSR uses uncertainty-guided timestep assignment and structured pruning with frequency- and direction-separable convolutions plus MMD distillation to create a 200x faster, 20x smaller diffusion SR model for remote sensing while retaining competitive quality.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.13305","ref_index":28,"ref_count":1,"confidence":0.55,"is_internal_anchor":false,"paper_title":"Bias at the End of the Score","primary_cat":"cs.CV","submitted_at":"2026-04-14T21:20:47+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Reward models used as quality scorers in text-to-image generation encode demographic biases that cause reward-guided training to sexualize female subjects, reinforce stereotypes, and reduce diversity.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.09405","ref_index":21,"ref_count":1,"confidence":0.55,"is_internal_anchor":false,"paper_title":"EGLOCE: Training-Free Energy-Guided Latent Optimization for Concept Erasure","primary_cat":"cs.CV","submitted_at":"2026-04-10T15:19:02+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"EGLOCE erases target concepts in diffusion models at inference time by optimizing latents with dual energy guidance that repels unwanted concepts while retaining prompt alignment.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.05171","ref_index":10,"ref_count":1,"confidence":0.55,"is_internal_anchor":false,"paper_title":"Modality-Aware and Anatomical Vector-Quantized Autoencoding for Multimodal Brain MRI","primary_cat":"cs.CV","submitted_at":"2026-04-06T21:07:34+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"NeuroQuant is a modality-aware 3D VQ-VAE that uses dual-stream encoding, a shared anatomical codebook, and FiLM to achieve superior multi-modal brain MRI reconstruction.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2603.16570","ref_index":20,"ref_count":1,"confidence":0.55,"is_internal_anchor":false,"paper_title":"Face2Scene: Using Facial Degradation as an Oracle for Diffusion-Based Scene Restoration","primary_cat":"cs.CV","submitted_at":"2026-03-17T14:27:24+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Face2Scene uses facial restoration as an oracle to derive degradation codes that condition a diffusion model for restoring the entire degraded scene.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2602.21977","ref_index":17,"ref_count":1,"confidence":0.55,"is_internal_anchor":false,"paper_title":"When LoRA Betrays: Backdooring Text-to-Image Models by Masquerading as Benign Adapters","primary_cat":"cs.CV","submitted_at":"2026-02-25T14:56:51+00:00","verdict":"CONDITIONAL","verdict_confidence":"MODERATE","novelty_score":8.0,"formal_verification":"none","one_line_summary":"MasqLoRA shows that an independent LoRA adapter can be trained on a few trigger-target pairs to backdoor diffusion models with 99.8% success rate while remaining stealthy when the trigger is absent.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2511.19365","ref_index":19,"ref_count":1,"confidence":0.55,"is_internal_anchor":false,"paper_title":"DeCo: Frequency-Decoupled Pixel Diffusion for End-to-End Image Generation","primary_cat":"cs.CV","submitted_at":"2025-11-24T17:59:06+00:00","verdict":"CONDITIONAL","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"DeCo decouples high- and low-frequency generation in pixel diffusion via a DiT plus lightweight decoder and a frequency-aware flow-matching loss, reaching FID 1.62 at 256x256 and 2.22 at 512x512 on ImageNet while closing the gap to latent diffusion methods.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2511.18719","ref_index":12,"ref_count":1,"confidence":0.55,"is_internal_anchor":false,"paper_title":"Seeing What Matters: Visual Preference Policy Optimization for Visual Generation","primary_cat":"cs.CV","submitted_at":"2025-11-24T03:21:17+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"ViPO enhances GRPO for visual generation by creating spatially and temporally aware advantage maps from pretrained vision models to focus optimization on perceptually important regions.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2511.12968","ref_index":13,"ref_count":1,"confidence":0.55,"is_internal_anchor":false,"paper_title":"GrOCE:Graph-Guided Online Concept Erasure for Text-to-Image Diffusion Models","primary_cat":"cs.CV","submitted_at":"2025-11-17T04:47:16+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"GrOCE uses dynamic semantic graphs for online, training-free erasure of target concepts from diffusion model prompts via cluster identification and selective severing.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null}],"limit":50,"offset":0}