D2PO learns better low-NFE diffusion timestep schedules and CFG weights via DPO on a score-based energy with a dynamic denser-schedule preference target.
In: NeurIPS (2020)
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 8roles
background 1polarities
background 1representative citing papers
Anti-Prompt protects images from text-guided image-to-video generation by suppressing text-conditioned attention during denoising, producing visible generation failures.
Refinement via Regeneration (RvR) reformulates image refinement in unified multimodal models as conditional regeneration using prompt and semantic tokens from the initial image, yielding higher alignment scores than editing-based methods.
HO-Flow synthesizes realistic hand-object motions from text and canonical 3D objects via an interaction-aware VAE and masked flow matching, reporting SOTA physical plausibility and diversity on GRAB, OakInk, and DexYCB.
OT-NFM parameterizes the flow map directly with neural flows and uses optimal transport for consistent noise-data couplings to achieve ODE-free one-step generation while avoiding mean collapse.
MIRAGE introduces a benchmark for multi-instance image editing and a training-free framework that uses vision-language parsing and parallel regional denoising to achieve precise edits without altering backgrounds.
FASTER adds a Horizon-Aware Schedule to flow VLAs that compresses immediate-action denoising to one step while keeping long-horizon trajectory quality, lowering real-robot reaction latency.
Weak-to-strong knowledge distillation applied early and then turned off accelerates convergence to target performance in visual learning tasks by factors of 1.7-4.8x.
citing papers explorer
-
D2PO: Optimizing Diffusion Samplers via Dynamic Preference
D2PO learns better low-NFE diffusion timestep schedules and CFG weights via DPO on a score-based energy with a dynamic denser-schedule preference target.
-
Anti-Prompt: Image Protection against Text-Guided Image-to-Video Generation
Anti-Prompt protects images from text-guided image-to-video generation by suppressing text-conditioned attention during denoising, producing visible generation failures.
-
Refinement via Regeneration: Enlarging Modification Space Boosts Image Refinement in Unified Multimodal Models
Refinement via Regeneration (RvR) reformulates image refinement in unified multimodal models as conditional regeneration using prompt and semantic tokens from the initial image, yielding higher alignment scores than editing-based methods.
-
HO-Flow: Generalizable Hand-Object Interaction Generation with Latent Flow Matching
HO-Flow synthesizes realistic hand-object motions from text and canonical 3D objects via an interaction-aware VAE and masked flow matching, reporting SOTA physical plausibility and diversity on GRAB, OakInk, and DexYCB.
-
ODE-free Neural Flow Matching for One-Step Generative Modeling
OT-NFM parameterizes the flow map directly with neural flows and uses optimal transport for consistent noise-data couplings to achieve ODE-free one-step generation while avoiding mean collapse.
-
MIRAGE: Benchmarking and Aligning Multi-Instance Image Editing
MIRAGE introduces a benchmark for multi-instance image editing and a training-free framework that uses vision-language parsing and parallel regional denoising to achieve precise edits without altering backgrounds.
-
FASTER: Rethinking Real-Time Flow VLAs
FASTER adds a Horizon-Aware Schedule to flow VLAs that compresses immediate-action denoising to one step while keeping long-horizon trajectory quality, lowering real-robot reaction latency.
-
Weak-to-Strong Knowledge Distillation Accelerates Visual Learning
Weak-to-strong knowledge distillation applied early and then turned off accelerates convergence to target performance in visual learning tasks by factors of 1.7-4.8x.