PhyEditBench is a new benchmark for physics-aware image editing with real and synthetic instances plus a training-free PhyWorld baseline that uses test-time scaling to outperform SOTA models.
arXiv preprint arXiv:2505.17618 , year =
11 Pith papers cite this work. Polarity classification is still indexing.
11
Pith papers citing it
citation-role summary
background 4
citation-polarity summary
years
2026 11roles
background 4polarities
background 4representative citing papers
SMC-ITA applies sequential Monte Carlo resampling with lookahead-based multi-dimensional cross-modal rewards to improve inference-time alignment in video-to-audio generation, reporting 55.67% DeSync reduction and gains in IB-score and audio quality over baselines.
Presents multi-verifier framework and Adaptive Reward Weighting (ARW) for inference-time scaling in joint audio-video generation, reporting gains in alignment and synchronization on VGGSound and JavisBench-mini.
VLMs formulate differentiable rewards from task-specific rules to enable test-time online LoRA optimization of VGMs, delivering 16.7-point gains on symbolic and general video reasoning benchmarks over VLM-as-solver and Best-of-N baselines.
IPR improves valid solution rates on MNIST Sudoku from 55.8% to 75.0% by iteratively refining partial regions in sequential diffusion models without external verifiers or reward models.
CollabVR improves video reasoning performance by coupling vision-language models and video generation models in a closed-loop step-level collaboration that detects and repairs generation failures.
SpecLoR rectifies the amplitude spectrum of lookahead-estimated clean latents to natural-video priors during early ODE sampling steps, cutting physical artifacts with only four extra NFEs.
Stream-T1 is a test-time scaling framework for streaming video generation using scaled noise propagation from history, reward pruning across short and long windows, and feedback-guided memory sinking to improve temporal consistency and visual quality.
NoiseRater meta-learns instance-level importance scores for noise in diffusion training via bilevel optimization, then uses a two-stage pipeline to improve efficiency and generation quality on FFHQ and ImageNet.
Weight-shared looped transformers trained with intra-loop self-distillation match MaskGIT-class FID/FVD at roughly 4x fewer parameters and support any-time inference across loop counts.
A survey of test-time scaling for multimodal foundation models that introduces a three-way taxonomy of sampling, feedback, and search approaches along with applications and benchmarks.
citing papers explorer
-
PhyEditBench: A Real-World Multi-Stage Benchmark for Physics-Aware Image Editing
PhyEditBench is a new benchmark for physics-aware image editing with real and synthetic instances plus a training-free PhyWorld baseline that uses test-time scaling to outperform SOTA models.
-
SMC-ITA: Sequential Monte Carlo Inference-Time Alignment for Video-to-Audio Generation
SMC-ITA applies sequential Monte Carlo resampling with lookahead-based multi-dimensional cross-modal rewards to improve inference-time alignment in video-to-audio generation, reporting 55.67% DeSync reduction and gains in IB-score and audio quality over baselines.
-
Inference-Time Scaling for Joint Audio-Video Generation
Presents multi-verifier framework and Adaptive Reward Weighting (ARW) for inference-time scaling in joint audio-video generation, reporting gains in alignment and synchronization on VGGSound and JavisBench-mini.
-
VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization
VLMs formulate differentiable rewards from task-specific rules to enable test-time online LoRA optimization of VGMs, delivering 16.7-point gains on symbolic and general video reasoning benchmarks over VLM-as-solver and Best-of-N baselines.
-
Inference-Time Scaling in Diffusion Models through Iterative Partial Refinement
IPR improves valid solution rates on MNIST Sudoku from 55.8% to 75.0% by iteratively refining partial regions in sequential diffusion models without external verifiers or reward models.
-
CollabVR: Collaborative Video Reasoning with Vision-Language and Video Generation Models
CollabVR improves video reasoning performance by coupling vision-language models and video generation models in a closed-loop step-level collaboration that detects and repairs generation failures.
-
SpecLoR: Spectral Lookahead Rectification for Motion-Coherent Text-to-Video Generation
SpecLoR rectifies the amplitude spectrum of lookahead-estimated clean latents to natural-video priors during early ODE sampling steps, cutting physical artifacts with only four extra NFEs.
-
Stream-T1: Test-Time Scaling for Streaming Video Generation
Stream-T1 is a test-time scaling framework for streaming video generation using scaled noise propagation from history, reward pruning across short and long windows, and feedback-guided memory sinking to improve temporal consistency and visual quality.
-
NoiseRater: Meta-Learned Noise Valuation for Diffusion Model Training
NoiseRater meta-learns instance-level importance scores for noise in diffusion training via bilevel optimization, then uses a two-stage pipeline to improve efficiency and generation quality on FFHQ and ImageNet.
-
ELT: Elastic Looped Transformers for Visual Generation
Weight-shared looped transformers trained with intra-loop self-distillation match MaskGIT-class FID/FVD at roughly 4x fewer parameters and support any-time inference across loop counts.
-
Test-Time Scaling in Multimodal Foundation Models: A Comprehensive Survey of Generation and Reasoning
A survey of test-time scaling for multimodal foundation models that introduces a three-way taxonomy of sampling, feedback, and search approaches along with applications and benchmarks.