Fréchet Distance optimized as FD-loss in representation space by decoupling population size from batch size improves generator quality, enables one-step generation from multi-step models, and motivates a multi-representation metric FDr^k.
hub
Learning transferable visual models from natural language supervision
13 Pith papers cite this work. Polarity classification is still indexing.
13
Pith papers citing it
hub tools
citation-role summary
background 2
method 1
citation-polarity summary
verdicts
UNVERDICTED 13representative citing papers
TMPO uses Softmax Trajectory Balance to match policy probabilities over multiple trajectories to a Boltzmann reward distribution, improving diversity by 9.1% in diffusion alignment tasks.
Delta-Adapter extracts a semantic delta from a single image pair via a pre-trained vision encoder and injects it through a Perceiver adapter to enable scalable single-pair supervised editing.
WorldJen is a new benchmark for generative video models that uses VLM-judged multi-dimensional Likert questionnaires validated against human preferences to achieve perfect tier agreement.
Cambrian-P adds per-frame camera pose tokens and a regression head to video MLLMs, delivering 4.5-6.5% gains on spatial benchmarks, generalization to other video QA tasks, and SOTA streaming pose estimation on ScanNet.
4D-GSW introduces a kinematic-aware spatio-temporal watermarking framework for 4D Gaussian Splatting that uses a Spatio-Temporal Curvature metric and HMM-MRF model to maintain consistency under attacks.
PersonaVLM adds memory extraction, multi-turn retrieval-based reasoning, and personality inference to multimodal LLMs, yielding 22.4% gains on a new long-term personalization benchmark and outperforming GPT-4o.
Concept filtering of child images from training data offers only limited protection against CSAM generation in text-to-image models, as prompting strategies and fine-tuning can bypass filters even when most child images are removed.
Uni-Hand forecasts 2D/3D hand waypoints, head motion, and contact states in egocentric views using vision-language fusion and dual-branch diffusion, with new benchmarks for downstream robotics and action tasks.
Cambrian-S introduces VSI-SUPER benchmarks for long-horizon spatial recall and counting, shows data scaling yields 30% gains on existing tests, and demonstrates a self-supervised next-latent predictor using surprise outperforms baselines on the new spatial supersensing tasks.
Swift Sampling is a training-free frame selection method that uses Taylor expansions on video latent trajectories to pick temporally surprising frames, outperforming uniform sampling on long-video QA tasks.
WorldAct activates monolithic 3D worlds into interactive scenes via multimodal agent-guided decomposition, geometrically aligned mesh reconstruction, and 3D inpainting.
ADAPT reframes test-time adaptation as probabilistic Gaussian inference with CLIP-guided regularization, delivering SOTA results without gradients, source data, or full target access in both online and transductive settings.
citing papers explorer
-
Representation Fr\'echet Loss for Visual Generation
Fréchet Distance optimized as FD-loss in representation space by decoupling population size from batch size improves generator quality, enables one-step generation from multi-step models, and motivates a multi-representation metric FDr^k.
-
TMPO: Trajectory Matching Policy Optimization for Diverse and Efficient Diffusion Alignment
TMPO uses Softmax Trajectory Balance to match policy probabilities over multiple trajectories to a Boltzmann reward distribution, improving diversity by 9.1% in diffusion alignment tasks.
-
Delta-Adapter: Scalable Exemplar-Based Image Editing with Single-Pair Supervision
Delta-Adapter extracts a semantic delta from a single image pair via a pre-trained vision encoder and injects it through a Perceiver adapter to enable scalable single-pair supervised editing.
-
WorldJen: An End-to-End Multi-Dimensional Benchmark for Generative Video Models
WorldJen is a new benchmark for generative video models that uses VLM-judged multi-dimensional Likert questionnaires validated against human preferences to achieve perfect tier agreement.
-
Cambrian-P: Pose-Grounded Video Understanding
Cambrian-P adds per-frame camera pose tokens and a regression head to video MLLMs, delivering 4.5-6.5% gains on spatial benchmarks, generalization to other video QA tasks, and SOTA streaming pose estimation on ScanNet.
-
4D-GSW: Kinematic-Aware Spatio-Temporal Consistent Watermarking for 4D Gaussian Splatting
4D-GSW introduces a kinematic-aware spatio-temporal watermarking framework for 4D Gaussian Splatting that uses a Spatio-Temporal Curvature metric and HMM-MRF model to maintain consistency under attacks.
-
PersonaVLM: Long-Term Personalized Multimodal LLMs
PersonaVLM adds memory extraction, multi-turn retrieval-based reasoning, and personality inference to multimodal LLMs, yielding 22.4% gains on a new long-term personalization benchmark and outperforming GPT-4o.
-
Evaluating Concept Filtering Defenses against Child Sexual Abuse Material Generation by Text-to-Image Models
Concept filtering of child images from training data offers only limited protection against CSAM generation in text-to-image models, as prompting strategies and fine-tuning can bypass filters even when most child images are removed.
-
Uni-Hand: Universal Hand Motion Forecasting in Egocentric Views
Uni-Hand forecasts 2D/3D hand waypoints, head motion, and contact states in egocentric views using vision-language fusion and dual-branch diffusion, with new benchmarks for downstream robotics and action tasks.
-
Cambrian-S: Towards Spatial Supersensing in Video
Cambrian-S introduces VSI-SUPER benchmarks for long-horizon spatial recall and counting, shows data scaling yields 30% gains on existing tests, and demonstrates a self-supervised next-latent predictor using surprise outperforms baselines on the new spatial supersensing tasks.
-
Swift Sampling: Selecting Temporal Surprises via Taylor Series
Swift Sampling is a training-free frame selection method that uses Taylor expansions on video latent trajectories to pick temporally surprising frames, outperforming uniform sampling on long-video QA tasks.
-
WorldAct: Activating Monolithic 3D Worlds into Interactive-Ready Object-Centric Scenes
WorldAct activates monolithic 3D worlds into interactive scenes via multimodal agent-guided decomposition, geometrically aligned mesh reconstruction, and 3D inpainting.
-
Backpropagation-Free Test-Time Adaptation via Probabilistic Gaussian Alignment
ADAPT reframes test-time adaptation as probabilistic Gaussian inference with CLIP-guided regularization, delivering SOTA results without gradients, source data, or full target access in both online and transductive settings.