DCR uses a counterfactual attractor and projection-based repulsion to suppress default completion bias in diffusion models, improving fidelity for rare compositional prompts while preserving quality.
Canonical reference
LLM -grounded video diffusion models
Canonical reference. 80% of citing Pith papers cite this work as background.
7
Pith papers citing it
Background
80% of classified citations
citation-role summary
background 4
baseline 1
citation-polarity summary
verdicts
UNVERDICTED 7representative citing papers
MoRight disentangles object and camera motion via canonical-view specification and temporal cross-view attention, while decomposing motion into active user-driven and passive consequence components to learn and apply causality in video generation.
ViTexQA is a dataset forcing multi-frame text fusion for all questions, with FrameThinker achieving 6.3% ROUGE-L gain over baselines via CoT SFT and temporally-grounded RL.
PresentAgent-2 generates query-driven multimodal presentation videos with research grounding, supporting single-speaker, multi-speaker discussion, and interactive question-answering modes.
Representations learned by large AI models are converging toward a shared statistical model of reality.
This survey traces video generation technology from GANs to diffusion models and then to autoregressive and multimodal approaches while analyzing principles, strengths, and future trends.
The paper reviews the background, technology, applications, limitations, and future directions of OpenAI's Sora text-to-video generative model based on public information.
citing papers explorer
-
DCR: Counterfactual Attractor Guidance for Rare Compositional Generation
DCR uses a counterfactual attractor and projection-based repulsion to suppress default completion bias in diffusion models, improving fidelity for rare compositional prompts while preserving quality.
-
MoRight: Motion Control Done Right
MoRight disentangles object and camera motion via canonical-view specification and temporal cross-view attention, while decomposing motion into active user-driven and passive consequence components to learn and apply causality in video generation.
-
ViTexQA: A Multi-Frame Temporal Perception Dataset for Video Text Question Answering
ViTexQA is a dataset forcing multi-frame text fusion for all questions, with FrameThinker achieving 6.3% ROUGE-L gain over baselines via CoT SFT and temporally-grounded RL.
-
PresentAgent-2: Towards Generalist Multimodal Presentation Agents
PresentAgent-2 generates query-driven multimodal presentation videos with research grounding, supporting single-speaker, multi-speaker discussion, and interactive question-answering modes.
-
The Platonic Representation Hypothesis
Representations learned by large AI models are converging toward a shared statistical model of reality.
-
Evolution of Video Generative Foundations
This survey traces video generation technology from GANs to diffusion models and then to autoregressive and multimodal approaches while analyzing principles, strengths, and future trends.
-
Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models
The paper reviews the background, technology, applications, limitations, and future directions of OpenAI's Sora text-to-video generative model based on public information.