AnchorSeg uses ordered query banks of latent reasoning tokens plus a spatial anchor token and a Token-Mask Cycle Consistency loss to achieve 67.7% gIoU and 68.1% cIoU on the ReasonSeg benchmark.
hub Mixed citations
arXiv:2309.15807
Mixed citation behavior. Most common role is background (60%).
15
Pith papers citing it
Background
60% of classified citations
hub tools
citation-role summary
background 4
other 1
citation-polarity summary
verdicts
UNVERDICTED 15representative citing papers
3D-ARD+ unifies autoregressive token prediction with diffusion-based 3D latent generation to co-produce indoor scene layouts and object geometries that follow complex text-specified spatial and semantic constraints.
PacTure uses view packing and next-scale autoregressive prediction to generate consistent multi-view PBR textures faster than prior sequential or cross-attention methods.
ELLA introduces a timestep-aware semantic connector to link LLMs with diffusion models for improved dense prompt following, validated on a new 1K-prompt benchmark.
ElasticDiT introduces an elastic DiT architecture with adjustable spatial compression and block depth plus Shift Sparse Block Attention and a distilled VAE to enable a single model to cover multiple fidelity-latency points for high-resolution image generation on mobile devices.
Composer enables semantic-agnostic composition transfer from references and theme-driven planning via LVLMs to improve aesthetic quality in diffusion-based image generation.
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.
Semi-DPO applies semi-supervised learning to noisy preference data in diffusion DPO by training first on consensus pairs then iteratively pseudo-labeling conflicts, yielding state-of-the-art alignment with complex human preferences.
HRFD aligns multi-dimensional preferences in text-to-image diffusion via hierarchical relevance feedback and statistical distribution divergence measurement between liked and disliked image sets, remaining training-free and model-agnostic.
A single transformer combines language modeling loss and diffusion loss on mixed-modality data, scaling to 7B parameters and 2T tokens while matching specialized language and diffusion models.
Open-source text-to-video and image-to-video diffusion models generate high-quality 1024x576 videos, with the I2V variant claimed as the first to strictly preserve reference image content.
Diff.-NPO frames diffusion alignment as a self-play game reaching Nash equilibrium and reports better text-to-image results than prior DPO-style methods.
A 30B-parameter transformer and related models generate high-quality videos and audio, claiming state-of-the-art results on text-to-video, video editing, personalization, and audio generation tasks.
Step-Video-T2V describes a 30B-parameter text-to-video model with custom Video-VAE, 3D DiT, flow matching, and Video-DPO that claims state-of-the-art results on a new internal benchmark.
The Cosmos platform supplies open-source pre-trained world models and supporting tools for building fine-tunable digital world simulations to train Physical AI.
citing papers explorer
-
AnchorSeg: Language Grounded Query Banks for Reasoning Segmentation
AnchorSeg uses ordered query banks of latent reasoning tokens plus a spatial anchor token and a Token-Mask Cycle Consistency loss to achieve 67.7% gIoU and 68.1% cIoU on the ReasonSeg benchmark.
-
Co-generation of Layout and Shape from Text via Autoregressive 3D Diffusion
3D-ARD+ unifies autoregressive token prediction with diffusion-based 3D latent generation to co-produce indoor scene layouts and object geometries that follow complex text-specified spatial and semantic constraints.
-
PacTure: Efficient PBR Texture Generation on Packed Views with Visual Autoregressive Models
PacTure uses view packing and next-scale autoregressive prediction to generate consistent multi-view PBR textures faster than prior sequential or cross-attention methods.
-
ELLA: Equip Diffusion Models with LLM for Enhanced Semantic Alignment
ELLA introduces a timestep-aware semantic connector to link LLMs with diffusion models for improved dense prompt following, validated on a new 1K-prompt benchmark.
-
ElasticDiT: Efficient Diffusion Transformers via Elastic Architecture and Sparse Attention for High-Resolution Image Generation on Mobile Devices
ElasticDiT introduces an elastic DiT architecture with adjustable spatial compression and block depth plus Shift Sparse Block Attention and a distilled VAE to enable a single model to cover multiple fidelity-latency points for high-resolution image generation on mobile devices.
-
Advancing Aesthetic Image Generation via Composition Transfer
Composer enables semantic-agnostic composition transfer from references and theme-driven planning via LVLMs to improve aesthetic quality in diffusion-based image generation.
-
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.
-
Learning from Noisy Preferences: A Semi-Supervised Learning Approach to Direct Preference Optimization
Semi-DPO applies semi-supervised learning to noisy preference data in diffusion DPO by training first on consensus pairs then iteratively pseudo-labeling conflicts, yielding state-of-the-art alignment with complex human preferences.
-
Bridging the Intention-Expression Gap: Aligning Multi-Dimensional Preferences via Hierarchical Relevance Feedback in Text-to-Image Diffusion
HRFD aligns multi-dimensional preferences in text-to-image diffusion via hierarchical relevance feedback and statistical distribution divergence measurement between liked and disliked image sets, remaining training-free and model-agnostic.
-
Transfusion: Predict the Next Token and Diffuse Images with One Multi-Modal Model
A single transformer combines language modeling loss and diffusion loss on mixed-modality data, scaling to 7B parameters and 2T tokens while matching specialized language and diffusion models.
-
VideoCrafter1: Open Diffusion Models for High-Quality Video Generation
Open-source text-to-video and image-to-video diffusion models generate high-quality 1024x576 videos, with the I2V variant claimed as the first to strictly preserve reference image content.
-
Towards General Preference Alignment: Diffusion Models at Nash Equilibrium
Diff.-NPO frames diffusion alignment as a self-play game reaching Nash equilibrium and reports better text-to-image results than prior DPO-style methods.
-
Movie Gen: A Cast of Media Foundation Models
A 30B-parameter transformer and related models generate high-quality videos and audio, claiming state-of-the-art results on text-to-video, video editing, personalization, and audio generation tasks.
-
Step-Video-T2V Technical Report: The Practice, Challenges, and Future of Video Foundation Model
Step-Video-T2V describes a 30B-parameter text-to-video model with custom Video-VAE, 3D DiT, flow matching, and Video-DPO that claims state-of-the-art results on a new internal benchmark.
-
Cosmos World Foundation Model Platform for Physical AI
The Cosmos platform supplies open-source pre-trained world models and supporting tools for building fine-tunable digital world simulations to train Physical AI.