DisciplineGen-1M is a million-scale multidisciplinary dataset for text-to-image generation and editing, paired with a discipline-informed model that improves results on discipline-specific benchmarks.
Internvl-u: Democratizing unified multimodal models for understanding, reasoning, generation and editing
10 Pith papers cite this work. Polarity classification is still indexing.
10
Pith papers citing it
citation-role summary
background 2
baseline 2
citation-polarity summary
years
2026 10representative citing papers
A self-bootstrapping paradigm uses trajectories from a small seed model to activate pre-planned sub-question decomposition in target models, enabling consistent outperformance on multi-hop QA without external distillation.
Aurora introduces a VLM-based agent that converts raw user video edit requests into structured conditioning inputs for a unified diffusion transformer, improving performance on underspecified tasks via a new benchmark.
Edit-Compass and EditReward-Compass are new unified benchmarks for fine-grained image editing evaluation and realistic reward modeling in reinforcement learning optimization.
Lance presents a dual-stream mixture-of-experts model with modality-aware positional encoding and staged multi-task training that outperforms prior open-source unified models on image and video generation while keeping strong understanding performance.
Latent Action Control learns unobserved action trajectories via variational alignment and GRPO to inject reasoning into flow-based image generation, yielding gains on compositional benchmarks.
G²TR reduces visual tokens and prefill compute by 1.94x in separate-encoder UMMs via generation-guided importance from VAE latent consistency, balanced selection, and merging, while preserving reasoning accuracy and editing quality.
Tuna-2 shows that direct pixel embeddings can replace vision encoders in unified multimodal models, achieving competitive generation and stronger understanding at scale.
LLaDA2.0-Uni unifies multimodal understanding and generation inside one discrete diffusion large language model with a semantic tokenizer, MoE backbone, and diffusion decoder.
SenseNova-U1 presents native unified multimodal models that match top understanding VLMs while delivering strong performance in image generation, infographics, and interleaved tasks via the NEO-unify architecture.
citing papers explorer
-
DisciplineGen-1M: A Large-Scale Dataset for Multidisciplinary Visual Generation and Editing
DisciplineGen-1M is a million-scale multidisciplinary dataset for text-to-image generation and editing, paired with a discipline-informed model that improves results on discipline-specific benchmarks.
-
Plan Before Search: Search Agents Need Plan
A self-bootstrapping paradigm uses trajectories from a small seed model to activate pre-planned sub-question decomposition in target models, enabling consistent outperformance on multi-hop QA without external distillation.
-
Aurora: Unified Video Editing with a Tool-Using Agent
Aurora introduces a VLM-based agent that converts raw user video edit requests into structured conditioning inputs for a unified diffusion transformer, improving performance on underspecified tasks via a new benchmark.
-
Edit-Compass & EditReward-Compass: A Unified Benchmark for Image Editing and Reward Modeling
Edit-Compass and EditReward-Compass are new unified benchmarks for fine-grained image editing evaluation and realistic reward modeling in reinforcement learning optimization.
-
Lance: Unified Multimodal Modeling by Multi-Task Synergy
Lance presents a dual-stream mixture-of-experts model with modality-aware positional encoding and staged multi-task training that outperforms prior open-source unified models on image and video generation while keeping strong understanding performance.
-
Latent Action Control for Reasoning-Guided Unified Image Generation
Latent Action Control learns unobserved action trajectories via variational alignment and GRPO to inject reasoning into flow-based image generation, yielding gains on compositional benchmarks.
-
G$^2$TR: Generation-Guided Visual Token Reduction for Separate-Encoder Unified Multimodal Models
G²TR reduces visual tokens and prefill compute by 1.94x in separate-encoder UMMs via generation-guided importance from VAE latent consistency, balanced selection, and merging, while preserving reasoning accuracy and editing quality.
-
Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation
Tuna-2 shows that direct pixel embeddings can replace vision encoders in unified multimodal models, achieving competitive generation and stronger understanding at scale.
-
LLaDA2.0-Uni: Unifying Multimodal Understanding and Generation with Diffusion Large Language Model
LLaDA2.0-Uni unifies multimodal understanding and generation inside one discrete diffusion large language model with a semantic tokenizer, MoE backbone, and diffusion decoder.
-
SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-unify Architecture
SenseNova-U1 presents native unified multimodal models that match top understanding VLMs while delivering strong performance in image generation, infographics, and interleaved tasks via the NEO-unify architecture.