G squared TR: Generation-Guided Visual Token Reduction for Separate-Encoder Unified Multimodal Models

arXiv:2605.12309 · cs.CV · Submitted 2026-05-12 · Read on arXiv

cs.CV

Submitted: 2026-05-12

Updated: 2026-09-27

Code: https://github.com/lijunxian111/G2TR

Terminology

• Benchmark — 22× in this paper · explained in 2 episodes
• Pruning — 9× in this paper · explained in 4 episodes
• Thinking mode — 7× in this paper · explained in 2 episodes
• Embeddings — 5× in this paper · explained in 2 episodes
• Benchmarking — 4× in this paper · explained in 4 episodes
• Transformer — 4× in this paper · explained in 2 episodes
• Ablation — 3× in this paper · explained in 1 episode
• Consistency — 3× in this paper · explained in 3 episodes
• Core — 3× in this paper · explained in 2 episodes
• Cosine Similarity — 3× in this paper · explained in 3 episodes
• Decode — 3× in this paper · explained in 2 episodes
• KV cache — 3× in this paper · explained in 3 episodes
• Latent Representation — 3× in this paper · explained in 2 episodes
• Latent Representations — 3× in this paper · explained in 3 episodes
• Vision-language models — 3× in this paper · explained in 2 episodes
• Accuracy — 2× in this paper · explained in 1 episode
• Alignment — 2× in this paper · explained in 1 episode
• Decoupling — 2× in this paper · explained in 2 episodes
• Reconstruction Error — 2× in this paper · explained in 2 episodes
• Reinforcement Learning — 2× in this paper · explained in 4 episodes
• Ablation study — 1× in this paper · explained in 1 episode
• Diffusion Model — 1× in this paper · explained in 8 episodes
• Diffusion Models — 1× in this paper · explained in 6 episodes
• Edge Devices — 1× in this paper · explained in 2 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• Instruction Tuning — 1× in this paper · explained in 2 episodes
• Latent Diffusion Model — 1× in this paper · explained in 2 episodes
• Latent Diffusion Models — 1× in this paper · explained in 2 episodes
• Latent Space — 1× in this paper · explained in 7 episodes
• Multimodal Reasoning — 1× in this paper · explained in 5 episodes
• Redundancy — 1× in this paper · explained in 2 episodes
• Semantic Understanding — 1× in this paper · explained in 2 episodes
• Sparsity — 1× in this paper · explained in 4 episodes

Sources

• GPT-4 Technical Report
• Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling
• Emerging Properties in Unified Multimodal Pretraining
• Understanding and Harnessing Sparsity in Unified Multimodal Models
• PlanViz: Evaluating Planning-Oriented Image Generation and Editing for Computer-Use Tasks
• ROVER: Benchmarking Reciprocal Cross-Modal Reasoning for Omnimodal Generation
• Step1X-Edit: A Practical Framework for General Image Editing
• UniMoD: Efficient Unified Multimodal Transformers with Mixture-of-Depths
• WiseEdit: Benchmarking Cognition- and Creativity-Informed Image Editing
• IVC-Prune: Revealing the Implicit Visual Coordinates in LVLMs for Vision Token Pruning
• Chameleon: Mixed-Modal Early-Fusion Foundation Models
• Gemini: A Family of Highly Capable Multimodal Models
• InternVL-U: Democratizing Unified Multimodal Models for Understanding, Reasoning, Generation and Editing
• VL-Rethinker: Incentivizing Self-Reflection of Vision-Language Models with Reinforcement Learning
• RationalRewards: Reasoning Rewards Scale Visual Generation Both Training and Test Time
• Emergent Hierarchical Reasoning in LLMs through Reinforcement Learning
• Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution
• InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models