arXiv Computation and Language
Recursive Self-Improvement in Unified Multimodal Models
Read the original on arXiv Computation and Language →The Flow has not summarised this story yet — read it at arXiv Computation and Language.
Related stories
arXiv AI
1d ago
Visual Abstention in Unified Multimodal Models
arXiv:2610.07887v1 Announce Type: cross Abstract: Unified multimodal models (UMMs) integrate understanding and generation, yet their generative behavior is rarely governed by what they understand abo...
arXiv AI
Sep 3
Multimodal Language Models as Text-to-Image Model Evaluators
Multimodal Language Models as Text-to-Image Model Evaluators presents MT2IE, a framework where a multimodal large language model generates evaluation prompts and scores images, achieving higher correlation with human judgment than prior metrics. MT2IE recovers official T2I model rankings using only 20 prompts—far fewer than traditional benchmarks—and adapts prompts to each model’s performance, maintaining informative scoring ranges. The approach demonstrates that dynamic, interactive evaluation can replace static benchmarks as T2I models improve.
arXiv AI
Aug 19
Where a New Concept Must Enter: Entry Point Gates Cross-Task Usability in Unified Multimodal Models
The paper investigates how new concepts can be integrated into unified multimodal models (UMMs) by separating generation and understanding objectives through a novel visual entity bound to a single task direction. Experiments show that the effectiveness of cross‑task usability depends on where the concept is injected into the shared computation, with a mid‑stack alignment objective achieving high concept acquisition with minimal loss to overall performance. The study highlights that unified weights alone are insufficient; the two directions must share a semantic format at the entry point for efficient concept integration.
Hugging Face Trending Papers
Aug 10
Perception Before Supervision: Self-Contained Visual Distillation from Counterfactual Blind Spots
Self-improvement for multimodal large language models (MLLMs) is typically driven by reward-based methods that provide only coarse scalar feedback. Distillation offers a richer alternative through dense token-level supervision, but in the visual domain it usually depends on privileged context constructed using external annotations and tools, or stronger models.
arXiv AI
Sep 1
LOCI: A Locator-Critic with Refinement Loop
LOC I (Locator‑Critic) is a training‑free framework that separates visual search from evidence verification in Vision‑Language Models. It uses a Locator agent to propose candidate visual evidence and a Critic agent to assess its relevance, engaging in an iterative refinement loop that progressively improves the evidence until it is sufficient to answer a question. The approach yields state‑of‑the‑art results on several complex visual benchmarks, boosting accuracy for both open‑weight models like Qwen3‑VL and proprietary models such as Gemini 2.5 Pro.
Hugging Face Trending Papers
Aug 12
Do You See What You Draw? A Semantic Closed-Loop Framework for Holistic Evaluation of Unified Multimodal Models
As Large Vision-Language Models increasingly aim to integrate visual generation and understanding within a single parameter space, evaluating such structural unification in a cohesive manner remains a critical challenge. Current evaluation protocols predominantly treat generative and discriminative capabilities as separate tasks, leaving a gap in system-level evaluation for unified multimodal models (UMMs).