arXiv AI
On the Limits of Scale: Inverse Scaling in Vision-Language Models
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Jun 16
UniT: Unified Multimodal Chain-of-Thought Test-time Scaling
arXiv:2602. 12279v2 Announce Type: replace-cross Abstract: Unified models can handle both multimodal understanding and generation within a single architecture, yet they typically operate in a single pass without iteratively refining their outputs.
Hugging Face Trending Papers
Sep 1
Teaching Vision-Language Models to Use the Scale They Are Given: Label-Free Equivariance Training for Metric Physical Reasoning
Metric questions about video require vision-language models to use supplied real-world references to convert visual measurements into physical units. Yet we find that current models use this scale inf...
arXiv Computation and Language
Sep 15
TestHallVQA: Exploring LVLMs' Document-Level Reasoning under Redundant Contexts from Scientific Exams
arXiv:2609.13158v1 Announce Type: new Abstract: Large Vision--Language Models (LVLMs) are increasingly expected to perform visual question answering (VQA) over planar media. However, existing planar...
arXiv Computation and Language
Oct 15
More Than Seeing: Vision as Scalable Anchors in Native Multimodal Pre-Training
arXiv:2610.19443v1 Announce Type: new Abstract: Native multimodal pre-training trains a single model from scratch on text and multimodal data, enabling it to understand both language and visual input...
arXiv Computation and Language
Oct 9
Scaling Native Multimodal Pre-Training From Scratch
The paper investigates how to scale a Transformer-based vision‑language model trained from scratch on multimodal inputs under a fixed compute budget. It finds that minimal loss follows a predictable compute law while optimal model size and token count obey power‑law scaling, with language and multimodal objectives showing distinct allocation trends. The study also proposes a budget‑compensation rule that allows additional multimodal tokens to offset text‑efficiency penalties, and demonstrates that native multimodal pre‑training improves spatial reasoning and few‑shot learning.
arXiv AI
Jun 2
Understanding the Effects of Distractors on Reasoning Vision-Language Models
arXiv:2511. 21397v2 Announce Type: replace-cross Abstract: How does irrelevant information (i.