Papers10

#OCR

Phi-4-reasoning-vision-15B Technical Report

Jyoti Aneja, Michael Harrison et al.Mar 4arXiv

Phi-4-reasoning-vision-15B is a small, open-weight AI that understands pictures and text together and is especially good at math, science, and using computer screens.

#multimodal reasoning#vision-language model#mid-fusion

From Blind Spots to Gains: Diagnostic-Driven Iterative Training for Large Multimodal Models

Intermediate

Hongrui Jia, Chaoya Jiang et al.Feb 26arXiv

Large multimodal models (LMMs) can look at pictures and read text, but they still miss tricky cases, like tiny chart labels or multi-step math.

#Large Multimodal Models#Diagnostic-driven Progressive Evolution#Reinforcement Learning

DODO: Discrete OCR Diffusion Models

Beginner

Sean Man, Roy Ganz et al.Feb 18arXiv

OCR is like reading a page exactly as it is, and that strictness makes it perfect for fast, parallel generation.

#OCR#vision-language models#discrete diffusion

Adapting Vision-Language Models for E-commerce Understanding at Scale

Beginner

Matteo Nulli, Vladimir Orshulevich et al.Feb 12arXiv

This paper shows a simple, repeatable way to teach general Vision-Language Models (VLMs) to understand e-commerce items much better without forgetting their general skills.

#Vision-Language Models#E-commerce adaptation#Attribute extraction

Thinking with Drafting: Optical Decompression via Logical Reconstruction

Beginner

Jingxuan Wei, Honghao He et al.Feb 12arXiv

The paper fixes a common problem in AI: models can read pictures and text well, but they often mess up the logic behind them.

#Thinking with Drafting#optical decompression#visual algebra

AdaptMMBench: Benchmarking Adaptive Multimodal Reasoning for Mode Selection and Reasoning Process

Intermediate

Xintong Zhang, Xiaowen Zhang et al.Feb 2arXiv

AdaptMMBench is a new test that checks if AI models know when to just look and think, and when to use extra visual tools like zooming or brightening an image.

#Adaptive Multimodal Reasoning#Vision-Language Models#Tool Invocation

Kimi K2.5: Visual Agentic Intelligence

Beginner

Kimi Team, Tongtong Bai et al.Feb 2arXiv

Kimi K2.5 is a new open-source AI that can read both text and visuals (images and videos) and act like a team of helpers to finish big tasks faster.

#multimodal learning#vision-language models#joint optimization

AdaReasoner: Dynamic Tool Orchestration for Iterative Visual Reasoning

Intermediate

Mingyang Song, Haoyu Sun et al.Jan 26arXiv

AdaReasoner teaches AI to pick the right visual tools, use them in the right order, and stop using them when they aren’t helping.

#AdaReasoner#dynamic tool orchestration#multimodal large language models

VTCBench: Can Vision-Language Models Understand Long Context with Vision-Text Compression?

Intermediate

Hongbo Zhao, Meng Wang et al.Dec 17arXiv

Long texts are expensive for AI to read because each extra token costs a lot of compute and memory.

#vision‑text compression#VTCBench#vision‑language models

Thinking with Images via Self-Calling Agent

Intermediate

Wenxi Yang, Yuzhong Zhao et al.Dec 9arXiv

This paper teaches a vision-language model to think about images by talking to copies of itself, using only words to plan and decide.

#Self-Calling Chain-of-Thought#sCoT#interleaved multimodal chain-of-thought