Papers23

#vision-language models

Few Tokens Matter: Entropy Guided Attacks on Vision-Language Models

The paper shows that when vision-language models write captions, only a small set of uncertain words (about 20%) act like forks that steer the whole sentence.

#vision-language models#autoregressive generation#entropy

LongVideoAgent: Multi-Agent Reasoning with Long Videos

Intermediate

Runtao Liu, Ziyi Liu et al.Dec 23arXiv

LongVideoAgent is a team of three AIs that work together to answer questions about hour‑long TV episodes without missing small details.

#long video question answering#multi-agent reasoning#temporal grounding

Learning to Reason in 4D: Dynamic Spatial Understanding for Vision Language Models

Intermediate

Shengchao Zhou, Yuxin Chen et al.Dec 23arXiv

The paper tackles a big blind spot in vision-language models: understanding how objects move and relate in 3D over time (dynamic spatial reasoning, or DSR).

#dynamic spatial reasoning#vision-language models#4D understanding

Masking Teacher and Reinforcing Student for Distilling Vision-Language Models

Intermediate

Byung-Kwan Lee, Yu-Chiang Frank Wang et al.Dec 23arXiv

Big vision-language models are super smart but too large to fit on phones and small devices.

#vision-language models#knowledge distillation#masking teacher

Reasoning Palette: Modulating Reasoning via Latent Contextualization for Controllable Exploration for (V)LMs

Intermediate

Rujiao Long, Yang Li et al.Dec 19arXiv

Reasoning Palette gives a language or vision-language model a tiny hidden “mood” (a latent code) before it starts answering, so it chooses a smarter plan rather than just rolling dice on each next word.

#Reasoning Palette#latent contextualization#VAE

N3D-VLM: Native 3D Grounding Enables Accurate Spatial Reasoning in Vision-Language Models

Intermediate

Yuxin Wang, Lei Ke et al.Dec 18arXiv

This paper teaches a vision-language model to first find objects in real 3D space (not just 2D pictures) and then reason about where things are.

#3D grounding#vision-language models#spatial reasoning

Puzzle Curriculum GRPO for Vision-Centric Reasoning

Intermediate

Ahmadreza Jeddi, Hakki Can Karaimer et al.Dec 16arXiv

This paper teaches vision-language models to reason about pictures using puzzles instead of expensive human labels.

#vision-language models#reinforcement learning#group-relative policy optimization

A4-Agent: An Agentic Framework for Zero-Shot Affordance Reasoning

Intermediate

Zixin Zhang, Kanghao Chen et al.Dec 16arXiv

This paper builds A4-Agent, a smart three-part helper that figures out where to touch or use an object just from a picture and a written instruction, without any extra training.

#affordance prediction#zero-shot learning#vision-language models

FoundationMotion: Auto-Labeling and Reasoning about Spatial Movement in Videos

Intermediate

Yulu Gan, Ligeng Zhu et al.Dec 11arXiv

FoundationMotion is a fully automatic pipeline that turns raw videos into detailed motion data, captions, and quizzes about how things move.

#motion understanding#spatio-temporal reasoning#video question answering

From Macro to Micro: Benchmarking Microscopic Spatial Intelligence on Molecules via Vision-Language Models

Intermediate

Zongzhao Li, Xiangzhe Kong et al.Dec 11arXiv

The paper defines Microscopic Spatial Intelligence (MiSI) as the skill AI needs to understand tiny 3D things like molecules from 2D pictures and text, just like scientists do.

#microscopic spatial intelligence#vision-language models#orthographic projection

M3DR: Towards Universal Multilingual Multimodal Document Retrieval

Intermediate

Adithya S Kolavi, Vyoman JainDec 3arXiv

The paper introduces M3DR, a way for computers to find the right document image no matter which of 22 languages the query or the document uses.

#multilingual retrieval#multimodal retrieval#document image search

1 2