Papers11

#Qwen2.5-VL

Enhancing Multi-Image Understanding through Delimiter Token Scaling

Minyoung Lee, Yeji Park et al.Feb 2arXiv

Large Vision-Language Models (LVLMs) are great with one picture but get confused when you give them several, often mixing details from different images.

#Large Vision-Language Models#Multi-image understanding#Delimiter tokens

HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding

Intermediate

Haowei Zhang, Shudong Yang et al.Jan 21arXiv

HERMES is a training-free way to make video-language models understand live, streaming video quickly and accurately.

#HERMES#KV cache#hierarchical memory

FantasyVLN: Unified Multimodal Chain-of-Thought Reasoning for Vision-Language Navigation

Intermediate

Jing Zuo, Lingzhou Mu et al.Jan 20arXiv

FantasyVLN teaches a robot to follow language instructions while looking around, using a smart, step-by-step thinking style during training but not at test time.

#Vision-and-Language Navigation#Chain-of-Thought#Multimodal CoT

FocusUI: Efficient UI Grounding via Position-Preserving Visual Token Selection

Intermediate

Mingyu Ouyang, Kevin Qinghong Lin et al.Jan 7arXiv

FOCUSUI makes computer-using AI faster and still accurate by looking only at the important parts of a screen.

#UI grounding#vision-language models#visual token pruning

CPPO: Contrastive Perception for Vision Language Policy Optimization

Intermediate

Ahmad Rezaei, Mohsen Gholami et al.Jan 1arXiv

CPPO is a new way to fine‑tune vision‑language models so they see pictures more accurately before they start to reason.

#CPPO#Contrastive Perception Loss#Vision-Language Models

SemanticGen: Video Generation in Semantic Space

Intermediate

Jianhong Bai, Xiaoshi Wu et al.Dec 23arXiv

SemanticGen is a new way to make videos that starts by planning in a small, high-level 'idea space' (semantic space) and then adds the tiny visual details later.

#Video generation#Diffusion model#Semantic representation

DiffusionVL: Translating Any Autoregressive Models into Diffusion Vision Language Models

Intermediate

Lunbin Zeng, Jingfeng Yao et al.Dec 17arXiv

This paper shows a simple way to turn any strong autoregressive (step-by-step) model into a diffusion vision-language model (parallel, block-by-block) without changing the architecture.

#DiffusionVL#diffusion vision-language model#block diffusion

Zoom-Zero: Reinforced Coarse-to-Fine Video Understanding via Temporal Zoom-in

Intermediate

Xiaoqian Shen, Min-Hung Chen et al.Dec 16arXiv

Zoom-Zero helps AI answer questions about videos by first finding the right moment and then zooming in to double-check tiny details.

#Grounded Video Question Answering#Temporal Grounding#Coarse-to-Fine

Are We Ready for RL in Text-to-3D Generation? A Progressive Investigation

Intermediate

Yiwen Tang, Zoey Guo et al.Dec 11arXiv

This paper asks whether reinforcement learning (RL) can improve making 3D models from text and shows that the answer is yes if we design the training and rewards carefully.

#Reinforcement Learning#Text-to-3D Generation#Hi-GRPO

Rethinking Chain-of-Thought Reasoning for Videos

Intermediate

Yiwu Zhong, Zi-Yuan Hu et al.Dec 10arXiv

The paper shows that video AIs do not need long, human-like chains of thought to reason well.

#video reasoning#chain-of-thought#concise reasoning

LongCat-Image Technical Report

Intermediate

Meituan LongCat Team, Hanghang Ma et al.Dec 8arXiv

LongCat-Image is a small (6B) but mighty bilingual image generator that turns text into high-quality, realistic pictures and can also edit images very well.

#LongCat-Image#diffusion model#text-to-image