Papers1055

Qwen-Image-Layered: Towards Inherent Editability via Layer Decomposition

Shengming Yin, Zekai Zhang et al.Dec 17arXiv

The paper turns one flat picture into a neat stack of see‑through layers, so you can edit one thing without messing up the rest.

#image decomposition#RGBA layers#alpha blending

Not triaged yet

GRAN-TED: Generating Robust, Aligned, and Nuanced Text Embedding for Diffusion Models

Intermediate

Bozhou Li, Sihan Yang et al.Dec 17arXiv

This paper is about making the words you type into a generator turn into the right pictures and videos more reliably.

#diffusion models#text encoder#multimodal large language model

Not triaged yet

Nemotron-Math: Efficient Long-Context Distillation of Mathematical Reasoning from Multi-Mode Supervision

Intermediate

Wei Du, Shubham Toshniwal et al.Dec 17arXiv

Nemotron-Math is a giant math dataset with 7.5 million step-by-step solutions created in three thinking styles and with or without Python help.

#mathematical reasoning#long-context fine-tuning#multi-mode supervision

Not triaged yet

Step-GUI Technical Report

Intermediate

Haolong Yan, Jia Wang et al.Dec 17arXiv

This paper builds Step-GUI, a pair of small-but-strong GUI agent models (4B/8B) that can use phones and computers by looking at screenshots and following instructions.

#GUI automation#multimodal large language models#trajectory-level calibration

Not triaged yet

Robust and Calibrated Detection of Authentic Multimedia Content

Intermediate

Sarim Hashmi, Abdelrahman Elsayed et al.Dec 17arXiv

Deepfakes are getting so good that simple yes/no detectors are failing, especially when attackers add tiny, invisible changes.

#Authenticity Index#calibrated resynthesis#reconstruction-free inversion

Not triaged yet

DEER: Draft with Diffusion, Verify with Autoregressive Models

Intermediate

Zicong Cheng, Guo-Wei Yang et al.Dec 17arXiv

DEER is a new way to speed up big language models by letting a diffusion model draft many tokens at once and an autoregressive model double-check them.

#DEER#speculative decoding#diffusion LLM

Not triaged yet

Is Nano Banana Pro a Low-Level Vision All-Rounder? A Comprehensive Evaluation on 14 Tasks and 40 Datasets

Intermediate

Jialong Zuo, Haoyou Deng et al.Dec 17arXiv

This paper checks if a popular text-to-image model called Nano Banana Pro can fix messy photos without any extra training.

#low-level vision#zero-shot restoration#generative models

Not triaged yet

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

Not triaged yet

MemFlow: Flowing Adaptive Memory for Consistent and Efficient Long Video Narratives

Intermediate

Sihui Ji, Xi Chen et al.Dec 16arXiv

MemFlow is a new way for AI to remember the right parts of a long video story while it keeps making new parts, so characters and scenes stay consistent.

#MemFlow#Narrative Adaptive Memory#Sparse Memory Activation

Not triaged yet

TimeLens: Rethinking Video Temporal Grounding with Multimodal LLMs

Intermediate

Jun Zhang, Teng Wang et al.Dec 16arXiv

TimeLens studies how to teach AI not just what happens in a video, but exactly when it happens, which is called video temporal grounding (VTG).

#video temporal grounding#multimodal large language models#benchmark re-annotation

Not triaged yet

Spherical Leech Quantization for Visual Tokenization and Generation

Intermediate

Yue Zhao, Hanwen Jiang et al.Dec 16arXiv

This paper shows a simple, math-guided way to turn image pieces into tidy symbols (tokens) using points spread evenly on a sphere.

#Spherical Leech Quantization#Leech lattice#spherical codes

Not triaged yet

CRISP: Contact-Guided Real2Sim from Monocular Video with Planar Scene Primitives

Intermediate

Zihan Wang, Jiashun Wang et al.Dec 16arXiv

CRISP turns a normal phone video of a person into a clean 3D world and a virtual human that can move in it without breaking physics.

#real-to-sim#human-scene interaction#planar primitives

Not triaged yet

74 75 76 77 78