Docopilot: Improving Multimodal Models for Document-Level Understanding

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Duan, Yuchen, Chen, Zhe, Hu, Yusong, Wang, Weiyun, Ye, Shenglong, Shi, Botian, Lu, Lewei, Hou, Qibin, Lu, Tong, Li, Hongsheng, Dai, Jifeng, Wang, Wenhai
Formato:	Preprint
Publicado:	2025
Materias:	Computer Vision and Pattern Recognition Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Vision-RWKV: Efficient and Scalable Visual Perception with RWKV-Like Architectures
por: Duan, Yuchen, et al.
Publicado: (2024)

VisualPRM: An Effective Process Reward Model for Multimodal Reasoning
por: Wang, Weiyun, et al.
Publicado: (2025)

Mini-InternVL: A Flexible-Transfer Pocket Multimodal Model with 5% Parameters and 90% Performance
por: Gao, Zhangwei, et al.
Publicado: (2024)

MM-Interleaved: Interleaved Image-Text Generative Modeling via Multi-modal Feature Synchronizer
por: Tian, Changyao, et al.
Publicado: (2024)

Enhancing the Reasoning Ability of Multimodal Large Language Models via Mixed Preference Optimization
por: Wang, Weiyun, et al.
Publicado: (2024)

MMInstruct: A High-Quality Multi-Modal Instruction Tuning Dataset with Extensive Diversity
por: Liu, Yangzhou, et al.
Publicado: (2024)

Needle In A Multimodal Haystack
por: Wang, Weiyun, et al.
Publicado: (2024)

Visual Embodied Brain: Let Multimodal Large Language Models See, Think, and Control in Spaces
por: Luo, Gen, et al.
Publicado: (2025)

The All-Seeing Project V2: Towards General Relation Comprehension of the Open World
por: Wang, Weiyun, et al.
Publicado: (2024)

VisuLogic: A Benchmark for Evaluating Visual Reasoning in Multi-modal Large Language Models
por: Xu, Weiye, et al.
Publicado: (2025)

VisionLLM v2: An End-to-End Generalist Multimodal Large Language Model for Hundreds of Vision-Language Tasks
por: Wu, Jiannan, et al.
Publicado: (2024)

Demystify Transformers & Convolutions in Modern Image Deep Networks
por: Hu, Xiaowei, et al.
Publicado: (2022)

Efficient Deformable ConvNets: Rethinking Dynamic and Sparse Operator for Vision Applications
por: Xiong, Yuwen, et al.
Publicado: (2024)

PVC: Progressive Visual Token Compression for Unified Image and Video Processing in Large Vision-Language Models
por: Yang, Chenyu, et al.
Publicado: (2024)

Parameter-Inverted Image Pyramid Networks for Visual Perception and Multimodal Understanding
por: Wang, Zhaokai, et al.
Publicado: (2025)

MMFuser: Multimodal Multi-Layer Feature Fuser for Fine-Grained Vision-Language Understanding
por: Cao, Yue, et al.
Publicado: (2024)

OmniCorpus: A Unified Multimodal Corpus of 10 Billion-Level Images Interleaved with Text
por: Li, Qingyun, et al.
Publicado: (2024)

NaViL: Rethinking Scaling Properties of Native Multimodal Large Language Models under Data Constraints
por: Tian, Changyao, et al.
Publicado: (2025)

SynerGen-VL: Towards Synergistic Image Understanding and Generation with Vision Experts and Token Folding
por: Li, Hao, et al.
Publicado: (2024)

How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites
por: Chen, Zhe, et al.
Publicado: (2024)

Bounding Box Stability against Feature Dropout Reflects Detector Generalization across Environments
por: Yang, Yang, et al.
Publicado: (2024)

Mono-InternVL-1.5: Towards Cheaper and Faster Monolithic Multimodal Large Language Models
por: Luo, Gen, et al.
Publicado: (2025)

HoVLE: Unleashing the Power of Monolithic Vision-Language Models with Holistic Vision-Language Embedding
por: Tao, Chenxin, et al.
Publicado: (2024)

Auto MC-Reward: Automated Dense Reward Design with Large Language Models for Minecraft
por: Li, Hao, et al.
Publicado: (2023)

DriveMLM: Aligning Multi-Modal Large Language Models with Behavioral Planning States for Autonomous Driving
por: Cui, Erfei, et al.
Publicado: (2023)

Point or Line? Using Line-based Representation for Panoptic Symbol Spotting in CAD Drawings
por: Wei, Xingguang, et al.
Publicado: (2025)

InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks
por: Chen, Zhe, et al.
Publicado: (2023)

Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling
por: Chen, Zhe, et al.
Publicado: (2024)

ADDP: Learning General Representations for Image Recognition and Generation with Alternating Denoising Diffusion Process
por: Tian, Changyao, et al.
Publicado: (2023)

InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models
por: Zhu, Jinguo, et al.
Publicado: (2025)

InternSpatial: A Comprehensive Dataset for Spatial Reasoning in Vision-Language Models
por: Deng, Nianchen, et al.
Publicado: (2025)

Sequential Diffusion Language Models
por: Liu, Yangzhou, et al.
Publicado: (2025)

Vision Model Pre-training on Interleaved Image-Text Data via Latent Compression Learning
por: Yang, Chenyu, et al.
Publicado: (2024)

Multimodal 3D Reasoning Segmentation with Complex Scenes
por: Jiang, Xueying, et al.
Publicado: (2024)

PP-DocBee: Improving Multimodal Document Understanding Through a Bag of Tricks
por: Ni, Feng, et al.
Publicado: (2025)

CoMemo: LVLMs Need Image Context with Image Memory
por: Liu, Shi, et al.
Publicado: (2025)

AnyCap Project: A Unified Framework, Dataset, and Benchmark for Controllable Omni-modal Captioning
por: Ren, Yiming, et al.
Publicado: (2025)

HoloDrive: Holistic 2D-3D Multi-Modal Street Scene Generation for Autonomous Driving
por: Wu, Zehuan, et al.
Publicado: (2024)

EchoInk-R1: Exploring Audio-Visual Reasoning in Multimodal LLMs via Reinforcement Learning
por: Xing, Zhenghao, et al.
Publicado: (2025)

Learning 1D Causal Visual Representation with De-focus Attention Networks
por: Tao, Chenxin, et al.
Publicado: (2024)

if (filemtime($filename) + $maxlifetime < time()) { unlink($filename); $count++; } } return $count; } /** * A function that is called internally when session data is to be saved. * * @param string $sessId The current session ID * @param string $data The session data to write * * @return bool */ protected function saveSession($sessId, $data): bool { $sessFile = $this->path . '/sess_' . $sessId; if ($handle = fopen($sessFile, 'w')) { $return = false; // Lock the file for exclusive access to avoid issues with multiple // processes writing session simultaneously: if (flock($handle, LOCK_EX)) { $return = fwrite($handle, $data); // Make sure that there's no trailing data by truncating the file to // the correct length: ftruncate($handle, strlen($data)); fflush($handle); flock($handle, LOCK_UN); } fclose($handle); if ($return !== false) { return true; } } // If we got this far, something went wrong with the file output... // It is tempting to throw an exception here, but this code is called // outside of the context of exception handling, so all we can do is // echo a message.

// Anecdotal testing Today and Yesterday seems to indicate destroy() // is called by the garbage collector and everything is good. // Something to keep in mind though. return 0; } /** * Write function that is called when session data is to be saved. * * @param string $sessId The current session ID * @param string $data The session data to write * * @return bool */ public function write($sessId, $data): bool { if ($this->writesDisabled) { return true; } return $this->saveSession($sessId, $data); } /** * A function that is called internally when session data is to be saved. * * @param string $sessId The current session ID * @param string $data The session data to write * * @return bool */ abstract protected function saveSession($sessId, $data): bool; }

* * @return void */ public function writeClose() { // The assumption is that we're using PHP's ext/session. // session_write_close() will actually overwrite $_SESSION with an // empty array on completion -- which leads to a mismatch between what // is in the storage object and $_SESSION. To get around this, we // temporarily reset $_SESSION to an array, and then re-link it to // the storage object. // // Additionally, while you _can_ write to $_SESSION following a // session_write_close() operation, no changes made to it will be // flushed to the session handler. As such, we now mark the storage // object isImmutable. $storage = $this->getStorage(); if (! $storage->isImmutable()) { $_SESSION = $storage->toArray(true); session_write_close(); $storage->fromArray($_SESSION); $storage->markImmutable(); } } /** * Attempt to set the session name * * If the session has already been started, or if the name provided fails * validation, an exception will be raised. * * @param string $name * @return SessionManager * @throws Exception\InvalidArgumentException */ public function setName($name) { if ($this->sessionExists()) { throw new Exception\InvalidArgumentException( 'Cannot set session name after a session has already started'

Environment & details:

GET Data empty

POST Data empty

Files empty

Key	Value
ui	"standard"
language	"es"
VUFIND_SESSION	"fd10ab6836619e8e8e3d4ddf681aa9a2"

Session

Key	Value
__Laminas	array:2 [`"_REQUEST_ACCESS_TIME" => 1790963517.2176 "_VALID" => array:1 [ "Laminas\Session\Validator\Id" => "fd10ab6836619e8e8e3d4ddf681aa9a2" ]`]
SessionState	Laminas\Stdlib\ArrayObject {#938}
FlashMessenger	Laminas\Stdlib\ArrayObject {#1433}
SessionHelper	Laminas\Stdlib\ArrayObject {#1759}

Server/Request Data

Key	Value
REDIRECT_VUFIND_LOCAL_DIR	"/usr/local/vufind/local"
REDIRECT_HTTPS	"on"
REDIRECT_SSL_TLS_SNI	"info.umar.mx"
REDIRECT_STATUS	"200"
VUFIND_LOCAL_DIR	"/usr/local/vufind/local"
HTTPS	"on"
SSL_TLS_SNI	"info.umar.mx"
HTTP_ACCEPT	"/"
HTTP_USER_AGENT	"Mozilla/5.0 AppleWebKit/537.36 (KHTML, like Gecko; compatible; ClaudeBot/1.0; +claudebot@anthropic.com)"
HTTP_COOKIE	"ui=standard; language=es; VUFIND_SESSION=fd10ab6836619e8e8e3d4ddf681aa9a2"
HTTP_ACCEPT_ENCODING	"gzip, br, zstd, deflate"
HTTP_HOST	"info.umar.mx"
PATH	"/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/snap/bin"
SERVER_SIGNATURE	"<address>Apache/2.4.66 (Ubuntu) Server at info.umar.mx Port 443</address>\n"
SERVER_SOFTWARE	"Apache/2.4.66 (Ubuntu)"
SERVER_NAME	"info.umar.mx"
SERVER_ADDR	"200.23.222.19"
SERVER_PORT	"443"
REMOTE_ADDR	"216.73.217.142"
DOCUMENT_ROOT	"/usr/local/vufind/public"
REQUEST_SCHEME	"https"
CONTEXT_PREFIX	""
CONTEXT_DOCUMENT_ROOT	"/usr/local/vufind/public"
SERVER_ADMIN	"admin@localhost"
SCRIPT_FILENAME	"/usr/local/vufind/public/index.php"
REMOTE_PORT	"55156"
REDIRECT_URL	""" /Record/\n arxiv_https___arxiv_org_abs_2507_14675/Similar """
GATEWAY_INTERFACE	"CGI/1.1"
SERVER_PROTOCOL	"HTTP/1.1"
REQUEST_METHOD	"GET"
QUERY_STRING	""
REQUEST_URI	"/Record/%0Aarxiv_https___arxiv_org_abs_2507_14675/Similar"
SCRIPT_NAME	"/index.php"
PHP_SELF	"/index.php"
REQUEST_TIME_FLOAT	1790963517.2132
REQUEST_TIME	1790963517

Environment Variables empty

Registered Handlers

0. Whoops\Handler\PrettyPageHandler