ConvLLaVA: Hierarchical Backbones as Visual Encoder for Large Multimodal Models

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Ge, Chunjiang, Cheng, Sijie, Wang, Ziming, Yuan, Jiale, Gao, Yuan, Song, Jun, Song, Shiji, Huang, Gao, Zheng, Bo
Format:	Preprint
Veröffentlicht:	2024
Schlagworte:	Computer Vision and Pattern Recognition
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

EfficientTrain++: Generalized Curriculum Learning for Efficient Visual Backbone Training
von: Wang, Yulin, et al.
Veröffentlicht: (2024)

LLaVA-UHD: an LMM Perceiving Any Aspect Ratio and High-Resolution Images
von: Xu, Ruyi, et al.
Veröffentlicht: (2024)

Demystify Mamba in Vision: A Linear Attention Perspective
von: Han, Dongchen, et al.
Veröffentlicht: (2024)

Cross-Modal Adapter for Vision-Language Retrieval
von: Jiang, Haojun, et al.
Veröffentlicht: (2022)

LLaVA-UHD v2: an MLLM Integrating High-Resolution Semantic Pyramid via Hierarchical Window Transformer
von: Zhang, Yipeng, et al.
Veröffentlicht: (2024)

Probabilistic Contrastive Learning for Long-Tailed Visual Recognition
von: Du, Chaoqun, et al.
Veröffentlicht: (2024)

GSVA: Generalized Segmentation via Multimodal Large Language Models
von: Xia, Zhuofan, et al.
Veröffentlicht: (2023)

PerturboLLaVA: Reducing Multimodal Hallucinations with Perturbative Visual Training
von: Chen, Cong, et al.
Veröffentlicht: (2025)

LLaVA-MORE: A Comparative Study of LLMs and Visual Backbones for Enhanced Visual Instruction Tuning
von: Cocchi, Federico, et al.
Veröffentlicht: (2025)

VisionLLaMA: A Unified LLaMA Backbone for Vision Tasks
von: Chu, Xiangxiang, et al.
Veröffentlicht: (2024)

LLaVA-ST: A Multimodal Large Language Model for Fine-Grained Spatial-Temporal Understanding
von: Li, Hongyu, et al.
Veröffentlicht: (2025)

Everything to the Synthetic: Diffusion-driven Test-time Adaptation via Synthetic-Domain Alignment
von: Guo, Jiayi, et al.
Veröffentlicht: (2024)

AVG-LLaVA: An Efficient Large Multimodal Model with Adaptive Visual Granularity
von: Lan, Zhibin, et al.
Veröffentlicht: (2024)

LLaVA-FA: Learning Fourier Approximation for Compressing Large Multimodal Models
von: Zheng, Pengcheng, et al.
Veröffentlicht: (2026)

LLaVA-OneVision-2: Towards Next-Generation Perceptual Intelligence
von: An, Xiang, et al.
Veröffentlicht: (2026)

iLLaVA: An Image is Worth Fewer Than 1/3 Input Tokens in Large Multimodal Models
von: Hu, Lianyu, et al.
Veröffentlicht: (2024)

SZTU-CMU at MER2024: Improving Emotion-LLaMA with Conv-Attention for Multimodal Emotion Recognition
von: Cheng, Zebang, et al.
Veröffentlicht: (2024)

WSI-LLaVA: A Multimodal Large Language Model for Whole Slide Image
von: Liang, Yuci, et al.
Veröffentlicht: (2024)

Wiki-LLaVA: Hierarchical Retrieval-Augmented Generation for Multimodal LLMs
von: Caffagni, Davide, et al.
Veröffentlicht: (2024)

LLaVA-CoT: Let Vision Language Models Reason Step-by-Step
von: Xu, Guowei, et al.
Veröffentlicht: (2024)

VA-Adapter: Adapting Ultrasound Foundation Model to Echocardiography Probe Guidance
von: Wang, Teng, et al.
Veröffentlicht: (2025)

Agri-LLaVA: Knowledge-Infused Large Multimodal Assistant on Agricultural Pests and Diseases
von: Wang, Liqiong, et al.
Veröffentlicht: (2024)

LLaVA-UHD v3: Progressive Visual Compression for Efficient Native-Resolution Encoding in MLLMs
von: Sun, Shichu, et al.
Veröffentlicht: (2025)

Video-LLaVA: Learning United Visual Representation by Alignment Before Projection
von: Lin, Bin, et al.
Veröffentlicht: (2023)

Robust-LLaVA: On the Effectiveness of Large-Scale Robust Image Encoders for Multi-modal Large Language Models
von: Malik, Hashmat Shadab, et al.
Veröffentlicht: (2025)

FocusLLaVA: A Coarse-to-Fine Approach for Efficient and Effective Visual Token Compression
von: Zhu, Yuke, et al.
Veröffentlicht: (2024)

HyperLLaVA: Dynamic Visual and Language Expert Tuning for Multimodal Large Language Models
von: Zhang, Wenqiao, et al.
Veröffentlicht: (2024)

LLaVA-c: Continual Improved Visual Instruction Tuning
von: Liu, Wenzhuo, et al.
Veröffentlicht: (2025)

LLaVA-RadZ: Can Multimodal Large Language Models Effectively Tackle Zero-shot Radiology Recognition?
von: Li, Bangyan, et al.
Veröffentlicht: (2025)

LLaVA-SLT: Visual Language Tuning for Sign Language Translation
von: Liang, Han, et al.
Veröffentlicht: (2024)

LLaVA-UHD v4: What Makes Efficient Visual Encoding in MLLMs?
von: Fang, Kechen, et al.
Veröffentlicht: (2026)

LLaVA-Critic: Learning to Evaluate Multimodal Models
von: Xiong, Tianyi, et al.
Veröffentlicht: (2024)

MoE-LLaVA: Mixture of Experts for Large Vision-Language Models
von: Lin, Bin, et al.
Veröffentlicht: (2024)

ViP-LLaVA: Making Large Multimodal Models Understand Arbitrary Visual Prompts
von: Cai, Mu, et al.
Veröffentlicht: (2023)

Cosmos-LLaVA: Chatting with the Visual Cosmos-LLaVA: Görselle Sohbet Etmek
von: Zeer, Ahmed, et al.
Veröffentlicht: (2024)

Beyond LLaVA-HD: Diving into High-Resolution Large Multimodal Models
von: Zhang, Yi-Fan, et al.
Veröffentlicht: (2024)

LLaVA-KD: A Framework of Distilling Multimodal Large Language Models
von: Cai, Yuxuan, et al.
Veröffentlicht: (2024)

NOVO: Bridging LLaVA and SAM with Visual-only Prompts for Reasoning Segmentation
von: Yoon, Kyung-Yoon, et al.
Veröffentlicht: (2025)

Meta-Semi: A Meta-learning Approach for Semi-supervised Learning
von: Wang, Yulin, et al.
Veröffentlicht: (2020)

UniRepLKNet: A Universal Perception Large-Kernel ConvNet for Audio, Video, Point Cloud, Time-Series and Image Recognition
von: Ding, Xiaohan, et al.
Veröffentlicht: (2023)

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
language	"de"
VUFIND_SESSION	"a57ee538bd6831b526703d4b3ba40c0c"
ui	"standard"

Session

Key	Value
__Laminas	array:2 [`"_REQUEST_ACCESS_TIME" => 1790896973.9121 "_VALID" => array:1 [ "Laminas\Session\Validator\Id" => "a57ee538bd6831b526703d4b3ba40c0c" ]`]
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	"language=de; VUFIND_SESSION=a57ee538bd6831b526703d4b3ba40c0c; ui=standard"
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	"51716"
REDIRECT_URL	""" /Record/\n arxiv_https___arxiv_org_abs_2405_15738/Similar """
GATEWAY_INTERFACE	"CGI/1.1"
SERVER_PROTOCOL	"HTTP/1.1"
REQUEST_METHOD	"GET"
QUERY_STRING	""
REQUEST_URI	"/Record/%0Aarxiv_https___arxiv_org_abs_2405_15738/Similar"
SCRIPT_NAME	"/index.php"
PHP_SELF	"/index.php"
REQUEST_TIME_FLOAT	1790896973.9075
REQUEST_TIME	1790896973

Environment Variables empty

Registered Handlers

0. Whoops\Handler\PrettyPageHandler