Can MLLMs "Read" What is Missing?

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Guo, Jindi, Huang, Chaozheng, Fang, Xi
Format:	Preprint
Publié:	2026
Sujets:	Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Can MLLMs Absorb Math Reasoning Abilities from LLMs as Free Lunch?
par: Hu, Yijie, et autres
Publié: (2025)

VidComposition: Can MLLMs Analyze Compositions in Compiled Videos?
par: Tang, Yolo Y., et autres
Publié: (2024)

Taming a Retrieval Framework to Read Images in Humanlike Manner for Augmenting Generation of MLLMs
par: Xi, Suyang, et autres
Publié: (2025)

Can the Recovery Mechanism Survive AI? Skill Formation, Labor, and What Current Measurement Misses
par: Fan, Aysa Xuemo
Publié: (2026)

OmniScience: A Large-scale Multi-modal Dataset for Scientific Image Understanding
par: Tao, Haoyi, et autres
Publié: (2026)

Can MLLMs Understand the Deep Implication Behind Chinese Images?
par: Zhang, Chenhao, et autres
Publié: (2024)

Can MLLMs generate human-like feedback in grading multimodal short answers?
par: Sil, Pritam, et autres
Publié: (2024)

Can MLLMs Read Students' Minds? Unpacking Multimodal Error Analysis in Handwritten Math
par: Song, Dingjie, et autres
Publié: (2026)

Affordance Benchmark for MLLMs
par: Wang, Junying, et autres
Publié: (2025)

Redundancy Principles for MLLMs Benchmarks
par: Zhang, Zicheng, et autres
Publié: (2025)

UMoE: Unifying Attention and FFN with Shared Experts
par: Yang, Yuanhang, et autres
Publié: (2025)

GeoGS-CE: Learning Delay--Beam Channel Priors with 3D Gaussians for High-Mobility Scenarios
par: Zhang, Yumeng, et autres
Publié: (2026)

Perception or Prejudice: Can MLLMs Go Beyond First Impressions of Personality?
par: Kang, Caixin, et autres
Publié: (2026)

MLLMs are Deeply Affected by Modality Bias
par: Zheng, Xu, et autres
Publié: (2025)

VAP-Diffusion: Enriching Descriptions with MLLMs for Enhanced Medical Image Generation
par: Huang, Peng, et autres
Publié: (2025)

ChartPoint: Guiding MLLMs with Grounding Reflection for Chart Reasoning
par: Xu, Zhengzhuo, et autres
Publié: (2025)

What Is Missing: Interpretable Ratings for Large Language Model Outputs
par: Stranges, Nicholas, et autres
Publié: (2026)

Anthropomimetic Uncertainty: What Verbalized Uncertainty in Language Models is Missing
par: Ulmer, Dennis, et autres
Publié: (2025)

MirrorBench: Evaluating Self-centric Intelligence in MLLMs by Introducing a Mirror
par: Guo, Shengyu, et autres
Publié: (2026)

CodeCrash: Exposing LLM Fragility to Misleading Natural Language in Code Reasoning
par: Lam, Man Ho, et autres
Publié: (2025)

From Specific-MLLMs to Omni-MLLMs: A Survey on MLLMs Aligned with Multi-modalities
par: Jiang, Shixin, et autres
Publié: (2024)

Round-Trip Translation Reveals What Frontier Multilingual Benchmarks Miss
par: Skorobogat, Ronald, et autres
Publié: (2026)

COPO: Causal-Oriented Policy Optimization for Hallucinations of MLLMs
par: Guo, Peizheng, et autres
Publié: (2025)

Multi-Path Collaborative Reasoning via Reinforcement Learning
par: Lv, Jindi, et autres
Publié: (2025)

Scaling Spatial Reasoning in MLLMs through Programmatic Data Synthesis
par: Helu, Zhi, et autres
Publié: (2025)

RxnBench: A Multimodal Benchmark for Evaluating Large Language Models on Chemical Reaction Understanding from Scientific Literature
par: Li, Hanzheng, et autres
Publié: (2025)

MLLMs Know When Before Speaking: Revealing and Recovering Temporal Grounding via Attention Cues
par: Du, Dazhao, et autres
Publié: (2026)

Not Search, But Scan: Benchmarking MLLMs on Scan-Oriented Academic Paper Reasoning
par: Li, Rongjin, et autres
Publié: (2026)

Towards Faithful Reasoning in Comics for Small MLLMs
par: Feng, Chengcheng, et autres
Publié: (2026)

How Clinicians Think and What AI Can Learn From It
par: Sengupta, Dipayan, et autres
Publié: (2026)

Diffusion-CAM: Faithful Visual Explanations for dMLLMs
par: Zuo, Haomin, et autres
Publié: (2026)

FairReason: Balancing Reasoning and Social Bias in MLLMs
par: Pan, Zhenyu, et autres
Publié: (2025)

Can MLLMs Detect Phishing? A Comprehensive Security Benchmark Suite Focusing on Dynamic Threats and Multimodal Evaluation in Academic Environments
par: Zhou, Jingzhuo
Publié: (2025)

Towards Unified Surgical Scene Understanding:Bridging Reasoning and Grounding via MLLMs
par: Huang, Jincai, et autres
Publié: (2026)

Thinking Ahead: Foresight Intelligence in MLLMs and World Models
par: Gong, Zhantao, et autres
Publié: (2025)

WARBENCH: A Comprehensive Benchmark for Evaluating LLMs in Military Decision-Making
par: Li, Zongjie, et autres
Publié: (2026)

Conceal, Reconstruct, Jailbreak: Exploiting the Reconstruction-Concealment Tradeoff in MLLMs
par: Reza, Md Farhamdur, et autres
Publié: (2026)

Same Content, Different Answers: Cross-Modal Inconsistency in MLLMs
par: van Sprang, Angela, et autres
Publié: (2025)

Dense Connector for MLLMs
par: Yao, Huanjin, et autres
Publié: (2024)

What Single-Prompt Accuracy Misses: A Multi-Variant Reliability Audit of Language Models
par: Karmakar, Ranit, et autres
Publié: (2026)

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	"fr"
VUFIND_SESSION	"c046ea49ecb9f06d05e24a94f8b49925"
ui	"standard"

Session

Key	Value
__Laminas	array:2 [`"_REQUEST_ACCESS_TIME" => 1790987153.2949 "_VALID" => array:1 [ "Laminas\Session\Validator\Id" => "c046ea49ecb9f06d05e24a94f8b49925" ]`]
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=fr; VUFIND_SESSION=c046ea49ecb9f06d05e24a94f8b49925; 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	"60641"
REDIRECT_URL	""" /Record/\n arxiv_https___arxiv_org_abs_2604_21277/Similar """
GATEWAY_INTERFACE	"CGI/1.1"
SERVER_PROTOCOL	"HTTP/1.1"
REQUEST_METHOD	"GET"
QUERY_STRING	""
REQUEST_URI	"/Record/%0Aarxiv_https___arxiv_org_abs_2604_21277/Similar"
SCRIPT_NAME	"/index.php"
PHP_SELF	"/index.php"
REQUEST_TIME_FLOAT	1790987153.2904
REQUEST_TIME	1790987153

Environment Variables empty

Registered Handlers

0. Whoops\Handler\PrettyPageHandler