From Concrete to Abstract: A Multimodal Generative Approach to Abstract Concept Learning

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Xie, Haodong, Maharjan, Rahul Singh, Tavella, Federico, Cangelosi, Angelo
Format:	Preprint
Veröffentlicht:	2024
Schlagworte:	Computation and Language Artificial Intelligence
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

Hierarchical, Interpretable, Label-Free Concept Bottleneck Model
von: Xie, Haodong, et al.
Veröffentlicht: (2026)

Phonology Recognition in American Sign Language
von: Tavella, Federico, et al.
Veröffentlicht: (2021)

Fake or Real, Can Robots Tell? Evaluating VLM Robustness to Domain Shift in Single-View Robotic Scene Understanding
von: Tavella, Federico, et al.
Veröffentlicht: (2025)

Attributes-aware Visual Emotion Representation Learning
von: Maharjan, Rahul Singh, et al.
Veröffentlicht: (2025)

Bridging the Communication Gap: Artificial Agents Learning Sign Language through Imitation
von: Tavella, Federico, et al.
Veröffentlicht: (2024)

Building, Reusing, and Generalizing Abstract Representations from Concrete Sequences
von: Wu, Shuchen, et al.
Veröffentlicht: (2024)

Signs of Language: Embodied Sign Language Fingerspelling Acquisition from Demonstrations for Human-Robot Interaction
von: Tavella, Federico, et al.
Veröffentlicht: (2022)

Noise-Free Explanation for Driving Action Prediction
von: Zhu, Hongbo, et al.
Veröffentlicht: (2024)

Joint Action Language Modelling for Transparent Policy Execution
von: Wulff, Theodor, et al.
Veröffentlicht: (2025)

The Grounding Gap: How LLMs Anchor the Meaning of Abstract Concepts Differently from Humans
von: Chlapanis, Odysseas S., et al.
Veröffentlicht: (2026)

MedConclusion: A Benchmark for Biomedical Conclusion Generation from Structured Abstracts
von: Li, Weiyue, et al.
Veröffentlicht: (2026)

Meaningful Learning: Enhancing Abstract Reasoning in Large Language Models via Generic Fact Guidance
von: Xiong, Kai, et al.
Veröffentlicht: (2024)

SWAN: Semantic Watermarking with Abstract Meaning Representation
von: Ye, Ziping, et al.
Veröffentlicht: (2026)

Acquiring and Modelling Abstract Commonsense Knowledge via Conceptualization
von: He, Mutian, et al.
Veröffentlicht: (2022)

Learning to Plan Before Answering: Self-Teaching LLMs to Learn Abstract Plans for Problem Solving
von: Zhang, Jin, et al.
Veröffentlicht: (2025)

On Data Synthesis and Post-training for Visual Abstract Reasoning
von: Zhu, Ke, et al.
Veröffentlicht: (2025)

AnaloBench: Benchmarking the Identification of Abstract and Long-context Analogies
von: Ye, Xiao, et al.
Veröffentlicht: (2024)

LLMs Struggle with Abstract Meaning Comprehension More Than Expected
von: Alhazmi, Hamoud, et al.
Veröffentlicht: (2026)

Combining Induction and Transduction for Abstract Reasoning
von: Li, Wen-Ding, et al.
Veröffentlicht: (2024)

Large Language Models for Automated Literature Review: An Evaluation of Reference Generation, Abstract Writing, and Review Composition
von: Tang, Xuemei, et al.
Veröffentlicht: (2024)

The Emergence of Abstract Thought in Large Language Models Beyond Any Language
von: Chen, Yuxin, et al.
Veröffentlicht: (2025)

Evaluating Large Language Models for Abstract Evaluation Tasks: An Empirical Study
von: Liu, Yinuo, et al.
Veröffentlicht: (2026)

Emergent Symbolic Mechanisms Support Abstract Reasoning in Large Language Models
von: Yang, Yukang, et al.
Veröffentlicht: (2025)

Abstract Activation Spaces for Content-Invariant Reasoning in Large Language Models
von: Maraia, Gabriele, et al.
Veröffentlicht: (2026)

Bridge-RAG: An Abstract Bridge Tree Based Retrieval Augmented Generation Algorithm
von: Li, Zihang, et al.
Veröffentlicht: (2026)

ABEX: Data Augmentation for Low-Resource NLU via Expanding Abstract Descriptions
von: Ghosh, Sreyan, et al.
Veröffentlicht: (2024)

Abstract2Appendix: Academic Reviews Enhance LLM Long-Context Capabilities
von: Li, Shengzhi, et al.
Veröffentlicht: (2024)

Inclusivity in Large Language Models: Personality Traits and Gender Bias in Scientific Abstracts
von: Pervez, Naseela, et al.
Veröffentlicht: (2024)

WLASL-LEX: a Dataset for Recognising Phonological Properties in American Sign Language
von: Tavella, Federico, et al.
Veröffentlicht: (2022)

AI-Facilitated Analysis of Abstracts and Conclusions: Flagging Unsubstantiated Claims and Ambiguous Pronouns
von: Markhasin, Evgeny
Veröffentlicht: (2025)

Abstract Meaning Representation-Based Logic-Driven Data Augmentation for Logical Reasoning
von: Bao, Qiming, et al.
Veröffentlicht: (2023)

Do AI Models Perform Human-like Abstract Reasoning Across Modalities?
von: Beger, Claas, et al.
Veröffentlicht: (2025)

What is an "Abstract Reasoner"? Revisiting Experiments and Arguments about Large Language Models
von: Yun, Tian, et al.
Veröffentlicht: (2025)

Navigating Semantic Relations: Challenges for Language Models in Abstract Common-Sense Reasoning
von: Gawin, Cole, et al.
Veröffentlicht: (2025)

AR$^2$: Adversarial Reinforcement Learning for Abstract Reasoning in Large Language Models
von: Yeh, Cheng-Kai, et al.
Veröffentlicht: (2025)

AbstRaL: Augmenting LLMs' Reasoning by Reinforcing Abstract Thinking
von: Gao, Silin, et al.
Veröffentlicht: (2025)

Simplifying Scholarly Abstracts for Accessible Digital Libraries
von: Wang, Haining, et al.
Veröffentlicht: (2024)

Grounding Hierarchical Vision-Language-Action Models Through Explicit Language-Action Alignment
von: Wulff, Theodor, et al.
Veröffentlicht: (2026)

Investigating Large Language Models and Control Mechanisms to Improve Text Readability of Biomedical Abstracts
von: Li, Zihao, et al.
Veröffentlicht: (2023)

CausalARC: Abstract Reasoning with Causal World Models
von: Maasch, Jacqueline, et al.
Veröffentlicht: (2025)

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"
ui	"standard"
VUFIND_SESSION	"bb900e19343dae92211ea248981b777e"

Session

Key	Value
__Laminas	array:2 [`"_REQUEST_ACCESS_TIME" => 1790870985.2615 "_VALID" => array:1 [ "Laminas\Session\Validator\Id" => "bb900e19343dae92211ea248981b777e" ]`]
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; ui=standard; VUFIND_SESSION=bb900e19343dae92211ea248981b777e"
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	"216.73.216.147"
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	"36886"
REDIRECT_URL	""" /Record/\n arxiv_https___arxiv_org_abs_2410_02365/Similar """
GATEWAY_INTERFACE	"CGI/1.1"
SERVER_PROTOCOL	"HTTP/1.1"
REQUEST_METHOD	"GET"
QUERY_STRING	""
REQUEST_URI	"/Record/%0Aarxiv_https___arxiv_org_abs_2410_02365/Similar"
SCRIPT_NAME	"/index.php"
PHP_SELF	"/index.php"
REQUEST_TIME_FLOAT	1790870985.2536
REQUEST_TIME	1790870985

Environment Variables empty

Registered Handlers

0. Whoops\Handler\PrettyPageHandler