@inproceedings{ali-khan-2025-waste,
title = "Waste-Bench: A Comprehensive Benchmark for Evaluating {VLLM}s in Cluttered Environments",
author = "Ali, Muhammad and
Khan, Salman",
editor = "Christodoulopoulos, Christos and
Chakraborty, Tanmoy and
Rose, Carolyn and
Peng, Violet",
booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.emnlp-main.1578/",
doi = "10.18653/v1/2025.emnlp-main.1578",
pages = "31019--31032",
ISBN = "979-8-89176-332-6",
abstract = "Recent advancements in Large Language Models (LLMs) have paved the way for VisionLarge Language Models (VLLMs) capable ofperforming a wide range of visual understand-ing tasks. While LLMs have demonstrated impressive performance on standard naturalimages, their capabilities have not been thoroughly explored in cluttered datasets where there is complex environment having deformedshaped objects. In this work, we introduce a novel dataset specifically designed for waste classification in real-world scenarios, character-ized by complex environments and deformed shaped objects. Along with this dataset, we present an in-depth evaluation approach to rig-orously assess the robustness and accuracy of VLLMs. The introduced dataset and comprehensive analysis provide valuable insights intothe performance of VLLMs under challenging conditions. Our findings highlight the critical need for further advancements in VLLM{'}s ro-bustness to perform better in complex enviroments. The dataset and code for our experiments are available at https://github.com/aliman80/wastebench."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ali-khan-2025-waste">
<titleInfo>
<title>Waste-Bench: A Comprehensive Benchmark for Evaluating VLLMs in Cluttered Environments</title>
</titleInfo>
<name type="personal">
<namePart type="given">Muhammad</namePart>
<namePart type="family">Ali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Salman</namePart>
<namePart type="family">Khan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christos</namePart>
<namePart type="family">Christodoulopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carolyn</namePart>
<namePart type="family">Rose</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Violet</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-332-6</identifier>
</relatedItem>
<abstract>Recent advancements in Large Language Models (LLMs) have paved the way for VisionLarge Language Models (VLLMs) capable ofperforming a wide range of visual understand-ing tasks. While LLMs have demonstrated impressive performance on standard naturalimages, their capabilities have not been thoroughly explored in cluttered datasets where there is complex environment having deformedshaped objects. In this work, we introduce a novel dataset specifically designed for waste classification in real-world scenarios, character-ized by complex environments and deformed shaped objects. Along with this dataset, we present an in-depth evaluation approach to rig-orously assess the robustness and accuracy of VLLMs. The introduced dataset and comprehensive analysis provide valuable insights intothe performance of VLLMs under challenging conditions. Our findings highlight the critical need for further advancements in VLLM’s ro-bustness to perform better in complex enviroments. The dataset and code for our experiments are available at https://github.com/aliman80/wastebench.</abstract>
<identifier type="citekey">ali-khan-2025-waste</identifier>
<identifier type="doi">10.18653/v1/2025.emnlp-main.1578</identifier>
<location>
<url>https://aclanthology.org/2025.emnlp-main.1578/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>31019</start>
<end>31032</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Waste-Bench: A Comprehensive Benchmark for Evaluating VLLMs in Cluttered Environments
%A Ali, Muhammad
%A Khan, Salman
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-332-6
%F ali-khan-2025-waste
%X Recent advancements in Large Language Models (LLMs) have paved the way for VisionLarge Language Models (VLLMs) capable ofperforming a wide range of visual understand-ing tasks. While LLMs have demonstrated impressive performance on standard naturalimages, their capabilities have not been thoroughly explored in cluttered datasets where there is complex environment having deformedshaped objects. In this work, we introduce a novel dataset specifically designed for waste classification in real-world scenarios, character-ized by complex environments and deformed shaped objects. Along with this dataset, we present an in-depth evaluation approach to rig-orously assess the robustness and accuracy of VLLMs. The introduced dataset and comprehensive analysis provide valuable insights intothe performance of VLLMs under challenging conditions. Our findings highlight the critical need for further advancements in VLLM’s ro-bustness to perform better in complex enviroments. The dataset and code for our experiments are available at https://github.com/aliman80/wastebench.
%R 10.18653/v1/2025.emnlp-main.1578
%U https://aclanthology.org/2025.emnlp-main.1578/
%U https://doi.org/10.18653/v1/2025.emnlp-main.1578
%P 31019-31032
Markdown (Informal)
[Waste-Bench: A Comprehensive Benchmark for Evaluating VLLMs in Cluttered Environments](https://aclanthology.org/2025.emnlp-main.1578/) (Ali & Khan, EMNLP 2025)
ACL