REVIEW 7 cited by
Mementos: A Comprehensive Benchmark for Multimodal Large Language Model Reasoning over Image Sequences
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Mementos: A Comprehensive Benchmark for Multimodal Large Language Model Reasoning over Image Sequences
read the original abstract
Multimodal Large Language Models (MLLMs) have demonstrated proficiency in handling a variety of visual-language tasks. However, current MLLM benchmarks are predominantly designed to evaluate reasoning based on static information about a single image, and the ability of modern MLLMs to extrapolate from image sequences, which is essential for understanding our ever-changing world, has been less investigated. To address this challenge, this paper introduces Mementos, a new benchmark designed to assess MLLMs' sequential image reasoning abilities. Mementos features 4,761 diverse image sequences with varying lengths. We also employ a GPT-4 assisted method to evaluate MLLM reasoning performance. Through a careful evaluation of nine recent MLLMs on Mementos, including GPT-4V and Gemini, we find that they struggle to accurately describe dynamic information about given image sequences, often leading to hallucinations/misrepresentations of objects and their corresponding behaviors. Our quantitative analysis and case studies identify three key factors impacting MLLMs' sequential image reasoning: the correlation between object and behavioral hallucinations, the influence of cooccurring behaviors, and the compounding impact of behavioral hallucinations. Our dataset is available at https://github.com/umd-huang-lab/Mementos.
Forward citations
Cited by 7 Pith papers
-
SMMBench: A Benchmark for Source-Distributed Multimodal Agent Memory
SMMBench is a benchmark evaluating multimodal agents on cross-source reasoning, conflict resolution, preference reasoning, and action prediction, showing current systems struggle with evidence distributed across heter...
-
MuirBench: A Comprehensive Benchmark for Robust Multi-image Understanding
MuirBench is a new benchmark showing that top multimodal LLMs struggle with robust multi-image understanding, with GPT-4o at 68% and open-source models below 33% accuracy.
-
Beyond Retrieval: Analytic Memory for Multimodal Agents
ADAMM induces queryable analytic tables from multimodal interaction histories and combines them with semantic retrieval, improving benchmark accuracy by up to 11.3 points over memory baselines.
-
Spatio-Temporal Grounding of Large Language Models from Perception Streams
FESTS uses Spatial Regular Expressions compiled from queries to generate 27k training tuples that raise a 3B-parameter LLM's frame-level F1 on spatio-temporal video reasoning from 48.5% to 87.5%, matching GPT-4.1 whil...
-
Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling
InternVL 2.5 is the first open-source MLLM to surpass 70% on the MMMU benchmark via model, data, and test-time scaling, with a 3.7-point gain from chain-of-thought reasoning.
-
Towards Mitigating Hallucinations in Large Vision-Language Models by Refining Textual Embeddings
Injecting an average-pooled visual embedding into every text token improves hallucination-benchmark scores of Video-LLaVA by small single-digit amounts.
-
mPLUG-Owl3: Towards Long Image-Sequence Understanding in Multi-Modal Large Language Models
mPLUG-Owl3 introduces hyper attention blocks to integrate vision and language for long image-sequence understanding and reports SOTA results on single-image, multi-image, and video benchmarks.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.