Challenge: Existing Multimodal Large Language Models struggle with 3D spatial reasoning as they fail to construct structured abstractions of the 3D environment depicted in video inputs.
Approach: They propose a prompting method that induces MLLMs to generate 3D representations as reasoning traces for more accurate spatial question answering.
Outcome: Extensive experiments on VSI-Bench and OST-Bech show that TRACE improves over prior prompting strategies across a diverse range of MLLM backbones.

Similar Papers

Can Multimodal Large Language Models Understand Spatial Relations? (2025.acl-long)

Copied to clipboard

Challenge: Spatial relation reasoning is a crucial task for multimodal large language models to understand the objective world.
Approach: They propose a human-annotated spatial relation reasoning benchmark based on COCO2017 to improve MLLMs' spatial relation thinking.
Outcome: The proposed benchmark achieves 48.14% accuracy, far below the human-level accuracy of 98.40%.
Multimodal Causal Reasoning Benchmark: Challenging Multimodal Large Language Models to Discern Causal Links Across Modalities (2025.findings-acl)

Copied to clipboard

Challenge: Existing MLLMs lack robustness in multimodal causal reasoning compared to their performance in textual settings.
Approach: They propose a novel multimodal chain-of-thought (CoT) reasoning benchmark that leverages siamese images and text pairs to challenge MLLMs.
Outcome: The proposed benchmark leverages siamese images and text pairs to challenge MLLMs.
Position: Multimodal Large Language Models Can Significantly Advance Scientific Reasoning (2026.findings-acl)

Copied to clipboard

Challenge: Current scientific reasoning models struggle with generalization across domains and fall short of multimodal perception.
Approach: They propose to use multimodal large language models to integrate text, images, and other modalities to enhance scientific reasoning.
Outcome: The proposed models can integrate text, images, and other modalities and improve reasoning across disciplines.
Look and Think: Efficient Multimodal Reasoning via Modality-Decoupled Compression (2026.findings-acl)

Copied to clipboard

Challenge: Multimodal large language models have strong performance on visual question answering benchmarks . however, their inference efficiency is severely constrained by the rapidly growing context .
Approach: They propose a modality-decoupled compression method that enables efficient multimodal inference . they propose to evict visual tokens whenever visual grounding is unnecessary .
Outcome: The proposed method reduces the average context length by up to 57% while maintaining comparable performance to the standard MLLM baseline.
VQAGuider: Guiding Multimodal Large Language Models to Answer Complex Video Questions (2025.acl-long)

Copied to clipboard

Challenge: Multimodal large language models (MLLMs) can grasp the intention of a question and decomposing it to a series of visual recognition sub-tasks to find out the answer with the help of an agent.
Approach: They propose a framework for multimodal large language models to grasp the intention of a question and decompose it into a series of visual recognition sub-tasks to find out the answer.
Outcome: The proposed framework improves the accuracy of complex video-related questions by 29.6% and 17.2% on CVQA and the existing VQA datasets.
An Empirical Analysis on Spatial Reasoning Capabilities of Large Multimodal Models (2024.emnlp-main)

Copied to clipboard

Challenge: Large Multimodal Models (LMMs) have shown impressive generalization ability on vision and language tasks, but their spatial understanding is under-explored.
Approach: They construct a VQA dataset to analyze LMMs' spatial reasoning capabilities.
Outcome: The proposed model is stronger at basic object detection than complex spatial reasoning.
Probing Multimodal Large Language Models for Global and Local Semantic Representations (2024.lrec-main)

Copied to clipboard

Challenge: Existing studies have focused on the ability of MLLMs to generate single tokens one by one, while lacking studies about how their representation vectors can encode global multimodal information.
Approach: They propose to use image-caption corpus to train Multimodal Large Language Models (MLLMs) . they find that the topmost layers encode more global semantic information .
Outcome: The proposed models can encode more global semantic information, rather than the topmost layers, and perform better on visual-language entailment tasks.
From Multimodal LLM to Human-level AI: Modality, Instruction, Reasoning, Efficiency and beyond (2024.lrec-tutorials)

Copied to clipboard

Challenge: This tutorial aims to deliver a comprehensive review of cutting-edge research in MLLMs.
Approach: This tutorial will review cutting-edge research in MLLMs and examine the impact of ML in learning and reasoning.
Outcome: This course will review cutting-edge research in MLLMs and examine the impact of ML models on learning, learning, and multimodal reasoning.
Probing Logical Reasoning of MLLMs in Scientific Diagrams (2025.emnlp-main)

Copied to clipboard

Challenge: logical reasoning is key to real-world applications like science education, environmental monitoring, and medical diagnostics.
Approach: They construct visual questions that follow seven structured templates with progressively more complex reasoning involved.
Outcome: The proposed models perform logical inferences based on visual information.
Forgotten Polygons: Multimodal Large Language Models are Shape-Blind (2025.findings-acl)

Copied to clipboard

Challenge: Multimodal Large Language Models struggle with visual reasoning, despite strong performance on vision-language tasks.
Approach: They propose a visually cued chain-of-thought prompting that enhances multi-step mathematical reasoning by explicitly referencing visual annotations in diagrams.
Outcome: The proposed model improves GPT-4o's accuracy on an irregular polygon side-counting task from 7% to 93%.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations