Challenge: Video-language models excel at understanding video content but struggle with spatial relationships, temporal ordering, and cross-frame continuity.
Approach: They propose a framework that trains video-LLMs to distinguish accurate representations from carefully crafted adversarial examples.
Outcome: Experiments show that VideoPASTA improves performance without human annotation or captioning . the framework can be used on various state-of-the-art video-LLMs with no human annotation .

Similar Papers

TempCompass: Do Video LLMs Really Understand Videos? (2024.findings-acl)

Copied to clipboard

Challenge: Existing benchmarks on video large language models lack a comprehensive feedback on temporal perception ability . current models cannot distinguish between different temporal aspects and are limited in task formats .
Approach: They propose a benchmark to evaluate temporal perception ability of video large language models . they construct conflicting videos that share the same static content but differ in a specific temporal aspect .
Outcome: The proposed benchmarks show that video large language models exhibit poor temporal perception ability.
VideoINSTA: Zero-shot Long Video Understanding via Informative Spatial-Temporal Reasoning with LLMs (2024.findings-emnlp)

Copied to clipboard

Challenge: Long video understanding presents unique challenges due to the complexity of reasoning over extended timespans.
Approach: They propose a framework VideoINSTA to leverage large language models for video understanding . they propose 'event-based temporalreasoning' and 'content-based spatial reasoning'
Outcome: The proposed model significantly improves state-of-the-art on three long video question-answering benchmarks.
TemporalVLM: Video LLMs for Temporal Reasoning in Long Videos (2026.findings-acl)

Copied to clipboard

Challenge: Several video understanding applications require the ability of temporal reasoning.
Approach: They propose a video large language model for temporal reasoning and fine-grained understanding in long videos.
Outcome: The proposed model outperforms existing methods in time and motion studies and temporal action segmentation evaluations.
Video-LLaVA: Learning United Visual Representation by Alignment Before Projection (2024.emnlp-main)

Copied to clipboard

Challenge: Existing approaches to visual-language understanding lack unified tokenization for images and videos . lack of unified visual representations makes it difficult to learn multi-modal interactions from poor projection layers.
Approach: They propose to unify visual representation into the language feature space to advance the foundational LLM towards a unified LVLM.
Outcome: The proposed model outperforms Video-ChatGPT on image benchmarks and on 9 image benchmark benchmarks.
Video2Roleplay: A Multimodal Dataset and Framework for Video-Guided Role-playing Agents (2025.emnlp-main)

Copied to clipboard

Challenge: Existing approaches to RPAs focus on static role profiles, overlooking dynamic perceptual abilities inherent to humans.
Approach: They propose a framework that combines adaptive temporal sampling with dynamic and static role profiles.
Outcome: The proposed framework combines adaptive temporal sampling with dynamic and static role profiles.
Re-Align: Aligning Vision Language Models via Retrieval-Augmented Direct Preference Optimization (2025.emnlp-main)

Copied to clipboard

Challenge: emergence of large Vision Language Models (VLMs) has broadened the capabilities of single-modal Large Language Model (LLM) but VLMs are prone to significant hallucinations, especially in the form of cross-modal inconsistencies.
Approach: They propose a new alignment framework that leverages image retrieval to integrate both textual and visual preference signals.
Outcome: The proposed framework mitigates hallucinations more effectively than previous methods . it maintains robustness and scalability across a wide range of VLM sizes and architectures .
Mitigating the Discrepancy Between Video and Text Temporal Sequences: A Time-Perception Enhanced Video Grounding method for LLM (2025.coling-main)

Copied to clipboard

Challenge: Existing video LLMs excel at capturing the overall description of a video but lack the ability to demonstrate an understanding of temporal dynamics and localized content within the video.
Approach: They propose a Time-Perception Enhanced Video Grounding via Boundary Perception and Temporal Reasoning to improve LLMs' understanding of video temporality.
Outcome: The proposed method improves on three datasets: ActivityNet, Charades, and DiDeMo (up to 11.2% improvement on R@0.3).
Tuning Large Multimodal Models for Videos using Reinforcement Learning from AI Feedback (2024.acl-long)

Copied to clipboard

Challenge: Recent advances in large language models have influenced the development of video large multimodal models (VLMMs).
Approach: They propose a method that integrates video descriptions as context into a multimodal AI system to enrich the understanding of video content.
Outcome: Empirical evaluations show that the proposed approach outperforms existing approaches for video large multimodal models (VLMMs)
Enhancing Temporal Modeling of Video LLMs via Time Gating (2024.findings-emnlp)

Copied to clipboard

Challenge: Existing Video Large Language Models neglect temporal information in video data, leading to struggles with temporal-aware video understanding.
Approach: They propose a Time Gating Video LLM (TG-Vid) that employs a time gating module to enhance temporal modeling.
Outcome: The proposed model outperforms existing Large Language Models on video-and-language tasks and ablation studies show that the model outpersforms the existing models.
Direct Preference Optimization of Video Large Multimodal Models from Language Model Reward (2025.naacl-long)

Copied to clipboard

Challenge: Existing studies have demonstrated that direct preference optimization (DPO) can be effective in generalizing large language models, but its effectiveness in video domain remains limited.
Approach: They propose a framework that utilizes detailed video captions as a proxy of video content to enable language models to incorporate this information as supporting evidence for scoring video Question Answering (QA) predictions.
Outcome: The proposed framework shows that it can be used to align language models with video content and improves performance on open-ended video QA tasks.

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