Challenge: Existing MLLMs overemphasize knowledge retrieval while neglecting prior context, causing redundancy and incoherence.
Approach: They propose a framework that combines context compression, knowledge retrieval, and narration generation to improve models' performance.
Outcome: The proposed method significantly improves MLLM performance over existing models.

Similar Papers

Synchronized Video Storytelling: Generating Video Narrations with Structured Storyline (2024.acl-long)

Copied to clipboard

Challenge: Existing studies on dense video captioning and video story generation have made some progress, but in practical applications, we typically require synchronized narrations for ongoing visual scenes.
Approach: They propose a task of Synchronized Video Storytelling to generate synchronized narrations for videos using a benchmark dataset with rich annotations.
Outcome: The proposed framework can generate narrations with the guidance of the generated or predefined storyline and human evaluations validate the effectiveness.
Movie101v2: Improved Movie Narration Benchmark (2025.acl-long)

Copied to clipboard

Challenge: Automatic movie narration aims to generate video-aligned plot descriptions to assist visually impaired audiences.
Approach: They propose to break down the ultimate goal of automatic movie narration into three stages . they propose a large-scale, bilingual dataset with enhanced data quality .
Outcome: The proposed dataset breaks down the goal of automatic movie narration into three stages . achieving applicable movie narration is a fascinating goal that requires significant research .
MovieUN: A Dataset for Movie Understanding and Narrating (2022.findings-emnlp)

Copied to clipboard

Challenge: Automatic movie narration generation and narration grounding are important to provide a true movie experience for the blind and visually impaired.
Approach: They propose to use movie clips as a benchmark to support automatic movie narration generation and narration grounding tasks.
Outcome: The proposed methods are effective in supporting two movie-based tasks for the blind and visually impaired.
PedagogyBench: A Cognitive-Driven Benchmark for Multimodal Instructional Video Understanding (2026.findings-acl)

Copied to clipboard

Challenge: Existing video understanding benchmarks do not adequately capture the pedagogical logic embedded in instructional videos.
Approach: They propose a pedagogy-driven segmentation strategy and a dual-stream semantic injection pipeline that combines machine pre-annotation with expert refinement.
Outcome: The proposed model performs well on discriminative tasks but degrades on higher-order pedagogical diagnosis, relying on parametric memory rather than grounded visual perception.
ProLongVid: A Simple but Strong Baseline for Long-context Video Instruction Tuning (2025.emnlp-main)

Copied to clipboard

Challenge: Existing approaches to adapt image-focused models for video understanding have not been successful in analyzing long video sequences.
Approach: They propose a video instruction dataset that outperforms existing video instruction data for fine-tuning MLLMs by incrementally increasing input context length.
Outcome: The proposed model outperforms existing models on video benchmarks and outperformed proprietary models on VideoMME even with a compact 7B model.
AlignMMBench: Evaluating Chinese Multimodal Alignment in Large Vision-Language Models (2025.acl-long)

Copied to clipboard

Challenge: Existing benchmarks focus on basic abilities using nonverbal methods, such as yes-no and multiple-choice questions.
Approach: They propose a benchmark that provides more nuanced evaluations of alignment capabilities for large Vision-Language Models (VLMs) they use a rule-calibrated evaluator that exceeds GPT-4's evaluation ability and a “alignment score” to assess the robustness and stability of models across diverse prompts.
Outcome: The proposed benchmark covers 13 tasks across three categories and includes both single-turn and multi-turn dialogue scenarios.
Movie101: A New Movie Understanding Benchmark (2023.acl-long)

Copied to clipboard

Challenge: Existing methods to narrate movies with no actors are difficult to implement in real situations . a new metric is proposed to provide the best correlation with human evaluation .
Approach: They propose a large-scale Chinese movie benchmark to help visually impaired enjoy movies . they propose metric called Movie Narration Score (MNScore) which achieves best correlation with human evaluation.
Outcome: The proposed method outperforms baselines and the existing methods.
NarraBench: A Comprehensive Framework for Narrative Benchmarking (2026.eacl-long)

Copied to clipboard

Challenge: Existing benchmarks for narrative understanding are poorly aligned with existing metrics.
Approach: They propose to use NarraBench to assess aspects of narrative understanding that are either overlooked in current work or are poorly aligned with existing metrics.
Outcome: The proposed taxonomy and survey are useful to NLP researchers . they find that only 27% of tasks are well captured by existing benchmarks .
Multilingual Synopses of Movie Narratives: A Dataset for Vision-Language Story Understanding (2024.findings-emnlp)

Copied to clipboard

Challenge: Story video-text alignment is a core task in computational story understanding, but its progress has been held back by the scarcity of manually annotated video- text correspondences and the heavy concentration on English narrations of Hollywood movies.
Approach: They construct a multilingual video story dataset with 13,166 movie summary videos from 7 languages and manual annotations of fine-grained video-text correspondences.
Outcome: The proposed approach outperforms the SOTA methods on clip accuracy and Sentence IoU scores.
LongTableBench: Benchmarking Long-Context Table Reasoning across Real-World Formats and Domains (2025.findings-emnlp)

Copied to clipboard

Challenge: Evaluating 52 LLMs reveals that only the strongest models maintain robust performance under increasing context lengths and format diversity.
Approach: They propose a benchmark for evaluating long-context reasoning over semi-structured tables across diverse formats, tasks, and domains.
Outcome: The proposed model outperforms compression-based approaches on tasks requiring semantic integration.

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