VSTAT benchmark shows state-of-the-art MLLMs perform far below humans and only modestly above answer-prior baselines on visual state tracking, failing at visual perception despite correct textual reasoning.
hub Tool reference
LVBench: An Extreme Long Video Understanding Benchmark
Tool reference. 89% of classified Pith citations use this work as a method, library, or software dependency, not as a substantive claim.
36
Pith papers citing it
Method reference
89% of classified citations
abstract
Recent progress in multimodal large language models has markedly enhanced the understanding of short videos (typically under one minute), and several evaluation datasets have emerged accordingly. However, these advancements fall short of meeting the demands of real-world applications such as embodied intelligence for long-term decision-making, in-depth movie reviews and discussions, and live sports commentary, all of which require comprehension of long videos spanning several hours. To address this gap, we introduce LVBench, a benchmark specifically designed for long video understanding. Our dataset comprises publicly sourced videos and encompasses a diverse set of tasks aimed at long video comprehension and information extraction. LVBench is designed to challenge multimodal models to demonstrate long-term memory and extended comprehension capabilities. Our extensive evaluations reveal that current multimodal models still underperform on these demanding long video understanding tasks. Through LVBench, we aim to spur the development of more advanced models capable of tackling the complexities of long video comprehension. Our data and code are publicly available at: https://lvbench.github.io.
hub tools
citation-role summary
dataset 7
background 1
method 1
citation-polarity summary
representative citing papers
VidMsg is a new benchmark dataset and QA/retrieval tasks for implicit message inference in short videos, where current models perform poorly.
Minerva-Ego is a new benchmark for egocentric visual reasoning with dense human-annotated traces and masks, showing that spatiotemporal hints substantially improve frontier model performance.
MCSC-Bench is the first large-scale dataset for the Multimodal Context-to-Script Creation task, requiring models to select relevant shots from redundant materials, plan missing shots, and generate coherent scripts with voiceovers.
VideoThinker uses LLM-generated synthetic tool trajectories in caption space grounded to video frames to train agentic VideoLLMs that outperform baselines on long-video benchmarks.
SIV-Bench is a new video benchmark with 2,792 clips and 5,455 QA pairs that evaluates MLLMs on social scene understanding, state reasoning, and dynamics prediction using social relation theory.
WorldSense provides the first benchmark requiring synergistic audio-video-text understanding on 1,662 real-world videos and 3,172 QA pairs, where the best current multimodal LLM reaches only 65.1% accuracy.
Video-MMMU benchmark shows large multimodal models exhibit steep performance drops on higher cognitive tasks when learning from professional videos and lag significantly behind humans in knowledge acquisition.
Presents Streaming-Train-248K dataset, Streaming Harness system, and Streaming-Eval benchmark to enable VLMs for proactive, memory-equipped streaming video understanding.
VTI-CoT proposes a visual-textual interleaved chain-of-thought method for video reasoning, built via automated annotation and OCR compression, claiming SOTA performance and better training efficiency on same-scale models.
MOSS-Video-Preview introduces a cross-attention architecture and synthesized real-time QA data to enable continuous perception, answer revision, and faster inference in video-language models compared to decoder-only designs.
DynFrame introduces tokenized learnable span-density retrieval and Segment-Decoupled GRPO in video MLLMs, achieving competitive or SOTA results on six benchmarks with 4B and 8B models.
LiteFrame is an efficient vision encoder backbone trained with Compressed Token Distillation and Language Model Adaptation to scale frame count in Video LLMs while cutting latency and raising accuracy.
Video MLLMs show an audio-visual Clever Hans effect relying on visual-acoustic correlations rather than audio verification; Thud interventions diagnose it and a 10K-sample preference alignment improves intervention performance by 28 points.
MiniCPM-o 4.5 uses the Omni-Flow streaming framework to deliver real-time full-duplex omni-modal interaction with proactive behavior in a 9B model that approaches Gemini 2.5 Flash performance.
XComp reaches extreme video compression (one token per selective frame) via learnable progressive token compression and question-conditioned frame selection, lifting LVBench accuracy from 42.9 percent to 46.2 percent after tuning on 2.5 percent of standard data.
TrajTok learns to tokenize video into object-trajectory tokens end-to-end, improving video CLIP, probing, and VLM performance over patch and token-merging baselines.
LongVT adds native video-cropping tool calling to LMMs for interleaved multimodal chain-of-tool-thought reasoning on long videos and releases VideoSIAH data for training and evaluation.
LLM Orchestration integrates modality experts via an LLM controller, cross-modal memory, and interaction layer to enable multimodal input-output without gradient-based training.
GLM-4.5V reaches state-of-the-art results on 42 multimodal benchmarks among open-source models of similar size by applying reinforcement learning with curriculum sampling to a strong vision foundation model.
MotionBench is a new benchmark showing poor fine-grained motion understanding in VLMs and proposes TE Fusion to improve performance with higher frame rates.
VideoChat-Flash applies hierarchical video token compression to achieve ~50x reduction in context length for long videos while maintaining near-original performance on long-context benchmarks.
AdaQ is a training-free adaptive quasi-Gaussian sampling method for keyframe selection that improves long-video understanding in MLLMs and can outperform GPT-4o with 64 frames.
LiveStarPro uses SVeD for response timing via perplexity, SCAM for incremental alignment, and TSHM for event-chain memory to achieve 28.9% better semantic correctness and 1.58x speedup on long video streams.
citing papers explorer
-
Benchmarking Visual State Tracking in Multimodal Video Understanding
VSTAT benchmark shows state-of-the-art MLLMs perform far below humans and only modestly above answer-prior baselines on visual state tracking, failing at visual perception despite correct textual reasoning.
-
VidMsg: A Benchmark for Implicit Message Inference in Short Videos
VidMsg is a new benchmark dataset and QA/retrieval tasks for implicit message inference in short videos, where current models perform poorly.
-
Minerva-Ego: Spatiotemporal Hints for Egocentric Video Understanding
Minerva-Ego is a new benchmark for egocentric visual reasoning with dense human-annotated traces and masks, showing that spatiotemporal hints substantially improve frontier model performance.
-
MCSC-Bench: Multimodal Context-to-Script Creation for Realistic Video Production
MCSC-Bench is the first large-scale dataset for the Multimodal Context-to-Script Creation task, requiring models to select relevant shots from redundant materials, plan missing shots, and generate coherent scripts with voiceovers.
-
VideoThinker: Building Agentic VideoLLMs with LLM-Guided Tool Reasoning
VideoThinker uses LLM-generated synthetic tool trajectories in caption space grounded to video frames to train agentic VideoLLMs that outperform baselines on long-video benchmarks.
-
SIV-Bench: A Video Benchmark for Social Interaction Understanding and Reasoning
SIV-Bench is a new video benchmark with 2,792 clips and 5,455 QA pairs that evaluates MLLMs on social scene understanding, state reasoning, and dynamics prediction using social relation theory.
-
WorldSense: Evaluating Real-world Omnimodal Understanding for Multimodal LLMs
WorldSense provides the first benchmark requiring synergistic audio-video-text understanding on 1,662 real-world videos and 3,172 QA pairs, where the best current multimodal LLM reaches only 65.1% accuracy.
-
Video-MMMU: Evaluating Knowledge Acquisition from Multi-Discipline Professional Videos
Video-MMMU benchmark shows large multimodal models exhibit steep performance drops on higher cognitive tasks when learning from professional videos and lag significantly behind humans in knowledge acquisition.
-
Harnessing Streaming Video in the Wild
Presents Streaming-Train-248K dataset, Streaming Harness system, and Streaming-Eval benchmark to enable VLMs for proactive, memory-equipped streaming video understanding.
-
VTI-CoT: Visual-Textual Interleaved Chain of Thought for Video Reasoning
VTI-CoT proposes a visual-textual interleaved chain-of-thought method for video reasoning, built via automated annotation and OCR compression, claiming SOTA performance and better training efficiency on same-scale models.
-
MOSS-Video-Preview: Toward Real-Time Video Understanding via Cross-Attention
MOSS-Video-Preview introduces a cross-attention architecture and synthesized real-time QA data to enable continuous perception, answer revision, and faster inference in video-language models compared to decoder-only designs.
-
DynFrame: Adaptive Reasoning-Driven Multimodal Framework with Dynamic Frame Augmentation for Complex Video Understanding
DynFrame introduces tokenized learnable span-density retrieval and Segment-Decoupled GRPO in video MLLMs, achieving competitive or SOTA results on six benchmarks with 4B and 8B models.
-
LiteFrame: Efficient Vision Encoders Unlock Frame Scaling in Video LLMs
LiteFrame is an efficient vision encoder backbone trained with Compressed Token Distillation and Language Model Adaptation to scale frame count in Video LLMs while cutting latency and raising accuracy.
-
When Vision Speaks for Sound
Video MLLMs show an audio-visual Clever Hans effect relying on visual-acoustic correlations rather than audio verification; Thud interventions diagnose it and a 10K-sample preference alignment improves intervention performance by 28 points.
-
MiniCPM-o 4.5: Towards Real-Time Full-Duplex Omni-Modal Interaction
MiniCPM-o 4.5 uses the Omni-Flow streaming framework to deliver real-time full-duplex omni-modal interaction with proactive behavior in a 9B model that approaches Gemini 2.5 Flash performance.
-
One Token per Highly Selective Frame: Towards Extreme Compression for Long Video Understanding
XComp reaches extreme video compression (one token per selective frame) via learnable progressive token compression and question-conditioned frame selection, lifting LVBench accuracy from 42.9 percent to 46.2 percent after tuning on 2.5 percent of standard data.
-
TrajTok: Learning Trajectory Tokens enables better Video Understanding
TrajTok learns to tokenize video into object-trajectory tokens end-to-end, improving video CLIP, probing, and VLM performance over patch and token-merging baselines.
-
LongVT: Incentivizing "Thinking with Long Videos" via Native Tool Calling
LongVT adds native video-cropping tool calling to LMMs for interleaved multimodal chain-of-tool-thought reasoning on long videos and releases VideoSIAH data for training and evaluation.
-
Training-Free Multimodal Large Language Model Orchestration
LLM Orchestration integrates modality experts via an LLM controller, cross-modal memory, and interaction layer to enable multimodal input-output without gradient-based training.
-
GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning
GLM-4.5V reaches state-of-the-art results on 42 multimodal benchmarks among open-source models of similar size by applying reinforcement learning with curriculum sampling to a strong vision foundation model.
-
MotionBench: Benchmarking and Improving Fine-grained Video Motion Understanding for Vision Language Models
MotionBench is a new benchmark showing poor fine-grained motion understanding in VLMs and proposes TE Fusion to improve performance with higher frame rates.
-
VideoChat-Flash: Hierarchical Compression for Long-Context Video Modeling
VideoChat-Flash applies hierarchical video token compression to achieve ~50x reduction in context length for long videos while maintaining near-original performance on long-context benchmarks.
-
Towards Fast and Effective Long Video Understanding of Multimodal Large Language Models via Adaptive Quasi-Gaussian Sampling
AdaQ is a training-free adaptive quasi-Gaussian sampling method for keyframe selection that improves long-video understanding in MLLMs and can outperform GPT-4o with 64 frames.
-
LiveStarPro: Proactive Streaming Video Understanding with Hierarchical Memory for Long-Horizon Streams
LiveStarPro uses SVeD for response timing via perplexity, SCAM for incremental alignment, and TSHM for event-chain memory to achieve 28.9% better semantic correctness and 1.58x speedup on long video streams.
-
OmniMem: Perturbation-aware Memory Compression for Streaming Audio-Visual LLMs
OmniMem achieves 2-4% higher accuracy than training-free baselines on long video benchmarks for audio-visual LLMs by using modality-aware KV cache allocation and perturbation-aware state selection, with further gains from budget-aware fine-tuning.
-
PyraVid: Hierarchical Multimodal Memory for Long-Horizon Video Reasoning
PyraVid is a hierarchical multimodal memory system that structures long videos into pyramids to improve long-horizon reasoning and evidence aggregation.
-
Seed1.8 Model Card: Towards Generalized Real-World Agency
Seed1.8 is a new foundation model that adds unified agentic capabilities for search, code execution, and GUI interaction to existing LLM and vision strengths.
-
Kimi K2.5: Visual Agentic Intelligence
Kimi K2.5 combines joint text-vision training with an Agent Swarm parallel orchestration framework to reach claimed state-of-the-art results on coding, vision, reasoning, and agent tasks while cutting latency up to 4.5 times.
-
MiniCPM-V 4.5: Cooking Efficient MLLMs via Architecture, Data, and Training Recipe
An 8B MLLM reaches state-of-the-art efficiency and performance under 30B by combining a unified 3D resampler, joint document-text training, and hybrid RL for reasoning modes.
-
CogVLM2: Visual Language Models for Image and Video Understanding
CogVLM2 family achieves state-of-the-art results on image and video understanding benchmarks through improved visual expert architecture, higher resolution inputs, and automated temporal grounding for videos.
-
InternVideo3: Agentify Foundation Models with Multimodal Contextual Reasoning
InternVideo3 introduces Multimodal Contextual Reasoning and M^2LA attention to enable closed-loop evidence accumulation in long-video understanding and agentic tool use, reporting strong benchmark results.
-
EasyVideoR1: Easier RL for Video Understanding
EasyVideoR1 delivers an optimized RL pipeline for video understanding in large vision-language models, achieving 1.47x throughput gains and aligned results on 22 benchmarks.
-
Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
Gemini 2.5 Pro and Flash models are presented as achieving frontier performance in reasoning, coding, and long-context multimodal tasks while spanning a cost-capability Pareto curve.
-
Seed1.5-VL Technical Report
Seed1.5-VL is a compact multimodal model that sets new records on dozens of vision-language benchmarks and outperforms prior systems on agent-style tasks.
-
VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding
VideoLLaMA3 uses a vision-centric training paradigm and token-reduction design to reach competitive results on image and video benchmarks.
-
Seed2.0 Model Card: Towards Intelligence Frontier for Real-World Complexity
Seed2.0 model series reports gains in reasoning, visual understanding, search, and reliability on intricate long-horizon tasks via an internal evaluation system.