M³Eval is a new cognitively-grounded benchmark that evaluates memory dimensions in multi-modal video models and reports consistent model weaknesses in disentanglement, interference, spatial-temporal grounding, and symbolic recall.
Svbench: A benchmark with temporal multi-turn dialogues for streaming video understanding
11 Pith papers cite this work. Polarity classification is still indexing.
11
Pith papers citing it
citation-role summary
background 1
baseline 1
citation-polarity summary
fields
cs.CV 11representative citing papers
X-Stream benchmark shows SOTA MLLMs score ~50% on concurrent multi-stream tasks and lack proactive ability, using a dual-verification pipeline to avoid single-stream bias.
OASIS organizes streaming video into hierarchical events and retrieves memory on-demand via intent-driven refinement to improve long-horizon accuracy and compositional reasoning with bounded token costs.
The work introduces the ORVOS task, the ORVOSB benchmark with causal annotations across 210 videos, and a baseline using updated prompts plus a temporal token reservoir.
StreamGaze is a new benchmark and QA generation pipeline that measures how well MLLMs leverage gaze trajectories for temporal reasoning and proactive intention prediction in streaming egocentric videos.
Introduces the first dedicated benchmark for live multi-modal LLM task guidance with mistake detection and a streaming baseline model.
Introduces Ego-MC-Bench benchmark and Ego-CoMist synthetic dataset showing that fine-tuning video LLMs on proactive mistake corrections improves performance especially for smaller models.
IPIBench evaluates MLLMs on interactive proactive intelligence in streaming videos, identifies unstable triggering and poor coordination, and proposes the training-free IPI-Agent framework to improve performance across settings.
A large-scale, hierarchically-annotated human-centric video dataset and a three-level benchmark (OHBench) are presented, showing that fine-tuning on a subset of the data improves audio-video generation model performance.
Streamo is a streaming video LLM trained end-to-end on the new Streamo-Instruct-465K dataset that unifies multiple real-time video tasks with claimed strong temporal reasoning and generalization.
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
-
M$^3$Eval: Multi-Modal Memory Evaluation through Cognitively-Grounded Video Tasks
M³Eval is a new cognitively-grounded benchmark that evaluates memory dimensions in multi-modal video models and reports consistent model weaknesses in disentanglement, interference, spatial-temporal grounding, and symbolic recall.
-
X-Stream: Exploring MLLMs as Multiplexers for Multi-Stream Understanding
X-Stream benchmark shows SOTA MLLMs score ~50% on concurrent multi-stream tasks and lack proactive ability, using a dual-verification pipeline to avoid single-stream bias.
-
OASIS: On-Demand Hierarchical Event Memory for Streaming Video Reasoning
OASIS organizes streaming video into hierarchical events and retrieves memory on-demand via intent-driven refinement to improve long-horizon accuracy and compositional reasoning with bounded token costs.
-
Online Reasoning Video Object Segmentation
The work introduces the ORVOS task, the ORVOSB benchmark with causal annotations across 210 videos, and a baseline using updated prompts plus a temporal token reservoir.
-
StreamGaze: Gaze-Guided Temporal Reasoning and Proactive Understanding in Streaming Videos
StreamGaze is a new benchmark and QA generation pipeline that measures how well MLLMs leverage gaze trajectories for temporal reasoning and proactive intention prediction in streaming egocentric videos.
-
Can Multi-Modal LLMs Provide Live Step-by-Step Task Guidance?
Introduces the first dedicated benchmark for live multi-modal LLM task guidance with mistake detection and a streaming baseline model.
-
Streaming Interventions: Can Video Large Language Models Correct Mistakes as They Occur?
Introduces Ego-MC-Bench benchmark and Ego-CoMist synthetic dataset showing that fine-tuning video LLMs on proactive mistake corrections improves performance especially for smaller models.
-
IPIBench: Evaluating Interactive Proactive Intelligence of MLLMs under Continuous Streams
IPIBench evaluates MLLMs on interactive proactive intelligence in streaming videos, identifies unstable triggering and poor coordination, and proposes the training-free IPI-Agent framework to improve performance across settings.
-
OmniHuman: A Large-scale Dataset and Benchmark for Human-Centric Video Generation
A large-scale, hierarchically-annotated human-centric video dataset and a three-level benchmark (OHBench) are presented, showing that fine-tuning on a subset of the data improves audio-video generation model performance.
-
Streaming Video Instruction Tuning
Streamo is a streaming video LLM trained end-to-end on the new Streamo-Instruct-465K dataset that unifies multiple real-time video tasks with claimed strong temporal reasoning and generalization.
-
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.