VideoMemBench: How Well Do MLLMs Remember in Video Conversations?
VideoMemBench is a benchmark for in-context video memory in multimodal large language models.
Source-based brief · Editor review not recorded · See checks and limits ↓
One primary source; other links are context, not independent corroboration.
- Primary sourceHugging Face
- Discovery linkHugging Face
The paper page is linked. Peer review and findings have not been independently checked by AINewsIQ.
Open full article view →- Original paper+45
- Fetched source page+30
- No editor link review+0
- Original non-discussion link+5
This measures the stored source trail and editorial steps. It does not certify accuracy, peer review, or independent corroboration. Popularity adds no points.
View full scoring →Read the scoring rubric →What the source says
VideoMemBench is a benchmark for in-context video memory in multimodal large language models. Each sample pairs one video with a long multi-turn dialogue whose turns are linked by typed cross-turn dependencies: Episodic Dependencies refer back to earlier visual episodes, and Answer Dependencies build on the model's own earlier answers. Dependencies are checked for necessity and non-leakage, using an LLM planner, generator, and judger with human expert review. The benchmark has 326 videos and 2,476 turns, 1,387 of which depend on earlier turns. Among over 20 evaluated MLLMs, the best overall score is 45.7%.
Claim explorer
Attribution, source and conditionsSource-stated points from the stored brief. Claim-level assessments have not been recorded.
Source claims not independently checked; the 45.7% top score and model name are as reported in the supplied text.
This connects a source, an attributed statement and its qualifications. It does not establish that the claim is correct.
Questions worth asking
Open questions for further reportingWhat remains unconfirmed?
Source claims not independently checked; the 45.7% top score and model name are as reported in the supplied text.
What material was available for this brief?
The recorded brief basis is fetched source page. These points are AINewsIQ paraphrases, not quotations or independent confirmations.
VideoMemBench contains 326 videos with 2,476 turns, of which 1,387 depend on earlier turns.
Source: Hugging Face ↗Stored source-based brief · key point 1 · AINewsIQ paraphraseEpisodic Dependencies probe memory of what the model has seen; Answer Dependencies probe memory of what it has said.
Source: Hugging Face ↗Stored source-based brief · key point 2 · AINewsIQ paraphraseEach dependency is verified for necessity and non-leakage, with each dialogue reviewed by human experts.
Source: Hugging Face ↗Stored source-based brief · key point 3 · AINewsIQ paraphraseAmong over 20 evaluated open and closed MLLMs, the top overall score is 45.7%.
Source: Hugging Face ↗Stored source-based brief · key point 4 · AINewsIQ paraphraseLimits from the stored brief
Source claims not independently checked; the 45.7% top score and model name are as reported in the supplied text.
This is a source-based abstract, not independent validation of the source's claims.
Evidence & sources
These links show where the signal came from and what the source page linked to. A linked page is context, not independent corroboration.
Related archive coverage
These relationships record a citation or topic overlap, not confirmation of the finding.
The paper page is linked. Peer review and findings have not been independently checked by AINewsIQ.
Timeline & updates
- Signal dated by source or discovery feed
This timestamp places the signal in the radar. It may be the discovery post date rather than the primary page's first publication date.
- Shared brief stored
AINewsIQ prepared one abstract from fetched source page.
Brief history · 1 retained version
These are changes to AINewsIQ’s own publication. Earlier history is unavailable unless recorded here. Complete retained versions are available to the editor.
- Version 1 · published
Source-based brief stored or updated. This does not establish that the publisher changed its page.
Automated record
Source observations · 1 recent captures
A changed capture means the extracted text differed. It can reflect page furniture or extraction changes; it does not establish a substantive correction. Source captures remain private.
Retained capture; no earlier comparison available.
New engagement snapshots do not mean the source itself changed. Source observations and AINewsIQ brief revisions are separate records.
Why this may matter
Existing video QA benchmarks use independent questions, so they cannot measure whether a model carries information across turns. VideoMemBench targets that gap, which matters for sustained dialogue over long videos.
Limits and open questions
Source claims not independently checked; the 45.7% top score and model name are as reported in the supplied text.
Organization-specific financial, security, and operational effects require the organization's own context and review.
Join the discussion
Have a different perspective or a question about the evidence? Discussion is free with a verified email account. Every comment is reviewed before publication.
No published comments yet.
New commenters: 2 submissions per 24 hours, at least 5 minutes apart, until 3 are approved. Discussion guidelines and moderation →