Pith. sign in

REVIEW 7 cited by

PerceptionLM: Open-Access Data and Models for Detailed Visual Understanding

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2504.13180 v3 pith:AILP7NVM submitted 2025-04-17 cs.CV cs.AIcs.LG

classification cs.CVcs.AIcs.LG
keywords datamodelsvideotrainingunderstandingresearchdetaileddistillation
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Vision-language models are integral to computer vision research, yet many high-performing models remain closed-source, obscuring their data, design and training recipe. The research community has responded by using distillation from black-box models to label training data, achieving strong benchmark results, at the cost of measurable scientific progress. However, without knowing the details of the teacher model and its data sources, scientific progress remains difficult to measure. In this paper, we study building a Perception Language Model (PLM) in a fully open and reproducible framework for transparent research in image and video understanding. We analyze standard training pipelines without distillation from proprietary models and explore large-scale synthetic data to identify critical data gaps, particularly in detailed video understanding. To bridge these gaps, we release 2.8M human-labeled instances of fine-grained video question-answer pairs and spatio-temporally grounded video captions. Additionally, we introduce PLM-VideoBench, a suite for evaluating challenging video understanding tasks focusing on the ability to reason about "what", "where", "when", and "how" of a video. We make our work fully reproducible by providing data, training recipes, code & models. https://github.com/facebookresearch/perception_models

Discussion (0). Sign in to comment.

Forward citations

Cited by 7 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. VideoMathQA: Benchmarking Mathematical Reasoning via Multimodal Understanding in Videos

    cs.CV 2025-06 conditional novelty 7.0 of 10

    A new dataset of 420 math video-question pairs with step-by-step reasoning annotations shows that current multimodal AI models, including the best proprietary system, answer fewer than half of the multi-binary questio...

  2. VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding

    cs.CV 2026-07 conditional novelty 6.0 of 10

    An open 4B video MLLM with inflated-3D ViT tokenization and adaptive streaming perception outperforms comparable open models on general, long-video, and streaming benchmarks while using fewer visual tokens.

  3. NarrativeTrack: Evaluating Entity-Centric Reasoning for Narrative Understanding

    cs.CV 2026-01 conditional novelty 6.0 of 10

    NarrativeTrack shows that video AI models, including GPT-4o, falter at tracking a specific person across scene changes, outfit changes, and similar-looking characters in long videos.

  4. Strefer: Empowering Video LLMs with Space-Time Referring and Reasoning via Synthetic Instruction Data

    cs.CV 2025-09 conditional novelty 6.0 of 10

    Adding Strefer's synthetic space-time reference questions to video instruction tuning improves mask-referred description/QA, timestamp QA, and temporal reasoning over a video-LLM baseline.

  5. CausalVQA: A Physically Grounded Causal Reasoning Benchmark for Video Models

    cs.CV 2025-06 conditional novelty 6.0 of 10

    CausalVQA provides 793 paired real-video causal reasoning questions on which the best multimodal model scores 61.66% versus 84.78% for humans, with the largest gaps on anticipation and hypothetical questions.

  6. BYO-Eval: Build Your Own Dataset for Fine-Grained Visual Assessment of Multimodal Language Models

    cs.CV 2025-06 conditional novelty 6.0 of 10

    A Blender-based diagnostic toolkit that tests VLMs on fine-grained visual skills by varying one visual attribute at a time, exposing failure modes that coarse benchmarks miss.

  7. Group Relative Augmentation for Data Efficient Action Detection

    cs.CV 2025-07 conditional novelty 5.0 of 10

    A LoRA plus FiLM feature-augmentation method with a group-weighted loss reports modest few-shot action detection gains on AVA and MOMA, but the evidence for the weighting component is weak.

Pith tools