SemExp
No estimate
No hardware requirements for this model
This model's weights are open, but no parameter count has been published for it. Every memory and speed figure starts from that number, so we would rather show nothing than a fabricated estimate.
On record
Full specification
Everything on record for this model. Most of it describes how it was trained rather than how it runs — useful context for judging how much work went into it, and how it compares with models built at a different scale.
Origin
Who built this model, where, and when it was published.
- Organisation
- Carnegie Mellon University (CMU),Facebook AI Research
- Organisation type
- Academia,Industry
- Country
- United States of America, France
- Published
- 2 July 2020
- Authors
- Devendra Singh Chaplot, Dhiraj Gandhi, Abhinav Gupta, Ruslan Salakhutdinov
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Robotics
- Task
- Object detection
- Approach
- Reinforcement learning
Size
How large the model is and how much data it was trained on. Parameters are the figure that decides whether it fits on a given graphics card.
- Training data
- tokens
"Our training and test set consists of a total of 86 scenes (25 Gibson tiny and 61 MP3D) and 16 scenes (5 Gibson tiny and 11 MP3D), respectively"
Availability
Whether you can obtain the model and run it on your own hardware, which is what decides if any of the graphics-card figures on this page apply.
- Weights
- Open — downloadable
- Model access
- Open weights (unrestricted)
- Training code
- Open source
MIT code/weights: https://github.com/devendrachaplot/Object-Goal-Navigation
How it is classified
Labels the source dataset applies when tracking notable models, and how confident it is in the entry.
- Why it is tracked
- SOTA improvement
- Record confidence
- Unknown
- Citations
- 723
"Our method achieves state-of-the-art performance on the object goal navigation task and won the CVPR2020 Habitat ObjectNav challenge"
Sources
Where this record came from and when it was last checked.
- Reference
- Object Goal Navigation using Goal-Oriented Semantic Exploration
- Last updated
- 25 May 2026
What the numbers mean
Background
SemExp was published by Carnegie Mellon University (CMU),Facebook AI Research, in United States of America, in July 2020. The organisation is categorised as academia,Industry.
It works in Robotics, and is recorded as doing object detection.
The weights are published, so it can be downloaded and run on your own hardware indefinitely, offline, with no account attached.
How it was trained
It is tracked in the underlying dataset for one reason in particular: sOTA improvement.
Answers
SemExp — common questions
Is SemExp open source?
Its weights are published, so SemExp can be downloaded and run on your own hardware. Note that open weights is not the same as open source in the full sense — it says nothing about the training data, the training code, or the commercial terms attached.
How many parameters does SemExp have?
No parameter count has been published for SemExp, which is why no memory or speed figure appears on this page.
Who created SemExp?
SemExp was published by Carnegie Mellon University (CMU),Facebook AI Research, based in United States of America, categorised as academia,Industry.
When was SemExp released?
SemExp was published in July 2020. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.
What is SemExp used for?
SemExp works in Robotics, and is recorded as handling object detection. A model can carry several of each, so these are the areas it was built for rather than a limit on what it will attempt.
Where can I download SemExp?
The weights for SemExp are published, though we do not hold a repository link for it. This site calculates hardware requirements rather than hosting model files.
What GPU do I need to run SemExp?
We cannot say. SemExp has open weights, but no parameter count has been published for it, and every memory and speed calculation starts from that number. We would rather show nothing than a fabricated estimate.
The other direction
Looking at it from the other side?
This page starts from the model. If you already own a card and want to know everything it will run, start from the hardware instead.