[Title]

or

[Optional: Interpretive Title]

[Authors (Venue and Year)]

Presented by [your name], [date]

Motivation

1-4 slides (make it engaging)
Should capture

• High level description of problem being solved (can use videos, images, etc)
• Why is that problem important?
• Why is that problem hard?
• High level idea of why prior work didn’t already solve this (Short description, later will go into details)

Contributions

Approximately one bullet, high level, for each of the following (the paper on 1 slide).

• Problem the reading is discussing
• Why is it important and hard
• What is the key limitation of prior work
• What is the key insight(s) (try to do in 1-3) of the proposed work
• What did they demonstrate by this insight? (tighter theoretical bounds, state of the art performance on X, etc)

Technical Background

1 or more slides

The background someone needs to understand this paper
That wasn’t just covered in a lecture or presentation

Problem Setting

1 or more slides
Problem Setup, Definitions, Notation
Be precise-- should be as formal as in the paper

Context in Literature

1 or more slides

Which other papers have tried to tackle this problem or a related problem?

• The paper’s related work is a good start, but there may be others
• What is the key limitations of prior work(s)?

Maybe have a few slides on other important/competing papers

Approach/Algorithm/Methods

Likely >1 slide

Describe algorithm or framework (pseudocode and flowcharts can help)

What is it trying to optimize?

Implementation details should be left out here, but may be discussed later if its relevant for limitations / experiments

Theory (if relevant)

What are the assumptions made for the theory? Are these reasonable? Realistic?

If the theory build strongly on other prior theory / results, reference those and state them here.

In what cases does the theory apply? How helpful is it, really?

Theory (if relevant)

State main results formally
Give proof sketches
Refer students to the full proofs in paper

Computation Experiments Setup (if relevant)

• Description of the experimental evaluation setting
• What is the domain(s)?
• What are the baseline(s)?
• How did the authors evaluate the success of their approach?
  • Clear description of the metrics that will be used

Computational Resources

What kind of computational resources were used? Is it feasible for a normal researcher/practitioner to use?

Numerical Results

>=1 slide

State results

Show figures / tables / plots

Discussion of Numerical Results

>=1 slide

What conclusions are drawn from the results?

Are the stated conclusions fully supported by the results and references? If so, why? (Recap the relevant supporting evidences from the given results + refs)

Hardware Demonstration (if Relevant)

What were the details of the hardware demonstrations (show videos if available)

How realistic was the demonstration? Was it in a very closed environment or more open?

Critique / Limitations / Open Issues

1 or more slides: What are the key limitations of the proposed approach / ideas? (e.g. does it require strong assumptions that are unlikely to be practical? Computationally expensive? Require a lot of data? Find only local optima? )

If follow up work has addressed some of these limitations, include pointers to that. But don’t limit your discussion only to the problems / limitations that have already been mentioned/addressed.

Impact and Legacy

How has this changed research in the field, or even how has it changed the world?

Tip: Use Google scholar cited-by links or connectedpapers.com:

Future Work for Paper/Reading

1 or more slides: What interesting questions does it raise for future work?

•  Your ideas for future work
•  Others’ ideas (if others have already built on this idea)

Contributions (Recap)

Approximately one bullet for each of the following (the paper on 1 slide)

• Problem the reading is discussing
• Why is it important and hard
• What is the key limitation of prior work
• What is the key insight(s) (try to do in 1-3) of the proposed work
• What did they demonstrate by this insight? (tighter theoretical bounds, state of the art performance on X, etc)