Probably a good advice during the wild Sydney times of #BingAI.
@maximelabonne
-
PageRank Authors’ Paper Rejected by SIGIR Conference
By
–
PageRank's authors in tears after SIGIR rejects their paper (circa 2023):
-
FLAN-UL2 Delivers Impressive Performance Boost for Language Models
By
–
Impressive performance boost from FLAN-UL2. The FLAN family keeps on giving. https://
huggingface.co/google/flan-ul2 -
Comparing Transformers vs Traditional ML for Time Series
By
–
Thanks I like the idea. Do you know if it's better than Transformer-based techniques for time series or even better than traditional ML?
-
RetroDiffusion: AI-Powered Pixel Art Generation for Aseprite
By
–
RetroDiffusion I've finally found a good solution for #AI-generated pixel art. #stablediffusion It works directly in Aseprite and creates better color palettes than me. Prompt: "A knight exploring a dark dungeon" https://
astropulse.gumroad.com/l/RetroDiffusi
on?rdt_cid=4339897583112722894
… -
Combinatorial Optimization and RL Shape Future Game Design
By
–
Overall, cool paper about a funny application of combinatorial optimization. Jokes aside, RL and optimization are probably the future of game design. At least for puzzle games. 🙂
-
Multi-Island Genetic Algorithms Outperform Standard Approaches
By
–
Here are the final results. The multi-island outperforms the standard GA while maintaining higher diversity. There are a lot of useful tips and tricks about GAs in this paper. GAs deserve more love.
-
Multi-Island Genetic Algorithm for Diversity Maintenance
By
–
Maintaining diversity is a big focus, so they implemented a "multi-island" GA. → Each population is divided into several sub-populations called "islands" → Applies GA separately on each sub-population, periodically migrating individuals between them
-
Genetic Algorithm for Puzzle Solving with Diversity Selection
By
–
Next, solving puzzles. The authors used a custom GA: 1/ Initialization using the previous algorithm 2/ Crossover/Mutation with a uniform crossover operation 3/ Find feasible solutions and "heal" broken ones 4/ Selection with a diversity criterion
-
Graph Node Selection Algorithm With Constraint-Based Synergy Optimization
By
–
Proposed solution: 1/ Defining a random traversal order for graph nodes 2/ Filtering the list of candidates according to constraint requirements 3/ Selecting an item that maximizes the synergy of partially filled neighboring candidates.