Kuldeep Singh Sidhu's picture
6 3

Kuldeep Singh Sidhu

singhsidhukuldeep

AI & ML interests

πŸ˜ƒ TOP 3 on HuggingFace for posts πŸ€— Seeking contributors for a completely open-source πŸš€ Data Science platform! singhsidhukuldeep.github.io

Recent Activity

updated a Space 38 minutes ago
singhsidhukuldeep/posts_leaderboard
posted an update about 14 hours ago
Exciting breakthrough in AI: @Meta's new Byte Latent Transformer (BLT) revolutionizes language models by eliminating tokenization! The BLT architecture introduces a groundbreaking approach that processes raw bytes instead of tokens, achieving state-of-the-art performance while being more efficient and robust. Here's what makes it special: >> Key Innovations Dynamic Patching: BLT groups bytes into variable-sized patches based on entropy, allocating more compute power where the data is more complex. This results in up to 50% fewer FLOPs during inference compared to traditional token-based models. Three-Component Architecture: β€’ Lightweight Local Encoder that converts bytes to patch representations β€’ Powerful Global Latent Transformer that processes patches β€’ Local Decoder that converts patches back to bytes >> Technical Advantages β€’ Matches performance of Llama 3 at 8B parameters while being more efficient β€’ Superior handling of non-English languages and rare character sequences β€’ Remarkable 99.9% accuracy on spelling tasks β€’ Better scaling properties than token-based models >> Under the Hood The system uses an entropy model to determine patch boundaries, cross-attention mechanisms for information flow, and hash n-gram embeddings for improved representation. The architecture allows simultaneous scaling of both patch and model size while maintaining fixed inference costs. This is a game-changer for multilingual AI and could reshape how we build future language models. Excited to see how this technology evolves!
posted an update 9 days ago
Groundbreaking Research Alert: The 'H' in HNSW Stands for "Hubs", Not "Hierarchy"! Fascinating new research reveals that the hierarchical structure in the popular HNSW (Hierarchical Navigable Small World) algorithm - widely used for vector similarity search - may be unnecessary for high-dimensional data. πŸ”¬ Key Technical Findings: β€’ The hierarchical layers in HNSW can be completely removed for vectors with dimensionality > 32, with no performance loss β€’ Memory savings of up to 38% achieved by removing the hierarchy β€’ Performance remains identical in both median and tail latency cases across 13 benchmark datasets πŸ› οΈ Under The Hood: The researchers discovered that "hub highways" naturally form in high-dimensional spaces. These hubs are well-connected nodes that are frequently traversed during searches, effectively replacing the need for explicit hierarchical layers. The hub structure works because: β€’ A small subset of nodes appear disproportionately in nearest neighbor lists β€’ These hub nodes form highly connected subgraphs β€’ Queries naturally traverse through these hubs early in the search process β€’ The hubs efficiently connect distant regions of the graph πŸ’‘ Industry Impact: This finding has major implications for vector databases and similarity search systems. Companies can significantly reduce memory usage while maintaining performance by implementing flat navigable small world graphs instead of hierarchical ones. πŸš€ What's Next: The researchers have released FlatNav, an open-source implementation of their flat navigable small world approach, enabling immediate practical applications of these findings.
View all activity

Organizations

MLX Community's profile picture Social Post Explorers's profile picture C4AI Community's profile picture

Posts 102

view post
Post
299
Exciting breakthrough in AI: @Meta 's new Byte Latent Transformer (BLT) revolutionizes language models by eliminating tokenization!

The BLT architecture introduces a groundbreaking approach that processes raw bytes instead of tokens, achieving state-of-the-art performance while being more efficient and robust. Here's what makes it special:

>> Key Innovations
Dynamic Patching: BLT groups bytes into variable-sized patches based on entropy, allocating more compute power where the data is more complex. This results in up to 50% fewer FLOPs during inference compared to traditional token-based models.

Three-Component Architecture:
β€’ Lightweight Local Encoder that converts bytes to patch representations
β€’ Powerful Global Latent Transformer that processes patches
β€’ Local Decoder that converts patches back to bytes

>> Technical Advantages
β€’ Matches performance of Llama 3 at 8B parameters while being more efficient
β€’ Superior handling of non-English languages and rare character sequences
β€’ Remarkable 99.9% accuracy on spelling tasks
β€’ Better scaling properties than token-based models

>> Under the Hood
The system uses an entropy model to determine patch boundaries, cross-attention mechanisms for information flow, and hash n-gram embeddings for improved representation. The architecture allows simultaneous scaling of both patch and model size while maintaining fixed inference costs.

This is a game-changer for multilingual AI and could reshape how we build future language models. Excited to see how this technology evolves!
view post
Post
1213
Groundbreaking Research Alert: The 'H' in HNSW Stands for "Hubs", Not "Hierarchy"!

Fascinating new research reveals that the hierarchical structure in the popular HNSW (Hierarchical Navigable Small World) algorithm - widely used for vector similarity search - may be unnecessary for high-dimensional data.

πŸ”¬ Key Technical Findings:

β€’ The hierarchical layers in HNSW can be completely removed for vectors with dimensionality > 32, with no performance loss

β€’ Memory savings of up to 38% achieved by removing the hierarchy

β€’ Performance remains identical in both median and tail latency cases across 13 benchmark datasets

πŸ› οΈ Under The Hood:
The researchers discovered that "hub highways" naturally form in high-dimensional spaces. These hubs are well-connected nodes that are frequently traversed during searches, effectively replacing the need for explicit hierarchical layers.

The hub structure works because:
β€’ A small subset of nodes appear disproportionately in nearest neighbor lists
β€’ These hub nodes form highly connected subgraphs
β€’ Queries naturally traverse through these hubs early in the search process
β€’ The hubs efficiently connect distant regions of the graph

πŸ’‘ Industry Impact:
This finding has major implications for vector databases and similarity search systems. Companies can significantly reduce memory usage while maintaining performance by implementing flat navigable small world graphs instead of hierarchical ones.

πŸš€ What's Next:
The researchers have released FlatNav, an open-source implementation of their flat navigable small world approach, enabling immediate practical applications of these findings.

models

None public yet

datasets

None public yet