Social Post Explorers

community
Activity Feed

AI & ML interests

None defined yet.

Recent Activity

social-post-explorers's activity

singhsidhukuldeep 
posted an update 1 day ago
view post
Post
1134
Exciting News in AI: JinaAI Releases JINA-CLIP-v2!

The team at Jina AI has just released a groundbreaking multilingual multimodal embedding model that's pushing the boundaries of text-image understanding. Here's why this is a big deal:

🚀 Technical Highlights:
- Dual encoder architecture combining a 561M parameter Jina XLM-RoBERTa text encoder and a 304M parameter EVA02-L14 vision encoder
- Supports 89 languages with 8,192 token context length
- Processes images up to 512×512 pixels with 14×14 patch size
- Implements FlashAttention2 for text and xFormers for vision processing
- Uses Matryoshka Representation Learning for efficient vector storage

⚡️ Under The Hood:
- Multi-stage training process with progressive resolution scaling (224→384→512)
- Contrastive learning using InfoNCE loss in both directions
- Trained on massive multilingual dataset including 400M English and 400M multilingual image-caption pairs
- Incorporates specialized datasets for document understanding, scientific graphs, and infographics
- Uses hard negative mining with 7 negatives per positive sample

📊 Performance:
- Outperforms previous models on visual document retrieval (52.65% nDCG@5)
- Achieves 89.73% image-to-text and 79.09% text-to-image retrieval on CLIP benchmark
- Strong multilingual performance across 30 languages
- Maintains performance even with 75% dimension reduction (256D vs 1024D)

🎯 Key Innovation:
The model solves the long-standing challenge of unifying text-only and multi-modal retrieval systems while adding robust multilingual support. Perfect for building cross-lingual visual search systems!

Kudos to the research team at Jina AI for this impressive advancement in multimodal AI!
singhsidhukuldeep 
posted an update 2 days ago
view post
Post
1128
Fascinating insights from @Pinterest 's latest research on improving feature interactions in recommendation systems!

Pinterest's engineering team has tackled a critical challenge in their Homefeed ranking system that serves 500M+ monthly active users. Here's what makes their approach remarkable:

>> Technical Deep Dive

Architecture Overview
• The ranking model combines dense features, sparse features, and embedding features to represent users, Pins, and context
• Sparse features are processed using learnable embeddings with size based on feature cardinality
• User sequence embeddings are generated using a transformer architecture processing past engagements

Feature Processing Pipeline
• Dense features undergo normalization for numerical stability
• Sparse and embedding features receive L2 normalization
• All features are concatenated into a single feature embedding

Key Innovations
• Implemented parallel MaskNet layers with 3 blocks
• Used projection ratio of 2.0 and output dimension of 512
• Stacked 4 DCNv2 layers on top for higher-order interactions

Performance Improvements
• Achieved +1.42% increase in Homefeed Save Volume
• Boosted Overall Time Spent by +0.39%
• Maintained memory consumption increase to just 5%

>> Industry Constraints Addressed

Memory Management
• Optimized for 60% GPU memory utilization
• Prevented OOM errors while maintaining batch size efficiency

Latency Optimization
• Removed input-output concatenation before MLP
• Reduced hidden layer sizes in MLP
• Achieved zero latency increase while improving performance

System Stability
• Ensured reproducible results across retraining
• Maintained model stability across different data distributions
• Successfully deployed in production environment

This work brilliantly demonstrates how to balance academic innovations with real-world industrial constraints. Kudos to the Pinterest team!
singhsidhukuldeep 
posted an update 4 days ago
view post
Post
3510
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:
• Lightweight Local Encoder that converts bytes to patch representations
• Powerful Global Latent Transformer that processes patches
• Local Decoder that converts patches back to bytes

>> Technical Advantages
• Matches performance of Llama 3 at 8B parameters while being more efficient
• Superior handling of non-English languages and rare character sequences
• Remarkable 99.9% accuracy on spelling tasks
• 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!
  • 2 replies
·
s3nh 
posted an update 6 days ago
view post
Post
1600
Welcome back,

Small Language Models Enthusiasts and GPU Poor oss enjoyers lets connect.
Just created an organization which main target is to have fun with smaller models tuneable on consumer range GPUs, feel free to join and lets have some fun, much love ;3

https://huggingface.co/SmolTuners
·
BlinkDL 
posted an update 7 days ago
view post
Post
1351
RWKV-7 "Goose" 0.4B trained w/ ctx4k automatically extrapolates to ctx32k+, and perfectly solves NIAH ctx16k 🤯 100% RNN and attention-free. Only trained on the Pile. No finetuning. Replicable training runs. tested by our community: https://github.com/Jellyfish042/LongMamba
AtAndDev 
posted an update 7 days ago
view post
Post
298
@s3nh Hey man check your discord! Got some news.
  • 4 replies
·
neph1 
posted an update 7 days ago
view post
Post
1037
For those interested in game development I've released an experimental finetune of Qwen2.5-Coder for Unity.

neph1/Qwen2.5-Coder-7B-Instruct-Unity

It's using a mix of open source datasets + one specifically made for this (also OS) with multiple responses.

Also thinking about making a code completion model, or one to have more architectural discussions with.
  • 1 reply
·
lorraine2 
posted an update 8 days ago
view post
Post
1965
🦙New NVIDIA paper: LLaMA-Mesh 🦙

We enable large language models to generate and understand 3D meshes by representing them as text and fine-tuning. This unifies the 3D and text modalities in a single model and preserves language abilities, unlocking conversational 3D creation with mesh understanding.

🔎 Project Page: https://research.nvidia.com/labs/toronto-ai/LLaMA-Mesh/
🕹️ Interactive Demo: Zhengyi/LLaMA-Mesh (courtesy of HuggingFace and Gradio)
📖 Full Paper: https://arxiv.org/abs/2411.09595
👨‍💻Code: https://github.com/nv-tlabs/LLaMa-Mesh
💾 Model Checkpoint: Zhengyi/LLaMA-Mesh
🧩 Blender Addon: https://github.com/huggingface/meshgen (courtesy of Dylan Ebert)
🎥 5-min Overview Video: https://youtu.be/eZNazN-1lPo?si=-idQa5aaceVw0Bbj (courtesy of AI Papers Academy)
singhsidhukuldeep 
posted an update 12 days ago
view post
Post
1227
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.

🔬 Key Technical Findings:

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

• Memory savings of up to 38% achieved by removing the hierarchy

• Performance remains identical in both median and tail latency cases across 13 benchmark datasets

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

💡 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.

🚀 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.
singhsidhukuldeep 
posted an update 13 days ago
view post
Post
454
Fascinating new research alert! Just read a groundbreaking paper on understanding Retrieval-Augmented Generation (RAG) systems and their performance factors.

Key insights from this comprehensive study:

>> Architecture Deep Dive
The researchers analyzed RAG systems across 6 datasets (3 code-related, 3 QA-focused) using multiple LLMs. Their investigation revealed critical insights into four key design factors:

Document Types Impact:
• Oracle documents (ground truth) aren't always optimal
• Distracting documents significantly degrade performance
• Surprisingly, irrelevant documents boost code generation by up to 15.6%

Retrieval Precision:
• Performance varies dramatically by task
• QA tasks need 20-100% retrieval recall
• Perfect retrieval still fails up to 12% of the time on previously correct instances

Document Selection:
• More documents ≠ better results
• Adding documents can cause errors on previously correct samples
• Performance degradation increases ~1% per 5 additional documents in code tasks

Prompt Engineering:
• Most advanced prompting techniques underperform simple zero-shot prompts
• Technique effectiveness varies significantly across models and tasks
• Complex prompts excel at difficult problems but struggle with simple ones

>> Technical Implementation
The study utilized:
• Multiple retrievers including BM25, dense retrievers, and specialized models
• Comprehensive corpus of 70,956 unique API documents
• Over 200,000 API calls and 1,000+ GPU hours of computation
• Sophisticated evaluation metrics tracking both correctness and system confidence

💡 Key takeaway: RAG system optimization requires careful balancing of multiple factors - there's no one-size-fits-all solution.
  • 1 reply
·
singhsidhukuldeep 
posted an update 14 days ago
view post
Post
1798
Exciting new research alert! 🚀 A groundbreaking paper titled "Understanding LLM Embeddings for Regression" has just been released, and it's a game-changer for anyone working with large language models (LLMs) and regression tasks.

Key findings:

1. LLM embeddings outperform traditional feature engineering in high-dimensional regression tasks.

2. LLM embeddings preserve Lipschitz continuity over feature space, enabling better regression performance.

3. Surprisingly, factors like model size and language understanding don't always improve regression outcomes.

Technical details:

The researchers used both T5 and Gemini model families to benchmark embedding-based regression. They employed a key-value JSON format for string representations and used average-pooling to aggregate Transformer outputs.

The study introduced a novel metric called Normalized Lipschitz Factor Distribution (NLFD) to analyze embedding continuity. This metric showed a high inverse relationship between the skewedness of the NLFD and regression performance.

Interestingly, the paper reveals that applying forward passes of pre-trained models doesn't always significantly improve regression performance for certain tasks. In some cases, using only vocabulary embeddings without a forward pass yielded comparable results.

The research also demonstrated that LLM embeddings are dimensionally robust, maintaining strong performance even with high-dimensional data where traditional representations falter.

This work opens up exciting possibilities for using LLM embeddings in various regression tasks, particularly those with high degrees of freedom. It's a must-read for anyone working on machine learning, natural language processing, or data science!
singhsidhukuldeep 
posted an update 16 days ago
view post
Post
2069
Exciting breakthrough in E-commerce Recommendation Systems!

Just read a fascinating paper from @eBay 's research team on "LLM-PKG" - a novel approach that combines Large Language Models with Product Knowledge Graphs for explainable recommendations.

Here's what makes it groundbreaking:

>> Technical Architecture
- The system uses a two-module approach: offline construction and online serving
- LLM generates initial product relationships and rationales, which are transformed into RDF triplets (Subject, Predicate, Object) to build the knowledge graph
- The system employs rigorous validation using LLM-based scoring (1-10 scale) to evaluate recommendation quality and prune low-quality nodes (score < 6)

>> Under the Hood
- Product mapping uses BERT embeddings and KNN indexing for semantic matching between LLM recommendations and actual inventory
- The system caches graph triplets in key-value databases for lightning-fast retrieval during online serving
- Supports both item-centric and user-centric recommendation scenarios

>> Real-World Impact
The A/B testing results are impressive:
- 5.19% increase in clicks
- 7.59% boost in transactions
- 8.56% growth in Gross Merchandise Bought
- 10.84% increase in ad revenue

This is a game-changer for e-commerce platforms looking to provide transparent, explainable recommendations while maintaining high performance at scale.
singhsidhukuldeep 
posted an update 18 days ago
view post
Post
1251
Exciting breakthrough in AI Recommendation Systems! Just read a fascinating paper from Meta AI and UW-Madison researchers on unifying generative and dense retrieval methods for recommendations.

The team introduced LIGER (LeveragIng dense retrieval for GEnerative Retrieval), a novel hybrid approach that combines the best of both worlds:

Key Technical Innovations:
- Integrates semantic ID-based generative retrieval with dense embedding methods
- Uses a T5 encoder-decoder architecture with 6 layers, 6 attention heads, and 128-dim embeddings
- Processes item attributes through sentence-T5-XXL for text representations
- Employs a dual-objective training approach combining cosine similarity and next-token prediction
- Implements beam search with size K for candidate generation
- Features an RQ-VAE with 3-layer MLP for semantic ID generation

Performance Highlights:
- Significantly outperforms traditional methods on cold-start recommendations
- Achieves state-of-the-art results on major benchmark datasets (Amazon Beauty, Sports, Toys, Steam)
- Reduces computational complexity from O(N) to O(tK) where t is semantic ID count
- Maintains minimal storage requirements while improving recommendation quality

The most impressive part? LIGER effectively solves the cold-start problem that has long plagued recommendation systems while maintaining computational efficiency.

This could be a game-changer for e-commerce platforms and content recommendation systems!

What are your thoughts on hybrid recommendation approaches?
reach-vb 
posted an update 18 days ago
view post
Post
3193
VLMs are going through quite an open revolution AND on-device friendly sizes:

1. Google DeepMind w/ PaliGemma2 - 3B, 10B & 28B: google/paligemma-2-release-67500e1e1dbfdd4dee27ba48

2. OpenGVLabs w/ InternVL 2.5 - 1B, 2B, 4B, 8B, 26B, 38B & 78B: https://huggingface.co/collections/OpenGVLab/internvl-25-673e1019b66e2218f68d7c1c

3. Qwen w/ Qwen 2 VL - 2B, 7B & 72B: Qwen/qwen2-vl-66cee7455501d7126940800d

4. Microsoft w/ FlorenceVL - 3B & 8B: https://huggingface.co/jiuhai

5. Moondream2 w/ 0.5B: https://huggingface.co/vikhyatk/

What a time to be alive! 🔥
singhsidhukuldeep 
posted an update 19 days ago
view post
Post
280
Exciting breakthrough in Search Engine Technology! Just read a fascinating paper on "Best Practices for Distilling Large Language Models into BERT for Web Search Ranking" from @TencentGlobal

Game-Changing Innovation: DisRanker
A novel distillation pipeline that combines the power of Large Language Models with BERT's efficiency for web search ranking - now deployed in commercial search engines!

Key Technical Highlights:
• Implements domain-specific Continued Pre-Training using clickstream data, treating queries as inputs to generate clicked titles and summaries
• Uses an end-of-sequence token to represent query-document pairs during supervised fine-tuning
• Employs hybrid Point-MSE and Margin-MSE loss for knowledge distillation, optimizing both absolute scores and relative rankings

Under the Hood:
- The system first pre-trains on massive clickstream data (59M+ query-document pairs)
- Transfers ranking expertise from a 7B parameter LLM to a compact BERT model
- Reduces inference latency from ~100ms to just 10ms while maintaining performance
- Achieves significant improvements:
• +0.47% PageCTR
• +0.58% UserCTR
• +1.2% Dwell Time

Real-World Impact:
Successfully integrated into production search systems as of February 2024, demonstrating that academic research can translate into practical industry solutions

What are your thoughts on this breakthrough?
Duskfallcrew 
posted an update 20 days ago
view post
Post
1309
So this thing about quotas?
I checked.
SOMEHOW i'm uhh
Not even close on main, probably over on my org but what can you do?
You never get unlimited.

Never have and never will :D
·
singhsidhukuldeep 
posted an update 20 days ago
view post
Post
378
Exciting Research Alert: Revolutionizing Recommendation Systems with PSL (Pairwise Softmax Loss)!

I just read a fascinating paper that introduces PSL - a groundbreaking approach to improve recommendation systems. Here's why this matters:

>> Key Innovations

Core Concept: PSL reimagines the traditional Softmax Loss by viewing it through a pairwise perspective, addressing two critical limitations of current systems:
- The loose connection between Softmax Loss and ranking metrics like DCG
- High sensitivity to false negative instances

Technical Implementation:
- Replaces exponential functions with alternative activation functions (Tanh, Atan, ReLU)
- Reformulates loss calculation from a pairwise perspective
- Integrates Distributionally Robust Optimization (DRO) principles

>> Real-World Impact

Enhanced Performance:
- Tighter surrogate for ranking metrics
- Better balance in data contribution weights
- Improved robustness against false negatives
- Superior handling of out-of-distribution scenarios

Practical Applications:
- E-commerce recommendations
- Content discovery systems
- Personalized service platforms

>> Implementation Benefits

The beauty of PSL lies in its simplicity - it requires minimal code modifications while delivering significant improvements in:
- Recommendation accuracy
- System robustness
- Training stability
- Distribution shift handling

This research opens new possibilities for building more reliable and accurate recommendation systems. The code is available on GitHub for those interested in implementation.

What are your thoughts on this approach? Have you encountered similar challenges in recommendation systems?
lorraine2 
posted an update 20 days ago
view post
Post
1203
New NVIDIA paper: ⚡ Multi-student Diffusion Distillation for Better One-step Generators ⚡

Do you want to make your diffusion models (a) run in a single step, (b) run with a smaller model, and (c) have improved quality simultaneously? Check out our multi-student distillation (MSD) method, which is simple and applicable to most diffusion models! The only catch is now we have to distill (and store) a mixture-of-expert student generators.

Explore the MSD project page to learn more: https://research.nvidia.com/labs/toronto-ai/MSD/

Work led by Yanke Song along with Weili Nie, Karsten Kreis and James Lucas

Check out more work from the Toronto AI Lab here: https://research.nvidia.com/labs/toronto-ai/
  • 1 reply
·
singhsidhukuldeep 
posted an update 21 days ago
view post
Post
1301
Exciting breakthrough in Document AI! Researchers from UNC Chapel Hill and Bloomberg have developed M3DocRAG, a revolutionary framework for multi-modal document understanding.

The innovation lies in its ability to handle complex document scenarios that traditional systems struggle with:
- Process 40,000+ pages across 3,000+ documents
- Answer questions requiring information from multiple pages
- Understand visual elements like charts, tables, and figures
- Support both closed-domain (single document) and open-domain (multiple documents) queries

Under the hood, M3DocRAG operates through three sophisticated stages:

>> Document Embedding:
- Converts PDF pages to RGB images
- Uses ColPali to project both text queries and page images into a shared embedding space
- Creates dense visual embeddings for each page while maintaining visual information integrity

>> Page Retrieval:
- Employs MaxSim scoring to compute relevance between queries and pages
- Implements inverted file indexing (IVFFlat) for efficient search
- Reduces retrieval latency from 20s to under 2s when searching 40K+ pages
- Supports approximate nearest neighbor search via Faiss

>> Question Answering:
- Leverages Qwen2-VL 7B as the multi-modal language model
- Processes retrieved pages through a visual encoder
- Generates answers considering both textual and visual context

The results are impressive:
- State-of-the-art performance on MP-DocVQA benchmark
- Superior handling of non-text evidence compared to text-only systems
- Significantly better performance on multi-hop reasoning tasks

This is a game-changer for industries dealing with large document volumes—finance, healthcare, and legal sectors can now process documents more efficiently while preserving crucial visual context.
·