Pratyay Banerjee

Neilblaze's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes

upvoted a collection about 7 hours ago

Qwen2.5-VL

Collection

Vision-language model series based on Qwen2.5 • 3 items • Updated 4 days ago • 287

upvoted a paper about 8 hours ago

ComplexFuncBench: Exploring Multi-Step and Constrained Function Calling under Long-Context Scenario

Paper • 2501.10132 • Published 14 days ago • 17

upvoted a paper 4 days ago

Chain-of-Retrieval Augmented Generation

Paper • 2501.14342 • Published 7 days ago • 34

upvoted an article 6 days ago

view article

Article

We now support VLMs in smolagents!

7 days ago

• 65

upvoted 3 papers 9 days ago

Video Depth Anything: Consistent Depth Estimation for Super-Long Videos

Paper • 2501.12375 • Published 9 days ago • 22

UI-TARS: Pioneering Automated GUI Interaction with Native Agents

Paper • 2501.12326 • Published 9 days ago • 47

Evolving Deeper LLM Thinking

Paper • 2501.09891 • Published 14 days ago • 100

upvoted an article 12 days ago

view article

Article

Introducing smolagents: simple agents that write actions in code.

Dec 31, 2024

• 536

upvoted 2 articles 13 days ago

view article

Article

Train 400x faster Static Embedding Models with Sentence Transformers

16 days ago

• 129

view article

Article

Llama-3.1-Storm-8B: Improved SLM with Self-Curation + Model Merging

By •

Aug 19, 2024

• 76

upvoted 8 papers 14 days ago

OmniThink: Expanding Knowledge Boundaries in Machine Writing through Thinking

Paper • 2501.09751 • Published 14 days ago • 47

FAST: Efficient Action Tokenization for Vision-Language-Action Models

Paper • 2501.09747 • Published 14 days ago • 23

HALoGEN: Fantastic LLM Hallucinations and Where to Find Them

Paper • 2501.08292 • Published 16 days ago • 17

Diffusion Adversarial Post-Training for One-Step Video Generation

Paper • 2501.08316 • Published 16 days ago • 32

MiniMax-01: Scaling Foundation Models with Lightning Attention

Paper • 2501.08313 • Published 16 days ago • 271

Multimodal LLMs Can Reason about Aesthetics in Zero-Shot

Paper • 2501.09012 • Published 15 days ago • 10

Towards Best Practices for Open Datasets for LLM Training

Paper • 2501.08365 • Published 16 days ago • 51

MMDocIR: Benchmarking Multi-Modal Retrieval for Long Documents

Paper • 2501.08828 • Published 15 days ago • 30

upvoted a paper 15 days ago

Graph Mamba: Towards Learning on Graphs with State Space Models

Paper • 2402.08678 • Published Feb 13, 2024 • 15

upvoted a collection 15 days ago

Granite Time Series Models

Collection

A collection of time series models trained by IBM licensed under Apache 2.0 license. • 5 items • Updated Dec 18, 2024 • 26