Pratyay Banerjee

Neilblaze's activity

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

liked a model about 23 hours ago

meta-llama/Llama-4-Maverick-17B-128E-Instruct

Image-Text-to-Text • 402B • Updated May 22, 2025 • 26.9k • • 477

liked 2 models 2 days ago

Qwen/Qwen2.5-3B-Instruct

Text Generation • 3B • Updated Sep 25, 2024 • 8.75M • 439

Qwen/Qwen3-4B-Instruct-2507-FP8

Text Generation • 4B • Updated Sep 17, 2025 • 653k • 74

upvoted a collection 2 days ago

Qwen3.5

Collection

21 items • Updated Mar 9 • 1.49k

liked a model 2 days ago

meta-llama/Llama-2-7b-chat-hf

Text Generation • Updated Apr 17, 2024 • 439k • 4.73k

upvoted a paper 3 days ago

Learning to Retrieve from Agent Trajectories

Paper • 2604.04949 • Published 14 days ago • 66

liked a dataset 3 days ago

microsoft/OpenMementos

Viewer • Updated 4 days ago • 457k • 153 • 17

upvoted an article 3 days ago

view article

Article

Welcome Gemma 4: Frontier multimodal intelligence on device

• 
• 
• +5

11 days ago

•

822

upvoted a collection 3 days ago

DFlash

Collection

Block Diffusion for Flash Speculative Decoding • 13 items • Updated 7 days ago • 50

liked a model 3 days ago

facebook/layerskip-llama3.2-1B

Text Generation • 1B • Updated Oct 26, 2024 • 3.2k • 25

upvoted 10 papers 5 days ago

Hyperagents

Paper • 2603.19461 • Published 24 days ago • 48

Memory Intelligence Agent

Paper • 2604.04503 • Published 7 days ago • 51

Do Phone-Use Agents Respect Your Privacy?

Paper • 2604.00986 • Published 11 days ago • 9

Can LLMs Learn to Reason Robustly under Noisy Supervision?

Paper • 2604.03993 • Published 8 days ago • 40

The Model Says Walk: How Surface Heuristics Override Implicit Constraints in LLM Reasoning

Paper • 2603.29025 • Published 13 days ago • 12

Meta-Harness: End-to-End Optimization of Model Harnesses

Paper • 2603.28052 • Published 14 days ago • 16

Universal YOCO for Efficient Depth Scaling

Paper • 2604.01220 • Published 11 days ago • 17

AgentHazard: A Benchmark for Evaluating Harmful Behavior in Computer-Use Agents

Paper • 2604.02947 • Published 10 days ago • 19

Omni-SimpleMem: Autoresearch-Guided Discovery of Lifelong Multimodal Agent Memory

Paper • 2604.01007 • Published 11 days ago • 29

LightThinker++: From Reasoning Compression to Memory Management

Paper • 2604.03679 • Published 9 days ago • 32