James Smith

Jamessmith1's activity

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

upvoted a paper 6 days ago

Document Retrieval-Aware Chunking (D-RAC): Universal Retrieval-Aware Ingestion of Enterprise Documents via PDF Normalization and Multimodal Markdown Conversion

Paper • 2609.24220 • Published 8 days ago • 68

upvoted 4 papers 13 days ago

Grouped Value Attention: Efficient KV Caching via On-Demand Key Reconstruction

Paper • 2609.13285 • Published 21 days ago • 81

DreamX-Creator: Democratizing Native Audio-Video Generation at 2K Resolution

Paper • 2608.31106 • Published 29 days ago • 96

Feyospace-v1: How the Cyber Mercury Seven Trained Frontier Cyber Models

Paper • 2609.08418 • Published 21 days ago • 136

Knowing When Not to Reuse: Conditional Experience Transfer in Autonomous LLM Post-Training

Paper • 2608.26730 • Published Aug 27 • 155

upvoted a paper 3 months ago

Grouped Query Experts: Mixture-of-Experts on GQA Self-Attention

Paper • 2606.20945 • Published Jun 18 • 81

liked 2 models 3 months ago

nvidia/nemotron-3.5-asr-streaming-0.6b

Automatic Speech Recognition • 0.6B • Updated 18 days ago • 995k • • 1.15k

unsloth/GLM-5.2-GGUF

Text Generation • 754B • Updated Jun 23 • 337k • 645

liked a Space 3 months ago

Running

Featured

48

LFM2 MoE WebGPU

💧

48

WebGPU-accelerated Mixture of Experts

liked 2 models 3 months ago

LiquidAI/LFM2-8B-A1B-smoltalk-LoRA

Updated Jun 10 • 39 • 9

LiquidAI/LFM2.5-Embedding-350M

Sentence Similarity • 0.4B • Updated Jun 20 • 25.6k • 162

liked 5 models 5 months ago

froggeric/Qwen-Fixed-Chat-Templates

Updated 24 days ago • 1.77k

HiDream-ai/HiDream-O1-Image

Image-Text-to-Image • 9B • Updated Jun 22 • 5.74k • 551

unsloth/Qwen3.6-27B-MTP-GGUF

Image-Text-to-Text • 27B • Updated May 26 • 969k • 1.32k

FrontiersMind/Nandi-Mini-600M-Early-Checkpoint

Text Generation • 0.6B • Updated May 17 • 148 • 105

FrontiersMind/Nandi-Mini-150M-Tool-Calling

Text Generation • 0.2B • Updated May 18 • 196 • 53

upvoted a paper 5 months ago

Web Retrieval-Aware Chunking (W-RAC) for Efficient and Cost-Effective Retrieval-Augmented Generation Systems

Paper • 2604.04936 • Published Jan 8 • 26

liked 3 models 6 months ago

FrontiersMind/Nandi-Mini-150M-Instruct

Text Generation • 0.2B • Updated May 18 • 156 • 52

FrontiersMind/Nandi-Mini-150M

Text Generation • 0.2B • Updated May 15 • 524 • 142

Qwen/Qwen3.5-9B

Image-Text-to-Text • 10B • Updated Mar 2 • 9.82M • • 2.05k