Lukas Cavigelli

lukasc-ch's activity

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

liked a model 1 day ago

huawei-csl/Qwen3.6-35B-A3B-MACaQ-R-GGUF

Text Generation • 35B • Updated 1 day ago • 546 • 10

authored 5 papers 1 day ago

MACaQ: Fast, Model Agnostic Calibrated Quantization for Low-Precision Weights and Activations

Paper • 2611.10649 • Published 6 days ago • 31

GitScholar: A Dataset for Predicting AI Research Impact from GitHub Engagement

Paper • 2609.26361 • Published Sep 22

Top-Theta Attention: Sparsifying Transformers by Compensated Thresholding

Paper • 2502.08363 • Published Feb 12, 2025 • 1

KVarN: Variance-Normalized KV-Cache Quantization Mitigates Error Accumulation in Reasoning Tasks

Paper • 2606.03458 • Published Jun 2 • 62

Don't be so Stief! Learning KV Cache low-rank approximation over the Stiefel manifold

Paper • 2601.21686 • Published May 29

upvoted a paper 1 day ago

MACaQ: Fast, Model Agnostic Calibrated Quantization for Low-Precision Weights and Activations

Paper • 2611.10649 • Published 6 days ago • 31

liked a Space 2 months ago

Running

97

Marigold V2: Revisiting Diffusion Transformers for Monocular Depth Estimation

🌼

97

Depth, surface normals, and albedo from a single image

upvoted a paper 2 months ago

Marigold V2: Revisiting Diffusion Transformers for Monocular Depth Estimation

Paper • 2609.08084 • Published Sep 8 • 60

liked a model 2 months ago

wanvideo/wan-3-0-video

Text-to-Video • Updated Sep 4 • 37

liked a model 4 months ago

moonshotai/Kimi-K3

Image-Text-to-Text • 2.8T • Updated Sep 2 • 773k • • 12k

updated a collection 5 months ago

Papers

Collection

3 items • Updated Jun 3 • 1

upvoted a paper 5 months ago

KVarN: Variance-Normalized KV-Cache Quantization Mitigates Error Accumulation in Reasoning Tasks

Paper • 2606.03458 • Published Jun 2 • 62

liked a model 9 months ago

huawei-csl/Qwen3-4B-PreSINQ-GGUF

Text Generation • 4B • Updated Feb 10 • 109 • 8

liked a model 11 months ago

huawei-bayerlab/windowseat-reflection-removal-v1-0

Image-to-Image • Updated Sep 13 • 47

upvoted a collection about 1 year ago

Papers

Collection

3 items • Updated Jun 3 • 1

liked 4 models about 1 year ago

huawei-csl/Qwen3-14B-4bit-SINQ

Text Generation • 9B • Updated Feb 2 • 16 • 5

huawei-csl/Qwen3-1.7B-4bit-SINQ

Text Generation • 1B • Updated Feb 2 • 32 • 5

huawei-csl/Qwen3-32B-4bit-ASINQ

Text Generation • 18B • Updated Feb 2 • 15 • 8

huawei-csl/Qwen3-32B-4bit-SINQ

Text Generation • 18B • Updated Feb 2 • 13 • 7