NVIDIA-labs OO Agents: Native Python Object-Oriented Agents
Paper • 2607.20709 • Published • 21
Alessio Devoto
aledevo
AI & ML interests
Efficient AI; Interpretability; AI for Scientific Discovery
Recent Activity
authored a paper 1 day ago
NVIDIA-labs OO Agents: Native Python Object-Oriented Agents authored a paper 1 day ago
Subliminal Clocks: Latent Time Modelling in Diffusion Language Models authored a paper 1 day ago
Attention Sinks in Diffusion Language ModelsOrganizations
authored 5
papers 1 day ago
Subliminal Clocks: Latent Time Modelling in Diffusion Language Models
Paper • 2607.01774 • Published • 38
Attention Sinks in Diffusion Language Models
Paper • 2510.15731 • Published • 50
Expected Attention: KV Cache Compression by Estimating Attention from Future Queries Distribution
Paper • 2510.00636 • Published • 1
Q-Filters: Leveraging QK Geometry for Efficient KV Cache Compression
Paper • 2503.02812 • Published • 10
upvoted a paper 1 day ago
upvoted a paper 2 days ago
liked a
Space 4 months ago
Runtime error on your Huggingface Space
1
#14 opened 5 months ago
by 
colinhong
upvoted an article 5 months ago
Article
How NVIDIA AI-Q Reached \#1 on DeepResearch Bench I and II
nvidia
• • 34 updated a
Space 10 months ago
upvoted an article 10 months ago
Article
Controlling Language Model Generation with NVIDIA's LogitsProcessorZoo
ariG23498, aerdem4
• • 51 Upload the results of the training-free version of the method [SepLLM - ICML 2025 Paper](https://arxiv.org/abs/2412.12094) based on "meta-llama/Meta-Llama-3.1-8B-Instruct"
1
#3 opened 12 months ago
by 
Gausson
Adding KVzip results
2
#2 opened 12 months ago
by 
Jang-Hyun
Solves 500 error for some users
1
#1 opened about 1 year ago
by 
Tonic
upvoted a paper about 1 year ago
published a
Space about 1 year ago
updated a
Space about 1 year ago