KV Cache Recycling to Expand Usable Context Capacity in Low Parameter LLMs
Paper • 2512.11851 • Published • 1
AI & ML interests
None defined yet.
Recent Activity
View all activity
parkneurals
authored a
paper 26 days ago
1aurent
authored a
paper about 1 month ago
Jackmin108
authored a
paper 2 months ago
1aurent
authored a
paper 3 months ago
JingzeShi
authored 2
papers 3 months ago
JingzeShi
submitted a
paper to Daily Papers 3 months ago
Johannes
authored a
paper 4 months ago
kenobi
authored 3
papers 5 months ago
On Invariance Penalties for Risk Minimization
Paper • 2106.09777 • Published
Generating (Factual?) Narrative Summaries of RCTs: Experiments with Neural Multi-Document Summarization
Paper • 2008.11293 • Published
Bayesian Deep Learning for Exoplanet Atmospheric Retrieval
Paper • 1811.03390 • Published
JingzeShi
authored a
paper 9 months ago
wubingheng
authored a
paper 9 months ago
Post
4108
Trainable selective sampling and sparse attention kernels are indispensable in the era of context engineering. We hope our work will be helpful to everyone! 🤗
Trainable Dynamic Mask Sparse Attention (2508.02124)
Trainable Dynamic Mask Sparse Attention (2508.02124)
wubingheng
authored a
paper 9 months ago
Post
4329
Hey all
Finally it's happening. DeepGit lite is back now, running on cpu only devices. Just smartly search across Github and spin up conversational agents in the background and have grounded conversation with repositories
Try it out now!!!! zamal/DeepGit
Finally it's happening. DeepGit lite is back now, running on cpu only devices. Just smartly search across Github and spin up conversational agents in the background and have grounded conversation with repositories
Try it out now!!!! zamal/DeepGit
- 1 reply
Post
1666
Say hallo to GermaNER 💪– a lightweight, high-accuracy NER model for German texts, powered by XLM-RoBERTa + LoRA adapters!
⚡ Fast, efficient, and open-source – perfect for tagging names, places & orgs in real-world German data.
Try it now on Hugging Face 👉 fau/GermaNER
⚡ Fast, efficient, and open-source – perfect for tagging names, places & orgs in real-world German data.
Try it now on Hugging Face 👉 fau/GermaNER
Post
4444
🚀 Videoxity is live on Hugging Face! 🎞️
A powerful, modular toolkit for intelligent video manipulation and scene editing.
With Videoxity, you can:
🖼️ Auto-caption keyframes with BLIP
🧠 Filter scenes using natural language (e.g. “remove dog scenes”)
✂️ Seamlessly trim videos with FFmpeg
📊 Generate frame-based summaries
Powered by Groq LLM + LangChain, OpenCV, BLIP, and SentenceTransformers, Videoxity bridges vision and language to give developers full control over video content.
🔧 Built for developers. Feedback welcome!
👉 Try it out here fau/videoxity
A powerful, modular toolkit for intelligent video manipulation and scene editing.
With Videoxity, you can:
🖼️ Auto-caption keyframes with BLIP
🧠 Filter scenes using natural language (e.g. “remove dog scenes”)
✂️ Seamlessly trim videos with FFmpeg
📊 Generate frame-based summaries
Powered by Groq LLM + LangChain, OpenCV, BLIP, and SentenceTransformers, Videoxity bridges vision and language to give developers full control over video content.
🔧 Built for developers. Feedback welcome!
👉 Try it out here fau/videoxity
JingzeShi
authored a
paper 11 months ago
samsja
authored a
paper 11 months ago