Article
CyberSecQwen-4B: Why Defensive Cyber Needs Small, Specialized, Locally-Runnable Models
•
4
Yu li
Yukkkop
AI & ML interests
None yet
Recent Activity
liked a model about 18 hours ago
oumoumad/ltx-2.3-dearchive-lora liked a model about 18 hours ago
lablab-ai-amd-developer-hackathon/CyberSecQwen-4B upvoted an article about 18 hours ago
CyberSecQwen-4B: Why Defensive Cyber Needs Small, Specialized, Locally-Runnable ModelsOrganizations
None yet
upvoted 2
articles about 18 hours ago
Article
EMO: Pretraining mixture of experts for emergent modularity
•
17
upvoted 8
papers 3 days ago
Generative Video Motion Editing with 3D Point Tracks
Paper • 2512.02015 • Published • 4
ÜberWeb: Insights from Multilingual Curation for a 20-Trillion-Token Dataset
Paper • 2602.15210 • Published • 1
Kakugo: Distillation of Low-Resource Languages into Small Language Models
Paper • 2601.14051 • Published • 1
BYOL: Bring Your Own Language Into LLMs
Paper • 2601.10804 • Published • 1
Make-it-Real: Unleashing Large Multimodal Model's Ability for Painting 3D Objects with Realistic Materials
Paper • 2404.16829 • Published • 5
Gamayun's Path to Multilingual Mastery: Cost-Efficient Training of a 1.5B-Parameter LLM
Paper • 2512.21580 • Published • 9
LiteReality: Graphics-Ready 3D Scene Reconstruction from RGB-D Scans
Paper • 2507.02861 • Published • 3
SpaceTimePilot: Generative Rendering of Dynamic Scenes Across Space and Time
Paper • 2512.25075 • Published • 16
upvoted 10
papers 6 days ago
REAM: Merging Improves Pruning of Experts in LLMs
Paper • 2604.04356 • Published • 9
Draft-Thinking: Learning Efficient Reasoning in Long Chain-of-Thought LLMs
Paper • 2603.00578 • Published • 2
DataDecide: How to Predict Best Pretraining Data with Small Experiments
Paper • 2504.11393 • Published • 20
QuaDMix: Quality-Diversity Balanced Data Selection for Efficient LLM Pretraining
Paper • 2504.16511 • Published • 23
BARE: Combining Base and Instruction-Tuned Language Models for Better Synthetic Data Generation
Paper • 2502.01697 • Published • 2
The Best Instruction-Tuning Data are Those That Fit
Paper • 2502.04194 • Published • 3
LEAD: Iterative Data Selection for Efficient LLM Instruction Tuning
Paper • 2505.07437 • Published • 2
SCAR: Efficient Instruction-Tuning for Large Language Models via Style Consistency-Aware Response Ranking
Paper • 2406.10882 • Published • 3
Clustering and Ranking: Diversity-preserved Instruction Selection through Expert-aligned Quality Estimation
Paper • 2402.18191 • Published • 2
Improving Influence-based Instruction Tuning Data Selection for Balanced Learning of Diverse Capabilities
Paper • 2501.12147 • Published • 2