Article
IBM releases SOTA Granite Time Series PatchTST-FM-r2 model with commercial-friendly license
ibm-research
• • 60
Peter
Tempo14
AI & ML interests
None yet
Recent Activity
View all activity
Organizations
upvoted an article 5 days ago
upvoted a paper about 1 month ago
upvoted an article about 2 months ago
Article
Anatomy of a Frontier Lab Agent Intrusion: A Technical Timeline of the July 2026 Incident
- +2
hlarcher, XciD, raphael-gl, chris-rannou
• • 506 upvoted 2
articles 4 months ago
Article
MiniMax Goes Sparse: Decoding M3's Attention from a Single Diagram
AtlasCloud-AI
• • 11 Article
LeRobot Humanoid: An Open, Low-Cost, 3D-Printed Humanoid for Robot Learning
VirgileBatto
• • 72 upvoted a paper 5 months ago
upvoted an article 5 months ago
Article
DeepSeek-V4: a million-token context that agents can actually use
burtenshaw
• • 60 upvoted 2
papers 5 months ago
upvoted 11
papers 6 months ago
SkillClaw: Let Skills Evolve Collectively with Agentic Evolver
Paper • 2604.08377 • Published • 226
SKILL0: In-Context Agentic Reinforcement Learning for Skill Internalization
Paper • 2604.02268 • Published • 100
Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills
Paper • 2603.25158 • Published • 53
SWE-Skills-Bench: Do Agent Skills Actually Help in Real-World Software Engineering?
Paper • 2603.15401 • Published • 21
GradMem: Learning to Write Context into Memory with Test-Time Gradient Descent
Paper • 2603.13875 • Published • 37
Online Experiential Learning for Language Models
Paper • 2603.16856 • Published • 61
V-JEPA 2.1: Unlocking Dense Features in Video Self-Supervised Learning
Paper • 2603.14482 • Published • 39
Memento-Skills: Let Agents Design Agents
Paper • 2603.18743 • Published • 59
Effective Distillation to Hybrid xLSTM Architectures
Paper • 2603.15590 • Published • 34
Mixture-of-Depths Attention
Paper • 2603.15619 • Published • 83
Neural Thickets: Diverse Task Experts Are Dense Around Pretrained Weights
Paper • 2603.12228 • Published • 12