AMIRAN KURTANIDZE

sunsulaki's activity

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

upvoted a collection about 13 hours ago

⛵ Vela 1.0

Collection

The model family for intelligent routing. • 11 items • Updated about 23 hours ago • 15

upvoted a paper 7 days ago

When Models Edit Too Much: On the Fidelity of Minimal Code Edits

Paper • 2609.04061 • Published 13 days ago • 10

upvoted a paper 12 days ago

Repo-To-Skill: Distilling GitHub Repositories Into AI4AI Skills

Paper • 2609.02749 • Published 14 days ago • 549

upvoted a paper 18 days ago

JIT-Agent: Scaling Harness Intelligence via Just-in-Time Harness Evolution

Paper • 2608.25593 • Published 21 days ago • 117

upvoted an article 21 days ago

view article

Article

Zero-Shot Text Classification in 2026: NLI, Embeddings, Rerankers, or LLMs?

• 

aarabil

•

Aug 9

• 2

upvoted 2 papers 24 days ago

On-Policy Self-Distillation without Any Supervision

Paper • 2608.06296 • Published Aug 9 • 220

BDH-CQ: In-Context Learning with Recurrent Latent Reasoning

Paper • 2608.09888 • Published Aug 10 • 781

upvoted a paper about 1 month ago

MatrAIx: Simulating the World with 8.3 Billion Persona Agents

Paper • 2608.04205 • Published Aug 4 • 54

upvoted a paper about 2 months ago

GLiNER: Generalist Model for Named Entity Recognition using Bidirectional Transformer

Paper • 2311.08526 • Published Nov 14, 2023 • 15

upvoted 4 papers 2 months ago

SkillHone: A Harness for Continual Agent Skill Evolution Through Persistent Decision History

Paper • 2606.08671 • Published Jun 23 • 48

Hierarchical Sparse Attention Done Right: Toward Infinite Context Modeling

Paper • 2607.02980 • Published Jul 3 • 85

DOPD: Dual On-policy Distillation

Paper • 2606.30626 • Published Jun 29 • 116

Orca: The World is in Your Mind

Paper • 2606.30534 • Published Jun 29 • 508

upvoted an article 3 months ago

view article

Article

80TB+ of astronomy for the HDD-poor: crossmatch the Multimodal Universe from your laptop

• 

hugging-science

•

Jun 29

• 25

upvoted 6 papers 3 months ago

Nemotron 3 Ultra: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning

Paper • 2606.15007 • Published Jun 12 • 20

APPO: Agentic Procedural Policy Optimization

Paper • 2606.12384 • Published Jun 10 • 79

On the Geometry of On-Policy Distillation

Paper • 2606.07082 • Published Jun 5 • 75

MaxProof: Scaling Mathematical Proof with Generative-Verifier RL and Population-Level Test-Time Scaling

Paper • 2606.13473 • Published Jun 11 • 97

ResearchClawBench: A Benchmark for End-to-End Autonomous Scientific Research

Paper • 2606.07591 • Published May 28 • 105

Toward Generalist Autonomous Research via Hypothesis-Tree Refinement

Paper • 2606.11926 • Published Jun 10 • 131