Зайцев Кирилл

levismithru's activity

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

upvoted a paper 5 days ago

Aspire: Can Models Self-Evolve from Vague Goals?

Paper • 2608.31111 • Published Aug 31 • 274

upvoted 2 papers 6 days ago

Learning from the Self-future: On-policy Self-distillation for dLLMs

Paper • 2606.18195 • Published Jun 16 • 175

HarnessDev: Can LLMs Create and Evolve Their Own Agent Harness?

Paper • 2609.01437 • Published Sep 1 • 569

upvoted a paper 10 days ago

NeoHorse-1: Towards Recursive Self-Improvement via Agentic Post-Training with Routing Harness

Paper • 2609.08183 • Published about 1 month ago • 328

upvoted a paper 26 days ago

ENEAS: Embedding-guided Neural Ensemble for Adaptive Segmentation

Paper • 2609.03756 • Published Sep 3 • 25

upvoted 3 papers 3 months ago

Boogu-Image-0.1: Boosting Open Agentic Multimodal Generation via Understanding under a Minimal Budget

Paper • 2607.13125 • Published Jul 18 • 140

The Mirage of Optimizing Training Policies: Monotonic Inference Policies as the Real Objective for LLM Reinforcement Learning

Paper • 2606.29526 • Published Jun 28 • 52

AI translation of literary texts is "fine", but readers still prefer human translations

Paper • 2606.26040 • Published Jun 24 • 6

upvoted 4 papers 4 months ago

Looped World Models

Paper • 2606.18208 • Published Jun 16 • 81

When Does Multi-Agent RL Improve LLM Workflows? Workflow, Scale, and Policy-Sharing Tradeoffs

Paper • 2605.24202 • Published May 22 • 17

Crafter: A Multi-Agent Harness for Editable Scientific Figure Generation from Diverse Inputs

Paper • 2605.30611 • Published May 28 • 65

Claw-Anything: Benchmarking Always-On Personal Assistants with Broader Access to User's Digital World

Paper • 2605.26086 • Published May 25 • 26

upvoted 4 papers 5 months ago

Delta Attention Residuals

Paper • 2605.18855 • Published May 13 • 8

Can Muon Fine-tune Adam-Pretrained Models?

Paper • 2605.10468 • Published May 11 • 6

Revisiting DAgger in the Era of LLM-Agents

Paper • 2605.12913 • Published May 13 • 6

Mean Mode Screaming: Mean--Variance Split Residuals for 1000-Layer Diffusion Transformers

Paper • 2605.06169 • Published May 7 • 57

upvoted 4 papers 6 months ago

Act Wisely: Cultivating Meta-Cognitive Tool Use in Agentic Multimodal Models

Paper • 2604.08545 • Published Apr 9 • 41

Adam's Law: Textual Frequency Law on Large Language Models

Paper • 2604.02176 • Published Apr 2 • 109

Training a Student Expert via Semi-Supervised Foundation Model Distillation

Paper • 2604.03841 • Published Apr 4 • 10

Video Models Reason Early: Exploiting Plan Commitment for Maze Solving

Paper • 2603.30043 • Published Mar 31 • 13