阿部拓海

terryhughes7's activity

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

upvoted a paper 2 days ago

Raven: The Harness of Harnesses for Composable Agentic Intelligence

Paper • 2609.33439 • Published 15 days ago • 675

upvoted a paper 9 days ago

Persona Dosing: Calibrated Activation Steering for Graded Trait Control

Paper • 2609.36388 • Published 14 days ago • 56

liked a Space 12 days ago

Running

Featured

893

Agent Memory Leaderboard

🧠

893

Unified memory evaluation · Results expected August 12.

liked a model 24 days ago

TokenRhythm/NeoHorse-1-9B

Text Generation • 9B • Updated Sep 10 • 8.69k • 1.02k

liked 7 models 27 days ago

moonshotai/Kimi-K2-Instruct

Text Generation • 1T • Updated Apr 23 • 321k • • 2.99k

Qwen/Qwen2.5-7B-Instruct

Text Generation • 8B • Updated Jan 12, 2025 • 7.75M • • 2.42k

mistralai/Mistral-7B-Instruct-v0.3

7B • Updated Dec 3, 2025 • 2.07M • 3.74k

TokenRhythm/NeoHorse-1-4B

Text Generation • 4B • Updated Sep 10 • 23.6k • 2.55k

meta-llama/Llama-3.1-8B-Instruct

Text Generation • 8B • Updated Sep 25, 2024 • 5.93M • • 8.34k

deepseek-ai/DeepSeek-R1

Text Generation • 684B • Updated Mar 27, 2025 • 1.12M • • 14.3k

zai-org/glm-4-9b-chat

9B • Updated Mar 13, 2025 • 55.8k • 1.32k

upvoted a paper 29 days ago

EVOHARNESSBENCH: Can Your Agents Keep Pace with an Evolving Harness?

Paper • 2609.04280 • Published Sep 3 • 32