namezz/drgrpo-tis-fix2-newdata-cold-start-qwen3-8b-base-notag-keepthink_lr-3e-6-1111-step-540-hf Updated 17 days ago
namezz/drgrpo-tis-fix2-newdata-cold-start-qwen3-8b-base-notag-keepthink_lr-3e-6-1111-step-540-hf Updated 17 days ago
Presenting a Paper is an Art: Self-Improvement Aesthetic Agents for Academic Presentations Paper • 2510.05571 • Published Oct 7 • 13
The Unreasonable Effectiveness of Scaling Agents for Computer Use Paper • 2510.02250 • Published Oct 2 • 24
Soft Thinking: Unlocking the Reasoning Potential of LLMs in Continuous Concept Space Paper • 2505.15778 • Published May 21 • 18
Soft Thinking: Unlocking the Reasoning Potential of LLMs in Continuous Concept Space Paper • 2505.15778 • Published May 21 • 18