| 2026-11-19 | 2611.17460 | Unfinished-Bench: Measuring Rule Violations by Persistent Agents in Realistic Work Environments | Seunghyun Lee et al. | arXiv | 8 | |
| 2026-11-13 | 2611.16905 | Factored One-sided Adam-Moment for Practical and Scalable SOAP | Jaemyung Yu et al. | arXiv | 14 | |
| 2026-10-21 | 2610.27851 | LaLa-World: Scaling Latent World Models with Natural Language Actions | Junha Song et al. | arXiv | 50 | |
| 2026-10-16 | 2610.22347 | Speculative Forcing for Efficient Autoregressive Video Generation | Hyunwook Choi et al. | arXiv | 80 | |
| 2026-10-14 | 2610.14351 | Learning Transferable World-Action Models from Task-Paired Human Videos | Jeongeun Park et al. | arXiv | 12 | |
| 2026-10-14 | 2610.16135 | Omni-Modal LLMs Know More Than They Say | Na Min An et al. | arXiv | 10 | |
| 2026-10-08 | 2610.07874 | On-Policy Distillation with Negative-Policy Rollouts | Jaehui Hwang et al. | arXiv | 21 | |
| 2026-10-08 | 2610.07659 | DLoop: Looped Speculative Decoding | Geonmo Gu et al. | arXiv | 15 | |
| 2026-09-10 | 2609.07103 | Revisiting Complete Reasoning Traces for Post-Training | Jaehui Hwang et al. | arXiv | 20 | |
| 2026-09-07 | 2609.04753 | Beneath the Surface of Chains-of-Thought: A Mechanistic Interpretation of Reasoning Operations in LLMs | Seogyeong Jeong et al. | arXiv | 14 | |
| 2026-09-01 | 2608.30135 | Verification-Aware Training for Speculative Decoding | Geonmo Gu et al. | arXiv | 10 | |
| 2026-08-07 | 2608.05802 | On-Policy Delta Distillation for Multilingual Math Reasoning | Byeongho Heo et al. | arXiv | 10 | |
| 2026-07-20 | 2607.15161 | On-Policy Delta Distillation | Byeongho Heo et al. | arXiv | 35 | |
| 2026-06-16 | 2606.15631 | Retrieve, Don't Retrain: Extending Vision Language Action Models to New Tasks at Test Time | Jeongeun Park et al. | arXiv | 16 | |