| 2026-11-20 | 2611.26511 | Direct3D-V3: Latent-Free Diffusion Transformers in the Native Voxel Domain | Shuang Wu et al. | arXiv | 4 | |
| 2026-11-09 | 2611.12886 | Reframe: Observation-Aligned Multi-Teacher On-Policy Distillation for Agentic Visual Reasoning | Haozhi Yuan et al. | arXiv | 39 | |
| 2026-11-04 | 2611.02568 | SeMo3D: Unifying 3D Generation, Editing, and Completion via Selective Modeling | Xiaokun Sun et al. | arXiv | 5 | |
| 2026-10-26 | 2610.27103 | Omni-Woodpecker: Hallucination Correction via Evidence-Prior Rebalancing for Omni LLMs | Zijian Liu et al. | arXiv | 33 | |
| 2026-10-22 | 2610.33106 | VibeGame: Prompt-to-Game Development with AI-Native Engine and Self-Evolving Adversarial Agent Team | Wenbo Hu et al. | arXiv | 22 | |
| 2026-10-20 | 2610.26453 | Remembering Has a Price: Learning Memory Worth under Resource Constraints | Guannan Lai et al. | arXiv | 6 | |
| 2026-10-19 | 2610.14157 | OpenMobile-2: Building Versatile Mobile Agents with Scalable Environments and App-Native Tools | Chenyang Yan et al. | arXiv | 54 | |
| 2026-10-13 | 2610.12933 | Learning More by Training Less: Uncertainty-Guided Progressive Contraction for Efficient Reasoning Post-Training | Suorong Yang et al. | arXiv | 14 | |
| 2026-10-02 | 2610.01762 | OneStreamer: Unifying Perception, Memory, and Proactive Response in Streaming Video Interaction | Xiangyu Zeng et al. | arXiv | 77 | |
| 2026-10-02 | 2609.37362 | Pretrain Once, Route Anywhere: Towards a Foundation Model for LLM Routing | Guannan Lai et al. | arXiv | 9 | |
| 2026-09-21 | 2609.21619 | Calibrating Teacher--Student Discrepancy for On-Policy Distillation | Qiangqiang He et al. | arXiv | 10 | |
| 2026-08-24 | 2608.21360 | OmniAssistBench: Assistant-style Interaction Benchmark for Omni-LLMs | Xianyun Sun et al. | arXiv | 27 | |
| 2026-08-05 | 2608.02602 | AURORA-LM: Autoencoding Unified Representation for Continuous-Latent Diffusion Language Modeling | Jiajun Liang et al. | arXiv | 71 | |
| 2026-08-03 | 2607.27888 | Not All Tokens Deserve Equal Credit: Counterfactual Sensitivity Credit Reallocation for Long-CoT Reasoning | Qiangqiang He et al. | arXiv | 7 | |
| 2026-07-17 | 2607.14660 | VIABench: A Comprehensive Video Benchmark Collected from Blind Individuals for Visual Impairment Assistance | Yunfeng Liu et al. | arXiv | 5 | |
| 2026-07-08 | 2607.05511 | Light-Omni: Reflex over Reasoning in Agentic Video Understanding with Long-Term Memory | Chang Nie et al. | arXiv | 21 | |
| 2026-07-07 | 2607.03751 | Look Before You Leap: Distilling Tree Search into Action Evaluation for Frozen VLA Models | Xinyi Xie et al. | arXiv | 17 | |
| 2026-06-23 | 2606.21649 | EvoEmbedding: Evolvable Representations for Long-Context Retrieval and Agentic Memory | Chang Nie et al. | arXiv | 34 | |
| 2026-06-16 | 2606.16255 | UniDDT: Unifying Multimodal Understanding and Generation with Decoupled Diffusion Transformer | Shuai Wang et al. | arXiv | 14 | |
| 2026-06-15 | 2606.14702 | OmniVideo-100K: A Dataset for Audio-Visual Reasoning through Structured Scripts and Evidence Chains | Xinyue Cai et al. | arXiv | 32 | |
| 2026-06-15 | 2606.13657 | Dense Supervision, Sparse Updates: On the Sparsity and Geometry of On-Policy Distillation | Guo Yu et al. | arXiv | 3 | |
| 2026-06-12 | 2606.13289 | HYDRA-X: Native Unified Multimodal Models with Holistic Visual Tokenizers | Guozhen Zhang et al. | arXiv | 31 | |
| 2026-06-05 | 2606.03645 | The Shape of Addition: Geometric Structures of Arithmetic in Large Language Models | Liuyuan Wen et al. | arXiv | 6 | |
| 2026-05-19 | 2605.16893 | NGM: A Plug-and-Play Training-Free Memory Module for LLMs | Yuwen Qu et al. | arXiv | 8 | |
| 2026-05-13 | 2605.06658 | Relit-LiVE: Relight Video by Jointly Learning Environment Video | Weiqing Xiao et al. | arXiv | 3 | |