Sign inGet started

Research Papers

Browse AI research from arXiv. Filter by category, search titles and abstracts, and keep scrolling for older papers.

Showing 25 of 1.5K results

  1. 1ChunkAct: Action Chunking for Agentic RoboticsBingxin Xu, Wenrui Bao, Xinxin Liu et al. · arXiv · 1d agocs.RO
  2. 2LoopWAM: Closed-Loop Generalist Policy Improvement from Deployment RolloutsWenxuan Guo, Yingping Liang, Zhaoguo Wang et al. · arXiv · 1d agocs.RO
  3. 3EgoExplorer: A Vision-Motion-Touch Observatory for Human Loco-Manipulation In SituYunsong Zhou, Xuekun Jiang, Haiqi Shen et al. · arXiv · 1d agocs.RO
  4. 4Dog-Breed Text-to-image Flow Matching from Pretraining to Fine-Tuning on 4 Consumer GPUsReyhaneh Esmailizadeh, Xingjian Leng, Zhanhao Liang et al. · arXiv · 1d agocs.CV
  5. 5Cepheid: Decoupling Scale from Structure for Cross-Family Motion CompletionChih-Hai Su, Tsung-Wei Ke, Yu-Lun Liu · arXiv · 1d agocs.CV
  6. 6What Matters in Quality-Aware VLA Pretraining: A Benchmark and Empirical StudyMingxuan Yan, Litian Gong, Dihong Huang et al. · arXiv · 1d agocs.RO
  7. 7Tev: Scaling Long-Horizon Agentic Environments with Dense Progress RewardsWenbo Hu, Shraman Pramanick, Krishna Kumar Singh et al. · arXiv · 1d agocs.CL
  8. 8PLAYGROUND: Progressive Layout Generation with Render-Grounded PlanningJaeho Lee, Junhwan Heo, Junghyun Park et al. · arXiv · 1d agocs.CV
  9. 9Data Free Training of Diffusion Models for Lattice Field TheoriesDennis Grinwald, Ankur Singha, Khaled Kahouli et al. · arXiv · 1d agohep-lat
  10. 10DoubtLess: Training-Free Contrastive Decoding for Efficient ReasoningMinghao Luo, Liang Chen · arXiv · 1d agocs.CL
  11. 11AesCode: Aesthetic Code Generation with Decoupled Cross-Modal RewardsXin Gao, Yifan Yang, Xin Li et al. · arXiv · 1d agocs.AI
  12. 12Hybrid Reasoning AgentsJiaru Zou, Yunzhe Qi, Sirui Chen et al. · arXiv · 1d agocs.CL
  13. 13Visual Tokens on Demand: Visual Budgeting for Scalable and Efficient Multi-Image Reasoning in Multimodal LLMsAimon Rahman, Joymallya Chakraborty, Vidit Bansal et al. · arXiv · 1d agocs.CV
  14. 14PixelMoE: Scaling Pixel-Space Diffusion with LLM-Style Mixture-of-ExpertsRuixiao Dong, Jianmin Bao, Bozhi Luan et al. · arXiv · 1d agocs.CV
  15. 15Exact Topological Compliance: Generating Persistence-Equivalent GraphsMattie Ji, Indradyumna Roy, Vikas Garg · arXiv · 1d agocs.LG
  16. 16Two Clocks: Why Larger Rollout Batches Learn Slower but Fail on Schedule in Reinforcement Learning with Verifiable RewardsYuante Li, Junwei Quan, Kai Qiu et al. · arXiv · 1d agocs.LG
  17. 17MFG: Multi-turn Feedback Guided Molecular OptimizationTrieu Nguyen, Frazier N. Baker, Ruoxi Gao et al. · arXiv · 1d agocs.AI
  18. 18WorldRecon: Generative Multi-View Mesh Reconstruction for Large-Scale 3D WorldMengchen Zhang, Yang Li, Chunshi Wang et al. · arXiv · 1d agocs.CV
  19. 19The Last Remote Sensing Model Built by Humans? Casting Any Earth Observation Task as Recursive Self-ImprovementSijie Zhao, Zeqi Zhou, Heli Qi et al. · arXiv · 1d agocs.CV
  20. 20RepProbe: Can Video Language Models Count Repeated Actions? A Diagnostic BenchmarkMahsa Khoshnoodi, Sarah Adel Bargal · arXiv · 1d agocs.CV
  21. 21LIBERO-RIG: A Hardware-Setup Robustness Benchmark for Vision-Language-Action ModelsAndrea Yaoyun Cui, Hanyu Wang, Xinyi Wang et al. · arXiv · 1d agocs.RO
  22. 22Who Improves the Robot? Toward Physical Recursive Self-ImprovementHai Zhou, Fan Yang, Zeyi Chen et al. · arXiv · 1d agocs.AI
  23. 23Fast Rates for Offline Q-Learning with KL RegularizationYize Hao, Guangxin Jiang, Shuang Qiu · arXiv · 1d agocs.LG
  24. 24Scaling Online Optimal Transport Minibatches for Flow MatchingPeter Chen, Sergey Levine · arXiv · 1d agocs.LG
  25. 25Plan-Bench: Can Existing VLMs Go Well Beyond Perception to Reason and Plan in Embodied Worlds?Juntong Feng, Qingan Liu, Jingru Dong et al. · arXiv · 1d agocs.CV

Source: the Silytics index, built from public metadata. Every entry links to its original source. Refreshed several times a day.