
[LG] Latent Feedback Is a Compute and Data Amplifier B Huang, C Dwivedi, X Ma, A Moreno… [Institute of Foundation Models] (2026) arxiv.org/abs/2611.20404

BUPT prof | Sharing latest AI papers & insights | Join me in embracing the AI revolution! #MachineLearning #AI #Innovation

[LG] Latent Feedback Is a Compute and Data Amplifier B Huang, C Dwivedi, X Ma, A Moreno… [Institute of Foundation Models] (2026) arxiv.org/abs/2611.20404

[CL] Replicating and Extending Weight-Space Programming: Frontier LLMs Compile Programs into Weights and Read Input Layers R Goworek, A Hickey, F Nanni, M O'Reilly [The Alan Turing Institute] (2026) arxiv.org/abs/2611.21449

[CL] Decision 1.0: Towards Open Decision Foundation Models X Liu, H Zhang, A Luo, H Chen… [vLLM Semantic Router Project] (2026) arxiv.org/abs/2611.18629

[CV] The Flip Test: Video World Models Fail to Learn the World State M Luo, L Yu, A W Yu, A Cao… [Google DeepMind & UT Austin] (2026) arxiv.org/abs/2611.19822

[LG] Latent Lattice Language Models S Duggal, Z Wu, W T. Freeman, A Torralba… [MIT & Adobe] (2026) arxiv.org/abs/2611.21608

[CL] Contrastive local learning in large nonlinear analog circuits P Pandey, P Wu, D Alyahya, E Y. Ma [UC Berkeley,] (2026) arxiv.org/abs/2611.17561

[LG] Elliptic Sampling: Optimal Interpolant Schedules for Gaussians and Beyond C Becker, T Kargin, K Hassibi, A Ozdaglar… [MIT] (2026) arxiv.org/abs/2611.18542

[LG] Delayed Effects of Temporary Weight Decay in Muon Pretraining M R Arefin, R Shwartz-Ziv, E Chang… [Meta] (2026) arxiv.org/abs/2611.17876

[CL] Benchmarks Don't Talk Back: Learning Through Self-Disagreement S Abbasloo, P Cheng [Microsoft Research] (2026) arxiv.org/abs/2611.17563

[RO] Training Reasoning Models in Simulation to Natively Use Real Robots J Tang, Z Zhang, J Guo, F Zhao… [MIT & UC Berkeley] (2026) arxiv.org/abs/2611.18562

[RO] Review the Episodes, Refine the Lessons: Simple Memory Evolution for Embodied Agents Y Yao, Y Zou, X Gao, G Jiao… [Shanghai Artificial Intelligence Laboratory] (2026) arxiv.org/abs/2611.11509

[CV] Ropedia Xperience 2: A Gold Standard for Scaling Physical AI Environments and Behaviors H Li, F Hong, Z Chen, H E Pang… [Ropedia Research Team] (2026) arxiv.org/abs/2611.17060

[LG] Speculative Self-Distillation enables Efficient Knowledge Internalization S Talaei, A Bhatia, A S Moakhar, J Hübotter… [Stanford University & ETH Zürich] (2026) arxiv.org/abs/2611.12016

[AI] System Optimizations for Cost-Efficient Agent Harnesses J Park, J Yu, E Zhou, T Hong… [UC Berkeley & Northwestern University & University of Illinois at Urbana-Champaign] (2026) arxiv.org/abs/2611.12122

[AI] Evolving Infra: Agent-Adaptive LLM Serving at Scale H Kang, W Xu, Z Li, Z Du… [Georgia Institute of Technology & University of Illinois Urbana-Champaign & UC Berkeley,] (2026) arxiv.org/abs/2611.12304

[CV] UGG: Unified Generative Geometry Model A Kiruga, Z Li, R Cai, H Lillemark… [Harvard University & MIT & UC San Diego] (2026) arxiv.org/abs/2611.14440