Massachusetts Institute of Technology · 30 records

dateidtitleauthorsvenue↑
2026-11-182611.23219Do LLM Agents Still Need to Be Told How to Self-Improve?Shobhita Sundaram et al.arXiv5
2026-11-18W7135230687Language model teams as distributed systemsElizabeth Mieczkowski et al.Proceedings of the National Academy of Sciences
2026-11-162611.17878DySENSE: Dynamic Spatiotemporal ENergy Synthesis and Emulation with Satellite ImageryKailai Sun et al.arXiv23
2026-11-12W4400480772Quantitative measurement of viscosity in two-dimensional electron fluidsYihang Zeng et al.Science
2026-11-05W4416284040Majorana edge reconstruction and the ν = 5/2 non-Abelian thermal Hall puzzleTevž Lotrič et al.Proceedings of the National Academy of Sciences
2026-11-01W4415354832Industrialization drives convergent microbiome and host physiological shifts in the human metaorganismMathilde Poyet et al.Cell
2026-10-31W7224993945The Lumina Project: The Demographics of Active Galactic Nuclei from Quasars to Little Red Dots at z ≥ 3Xuejian Shen et al.Monthly Notices of the Royal Astronomical Society
2026-10-282610.38331Multi-Token Prediction Done RightJayden TeoharXiv15
2026-10-16W7127326285Efficient and accurate steering of large language models through attention-guided feature learningParmida Davarmanesh et al.Proceedings of the National Academy of Sciences
2026-10-14W4415089841Laboratory Measurements of Energy Partitioning and Anomalous Electron Heating in Magnetized, Perpendicular Collisionless ShocksV. Valenzuela-Villaseca et al.The Astrophysical Journal
2026-10-082610.03799StepCAD: Mesh-to-CAD Code Generation via LLM Policy and Geometry-Guided SearchGhadi Nehme et al.arXiv5
2026-10-062610.06851Base Models Can Reason By Taking a Cue From Training DataSophie L. Wang et al.arXiv21
2026-10-052609.36529Triadic Linear Attention: Three-Dimensional Recurrent States for Long-Context Sequence ModelingOliver Sieberling et al.arXiv19
2026-10-052610.02126Local Support LearningAssaf Ben-Kish et al.arXiv7
2026-09-292609.36246Learning from Teacher Continuations at Student StatesHaojin Wang et al.arXiv41
2026-09-152609.15635ModaLens: Measuring Image Sensitivity in Report-Conditioned Medical VLMsSebastián Andrés Cajas Ordóñez et al.arXiv6
2026-09-142609.10728Towards a Deterministic Math Solver for Clinical Language ModelsFelipe Ocampo Osorio et al.arXiv2
2026-09-102509.01809The Price of Sparsity: Sufficient Conditions for Sparse Recovery using Sparse and Sparsified MeasurementsYoussef Chaabouni et al.arXiv2
2026-08-172608.13567Modular Cognitive Architecture Emerges in Large Language ModelsPengrui Han et al.arXiv17
2026-08-172608.03744Agents Catching Agents: Shortcut Cascades and Benchmark Gaming in Clinical Multi-Agent SystemsSebastián Andrés Cajas Ordóñez et al.arXiv6
2026-08-042608.01462Loud or Silent? A Reusable Framework for Per-Modality Failure Analysis in Multimodal Clinical AIQuang Bui et al.arXiv4
2026-07-142607.07470A Theory of Contrastive Learning with Natural ImagesAntonio Torralba et al.arXiv9
2026-07-022607.00924Graph-Native Reinforcement Learning Enables Traceable Scientific Hypothesis Generation through Conceptual RecombinationSubhadeep Pal et al.arXiv8
2026-06-182606.19336Learning User Simulators with Turing RewardsYingshan Susan Wang et al.arXiv2
2026-06-122606.13681EvoArena: Tracking Memory Evolution for Robust LLM Agents in Dynamic EnvironmentsJundong Xu et al.arXiv143
2026-06-032605.23895From Activation to Causality: Discovery of Causal Visual Representations in the Human BrainYuval Golbari et al.arXiv52
2026-05-282605.26032Everything at Every Scale: Scale-Invariant Diffusion with Continuous Super-ResolutionZixin Jessie Chen et al.arXiv13
2026-05-202605.18101SENSE: Satellite-based ENergy Synthesis for Sustainable EnvironmentKailai Sun et al.arXiv12
2026-05-202605.19932PEEK: Context Map as an Orientation Cache for Long-Context LLM AgentsZhuohan Gu et al.arXiv4
2026-05-122605.09196RigidFormer: Learning Rigid Dynamics using TransformersZhiyang Dou et al.arXiv13