Skip to yearly menu bar Skip to main content


Search All 2024 Events
 

34 Results

<<   <   Page 1 of 3   >   >>
Poster
Thu 2:30 An amortized approach to non-linear mixed-effects modeling based on neural posterior estimation
Jonas Arruda · Yannik Schälte · Clemens Peiter · Olga Teplytska · Ulrich Jaehde · Jan Hasenauer
Workshop
Learning high-dimensional mixed models via amortized variational inference
Priscilla Ong · Manuel Haussmann · Harri Lähdesmäki
Poster
Wed 2:30 Efficient Adaptation in Mixed-Motive Environments via Hierarchical Opponent Modeling and Planning
Yizhe Huang · Anji Liu · Fanqi Kong · Yaodong Yang · Song-Chun Zhu · Xue Feng
Poster
Transformers Implement Functional Gradient Descent to Learn Non-Linear Functions In Context
Xiang Cheng · Yuxin Chen · Suvrit Sra
Poster
Thu 2:30 Universality of Linear Recurrences Followed by Non-linear Projections: Finite-Width Guarantees and Benefits of Complex Eigenvalues
Antonio Orvieto · Soham De · Caglar Gulcehre · Razvan Pascanu · Samuel Smith
Poster
Tue 4:30 Characteristic Guidance: Non-linear Correction for Diffusion Model at Large Guidance Scale
Candi Zheng · Yuan LAN
Poster
Wed 4:30 Exact Conversion of In-Context Learning to Model Weights in Linearized-Attention Transformers
Brian Chen · Tianyang Hu · Hui Jin · Hwee Lee · Kenji Kawaguchi
Poster
Tue 2:30 The Linear Representation Hypothesis and the Geometry of Large Language Models
Kiho Park · Yo Joong Choe · Victor Veitch
Workshop
Implicit Optimization Bias of Next-token Prediction in Linear Models
Christos Thrampoulidis
Poster
Wed 4:30 Linear Alignment: A Closed-form Solution for Aligning Human Preferences without Tuning and Feedback
songyang gao · Qiming Ge · Wei Shen · Shihan Dou · Junjie Ye · Xiao Wang · Rui Zheng · Yicheng Zou · Zhi Chen · Hang Yan · Qi Zhang · Dahua Lin
Poster
Thu 4:30 A Unified Framework for Learning with Nonlinear Model Classes from Arbitrary Linear Samples
Ben Adcock · Juan Cardenas · Nick Dexter
Workshop
Task Descriptors Help Transformers Learn Linear Models In-Context
Ruomin Huang · Rong Ge