Summary of Meta-ttt: a Meta-learning Minimax Framework For Test-time Training, by Chen Tao et al.
Meta-TTT: A Meta-learning Minimax Framework For Test-Time Trainingby Chen Tao, Li Shen, Soumik MondalFirst submitted…
Summary of Towards a Theoretical Understanding Of Synthetic Data in Llm Post-training: a Reverse-bottleneck Perspective, by Zeyu Gan et al.
Towards a Theoretical Understanding of Synthetic Data in LLM Post-Training: A Reverse-Bottleneck Perspectiveby Zeyu Gan,…
Summary of Extending Contextual Self-modulation: Meta-learning Across Modalities, Task Dimensionalities, and Data Regimes, by Roussel Desmond Nzoyem et al.
Extending Contextual Self-Modulation: Meta-Learning Across Modalities, Task Dimensionalities, and Data Regimesby Roussel Desmond Nzoyem, David…
Summary of Reducing Variance in Meta-learning Via Laplace Approximation For Regression Tasks, by Alfredo Reichlin et al.
Reducing Variance in Meta-Learning via Laplace Approximation for Regression Tasksby Alfredo Reichlin, Gustaf Tegnér, Miguel…
Summary of Mitigating Copy Bias in In-context Learning Through Neuron Pruning, by Ameen Ali et al.
Mitigating Copy Bias in In-Context Learning through Neuron Pruningby Ameen Ali, Lior Wolf, Ivan TitovFirst…
Summary of Phympgn: Physics-encoded Message Passing Graph Network For Spatiotemporal Pde Systems, by Bocheng Zeng et al.
PhyMPGN: Physics-encoded Message Passing Graph Network for spatiotemporal PDE systemsby Bocheng Zeng, Qi Wang, Mengtao…
Summary of On Expressive Power Of Looped Transformers: Theoretical Analysis and Enhancement Via Timestep Encoding, by Kevin Xu and Issei Sato
On Expressive Power of Looped Transformers: Theoretical Analysis and Enhancement via Timestep Encodingby Kevin Xu,…
Summary of Equivariant Score-based Generative Models Provably Learn Distributions with Symmetries Efficiently, by Ziyu Chen et al.
Equivariant score-based generative models provably learn distributions with symmetries efficientlyby Ziyu Chen, Markos A. Katsoulakis,…
Summary of Investigating the Synergistic Effects Of Dropout and Residual Connections on Language Model Training, by Qingyang Li and Weimao Ke
Investigating the Synergistic Effects of Dropout and Residual Connections on Language Model Trainingby Qingyang Li,…
Summary of Fine-grained Gradient Restriction: a Simple Approach For Mitigating Catastrophic Forgetting, by Bo Liu et al.
Fine-Grained Gradient Restriction: A Simple Approach for Mitigating Catastrophic Forgettingby Bo Liu, Mao Ye, Peter…