Skip to content
conftrace_

gumbel softmax

9 papers

Explore in graph

Co-occurring keywords · papers mentioning both

layer selection (2) large language model (2) semi-structured sparsity (1) pruning method (1) attention mask (1) nonlinear relationship (1) gradient ascent (1) softmax approximation (1) next-word prediction (1) parameter isolation (1)

Papers

Probabilistic Group Mask Guided Discrete Optimization for Incremental Learning ICML 2025 Differentiable Combinatorial Scheduling at Scale ICML 2024 Indirectly Parameterized Concrete Autoencoders ICML 2024 InterpreTabNet: Distilling Predictive Signals from Tabular Data by Salient Feature Interpretation ICML 2024 Learnable Layer Selection and Model Fusion for Speech Self-Supervised Learning Models Interspeech 2024 MaskLLM: Learnable Semi-Structured Sparsity for Large Language Models NeurIPS 2024 A User-Adaptive Layer Selection Framework for Very Deep Sequential Recommender Models AAAI 2021 Learning to Screen for Fast Softmax Inference on Large Vocabulary Neural Networks ICLR 2019 Interpretable Textual Neuron Representations for NLP EMNLP 2018