| [ | |
| { | |
| "Name": "adaptive_block_size", | |
| "Title": "Adaptive Block Size: Dynamic Context Window Adjustment for Efficient Training", | |
| "Experiment": "Modify the model to dynamically adjust its block size during training, starting with a smaller block size and gradually increasing it. This could potentially lead to faster initial training and better long-range dependency learning.", | |
| "Interestingness": 6, | |
| "Feasibility": 4, | |
| "Novelty": 4, | |
| "novel": true | |
| }, | |
| { | |
| "Name": "layerwise_learning_rates", | |
| "Title": "Layer-wise Learning Rate Adaptation: Optimizing Training Dynamics in Transformer Models", | |
| "Experiment": "Implement layer-wise learning rates, where each transformer layer has its own learning rate. Modify the configure_optimizers function to assign different learning rates to different layers, with deeper layers having lower learning rates. Compare the training dynamics, convergence speed, and final performance with the baseline model.", | |
| "Interestingness": 4, | |
| "Feasibility": 6, | |
| "Novelty": 2, | |
| "novel": true | |
| }, | |
| { | |
| "Name": "vi_t_pruning_benchmark_execution", | |
| "Title": "Bayesian Scaffolded Sparsity: A Primitifal Approach to ViTF Compression against Alternate Mechanisms", | |
| "Experiment": [ | |
| "Design efficient techniques that use techniques like hard reset for preventing over compression", | |
| "Regular monitor & report of weights' magnitudes & norms as early detection" | |
| ], | |
| "Interestingness": 8, | |
| "Feasibility": 9, | |
| "Novelty": 7, | |
| "novel": true | |
| }, | |
| { | |
| "Name": "In-depth_SEqEembhead_expansion_evaluation", | |
| "Title": "Publishing comprehensive analysis on extensive gridsearch experimentation: Sequence Length vs Embedding Layer Dimensions & Attention Heads for T5 Models \u2013 Benchmarked Results across Various NLP standards & Practical Implications including Stability and Computation Efficiency.", | |
| "Experiment": [ | |
| "Present early-stage findings at a recognized neural processing symposia, eg NeurIPS/TACL/MAS etc." | |
| ], | |
| "Interestingness": 8, | |
| "Feasibility": 7, | |
| "Novelty": 9, | |
| "novel": true | |
| } | |
| ] |