2023

an archive of posts from this year

Dec 19, 2023 Investigating Vision Transformer-Based Models for Closure Modeling of Fluid Dynamical Systems
Dec 12, 2023 Are Watermarked Large Language Models More Prone to Hallucinations?
Dec 12, 2023 Predicting the Future: LSTM vs Transformers for Time Series Modeling
Dec 12, 2023 Studying the benefits and limitations of sparse auto-encoders for compositional reasoning tasks
Dec 12, 2023 Solvent Encoding for solubility prediction using GNN
Dec 12, 2023 6.s898 Final Project- Investigating the biological underpinnings of latent embeddings for scRNA-seq
Dec 12, 2023 Forbidden Facts
Dec 12, 2023 Modeling Elephantfish Communication through Deep RNNs
Dec 12, 2023 Exploring Image-Supervised Contrastive Diffusion - A Comparative Analysis with Applications in Image-to-Video Generation
Dec 12, 2023 Combining Modalities for Better Molecular Representation Learning
Dec 12, 2023 Exploring Frobenius and Spectral Normalization in MLPs and Residual networks
Dec 12, 2023 Iterated Representation Learning
Dec 12, 2023 A Method for Alleviating Catastrophic Forgetting With Explainability
Dec 12, 2023 Graph Articulated Objects
Dec 12, 2023 Physics Loss
Dec 12, 2023 Diffusion Models on Low-Brightness Images
Dec 12, 2023 Semi-Supervised Domain Adaptation using Diffusion Models
Dec 12, 2023 The Effect of Activation Functions On Superposition in Toy Models
Dec 12, 2023 Gradient-Boosted Neural Wavlet Interpolation for Time Series (G-BiTS)
Dec 12, 2023 Challenges in Deep Learning Surrogates for Constrained Linear Optimization
Dec 12, 2023 Activation Patching in Vision Transformers
Dec 12, 2023 Transformer-Based Approaches for Hyperspectral Imagery in Remote Sensing
Dec 12, 2023 Learning Generals.io
Dec 12, 2023 A Comparative Study of transformer on long sequence time series data
Dec 12, 2023 Transfer Resistant Model Training
Dec 12, 2023 Sparse Autoencoders for a More Interpretable RLHF
Dec 12, 2023 Using Synthetic Data to Minimize Real Data Requirements
Dec 12, 2023 Applications of Deep Learning in Timbre Transfer
Dec 12, 2023 The Effect of Activation Functions On Superposition in Toy Models
Dec 12, 2023 Training Robust Networks
Dec 12, 2023 Imposing uniformity through Poisson flow models
Dec 12, 2023 6-DOF estimation through visual place recognition
Dec 12, 2023 Tracing the Seeds of Conflict: Advanced Semantic Parsing Techniques for Causality Detection in News Texts
Dec 12, 2023 To Encode or Not To Encode: The Case for the Encoder-free Autodecoder Architecture
Dec 12, 2023 New Synthesis Approach for Personalized LLMS
Dec 12, 2023 Augmenting Expert Domain Image Inputs for Enhancing Visual Language Models Performance
Dec 12, 2023 Embeddings for Spatio-temporal Forecasting
Dec 12, 2023 In the pursuit of cheap and robust word embeddings
Dec 12, 2023 Leveraging Representation Engineering For LLM’s In-Context-Learning
Dec 12, 2023 Reasoning with Maps: Assessing Spatial Comprehension on Maps in Pre-trained Models
Dec 12, 2023 Autoen-chorder: Predicting Musical Success With Neural Nets
Dec 12, 2023 Ensemble Learning for Mitigating Double Descent
Dec 12, 2023 Injecting Node Information via Embedding Initializations
Dec 11, 2023 Overparameterization of Neural Networks through Kernel Regression and Gaussian Processes
Dec 11, 2023 Exploring Methods for Generating Music
Dec 11, 2023 Can Constrastive Learning Recommend Me a Movie?
Dec 11, 2023 Improving CLIP Spatial Awareness Using Hard Negative Mining
Dec 11, 2023 Multimodal Commonsense
Dec 11, 2023 Exploring Univariate Time Series Anomaly Detection using VAE's
Dec 11, 2023 Graph Transformers
Dec 11, 2023 Learning a Lifted Linearization for Switched Dynamical Systems
Dec 10, 2023 Sparse Autoencoder Universality - Under What Conditions are Learned Features Consistent?
Dec 10, 2023 Optimizations of Transformers for Small-scale Performance
Dec 10, 2023 Guided Transfer Learning and Learning How to Learn: When Is It Useful?
Dec 9, 2023 Alive Scene
Dec 5, 2023 Projected fast feedforward networks
Dec 1, 2023 Understanding Linear Mode Connectivity
Dec 1, 2023 Transformers vs. RNNs: How do findings from real-world datasets relate to the theory?
Dec 1, 2023 Exploring the latent space of text-to-image diffusion models
Nov 16, 2023 Accelerating large model inference with speculative decoding - 6.s898
Nov 11, 2023 Unraveling Social Reasoning in LLMs: A Deep Dive into the Social IQA Benchmark
Nov 11, 2023 Comparing data augmentation using VAEs and denoising-VAEs for limited noisy datasets
Nov 10, 2023 Emoji3Vec
Nov 10, 2023 Modeling Human Speech Recognition with Different Network Architectures
Nov 9, 2023 Analytic, Empirical, and Monte Carlo Bayesian Methods for Uncertainty Estimation
Nov 9, 2023 Understanding LLM Attention on Useless Numbers in Word Problems (and this Title has 8 Es)
Nov 9, 2023 Cross-Lingual Fine-Tuning for Multilingual Text Embeddings
Nov 9, 2023 Learning Interpretable Features with Sparse Auto-Encoders
Nov 9, 2023 How does model size impact catastrophic forgetting in online continual learning?
Nov 9, 2023 VGAE Clustering of the Fruit Fly Connectome
Nov 9, 2023 Robust Image to Video Generation Using Contrastive Diffusion Over Latents
Nov 9, 2023 Adaptive Controller with Neural Net Equations of Motion for High-DOF Robots
Nov 9, 2023 Robustness of self-supervised ViT features in b-mode images
Nov 9, 2023 Investigating the Impact of Symmetric Optimization Algorithms on Learnability
Nov 9, 2023 Can CNN learn shapes?
Nov 8, 2023 Quantum Circuit Optimization with Graph Neural Nets
Nov 8, 2023 Structural vs Data Inductive Bias
Nov 8, 2023 From Scroll to Misbelief - Modeling the Unobservable Susceptibility to Misinformation on Social Media
Nov 8, 2023 Examining assumptions in scRNA-seq foundation model pre-training (6.S898 Final Project)
Nov 8, 2023 Increasing Context Length For Transformers
Nov 8, 2023 Zero-Shot Machine-Generated Image Detection using Sinks of Gradient Flows
Nov 8, 2023 Denoising EMG signals
Nov 8, 2023 A Deeper Look into Equivariance for Materials Data
Nov 7, 2023 Prompt to Prompt
Nov 7, 2023 Understanding Bias in Speech to Text Language Models
Nov 6, 2023 Regularization Techniques for Attention Layers in Transformer Models
Nov 5, 2023 Neural PDEs for learning local dynamics and longer temporal rollouts
Nov 1, 2023 Graph neural networks v.s. transformers for geometric graphs