Blog

all archives

- - - - - papers - - - - -

• The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A" 24 November 2023
• Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videos 22 November 2023
• Battle of the Backbones: A Large-Scale Comparison of Pretrained Models across Computer Vision Tasks 22 November 2023
• Grounding Visual Illusions in Language: Do Vision-Language Models Perceive Illusions Like Humans? 18 November 2023
• GROOT: Learning to Follow Instructions by Watching Gameplay Videos 17 November 2023
• Learning to Model the World with Language 16 November 2023
• Vision Transformers Need Registers 15 November 2023
• Symbol tuning improves in-context learning in language models 15 November 2023
• multitask prompted training enables zero-shot task generalization 15 November 2023
• Retrieval-Augmented Multimodal Language Modeling 03 August 2023
• Language Models are General-Purpose Interfaces 19 July 2023
• MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models 03 July 2023
• Dropout Reduces Underfitting 16 June 2023
• LIMA: Less Is More for Alignment 23 May 2023
• AttentionViz: A Global View of Transformer Attention 22 May 2023
• Playable Environments: Video Manipulation in Space and Time 28 March 2023
• Extracting Training Data from Diffusion Models 27 March 2023
• Discovering Bugs in Vision Models using Off-the-shelf Image Generation and Captioning 27 March 2023
• TASK2VEC: Task Embedding for Meta-Learning 24 March 2023
• Ignore Previous Prompt: Attack Techniques For Language Models 24 March 2023
• Explainability Via Causal Self-Talk 19 March 2023
• Decision Transformer: Reinforcement Learning via Sequence Modeling 15 March 2023
• HyperSTAR: Task-Aware Hyperparameters for Deep Networks 22 February 2023
• attention-aware learning for hyperparameter prediction in image processing pipelines 20 February 2023
• Label Distribution Learning 16 February 2023
• Training language models to follow instructions with human feedback 15 February 2023
• Reconstructing Training Data from Trained Neural Networks 31 January 2023
• Sparse and Hierarchical Masked Modeling for Convolutional Representation Learning 20 January 2023
• learning transferable visual models from natural language supervision 18 January 2023
• Mastering Diverse Domains through World Models 17 January 2023
• gpvit: a high resolution non-hierarchical vision transformer with group propagation 16 January 2023
• Where Should I Spend My FLOPS? Efficiency Evaluations of Visual Pre-training Methods 22 December 2022
• What I Cannot Predict, I Do Not Understand: A Human-Centered Evaluation Framework for Explainability Methods 22 December 2022
• Don't Lie to Me! Robust and Efficient Explainability with Verified Perturbation Analysis 05 December 2022
• Masked Autoencoders Are Scalable Vision Learners 16 November 2022
• Quantifying Attention Flow in Transformers 13 October 2022
• Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV) 21 September 2022
• This Looks Like That: Deep Learning for Interpretable Image Recognition 28 July 2022
• Sanity Checks for Saliency Maps 28 July 2022
• A Framework of Explanation Generation toward Reliable Autonomous Robots 23 July 2022
• Bridging the Gap: Providing Post-Hoc Symbolic Explanations for Sequential Decision-Making Problems with Inscrutable Representations 18 July 2022
• XRAI: Better Attributions Through Regions 26 June 2022
• Towards Automatic Concept-based Explanations 19 June 2022
• SCOUTER: Slot Attention-based Classifier for Explainable Image Recognition 29 May 2022
• Evaluation of Similarity-based Explanations 29 May 2022
• A Benchmark for Interpretability Methods in Deep Neural Networks 29 May 2022

- - - - - junk - - - - -

• GPT can make tetris 01 December 2022