Search Results for author:
Found 11 papers, 2 papers with code
Learning to Decompose and Disentangle Representations for Video Prediction
Our goal is to predict future video frames given a sequence of input frames.
Spatiotemporal Relationship Reasoning for Pedestrian Intent Prediction
In addition, we introduce a new dataset designed specifically for autonomous-driving scenarios in areas with dense pedestrian populations: the Stanford-TRI Intent Prediction (STIP) dataset.
Temporal Modular Networks for Retrieving Complex Compositional Activities in Videos
A major challenge in computer vision is scaling activity understanding to the long tail of complex activities without requiring collecting large quantities of data for new actions.
Generalized Boosting
Using thorough empirical evaluation, we show that our learning algorithms have superior performance over traditional additive boosting algorithms, as well as existing greedy learning techniques for DNNs.
Contrastive learning of strong-mixing continuous-time stochastic processes
Contrastive learning is a family of self-supervised methods where a model is trained to solve a classification task constructed from unlabeled data.
Analyzing and Improving the Optimization Landscape of Noise-Contrastive Estimation
Noise-contrastive estimation (NCE) is a statistically consistent method for learning unnormalized probabilistic models.
Masked prediction tasks: a parameter identifiability view
This lens is undoubtedly very interesting, but suffers from the problem that there isn't a "canonical" set of downstream tasks to focus on -- in practice, this problem is usually resolved by competing on the benchmark dataset du jour.
Transformers Learn Shortcuts to Automata
Algorithmic reasoning requires capabilities which are most naturally understood through recurrent models of computation, like the Turing machine.
Understanding Augmentation-based Self-Supervised Representation Learning via RKHS Approximation and Regression
Recent work has built the connection between self-supervised learning and the approximation of the top eigenspace of a graph Laplacian operator, suggesting that learning a linear probe atop such representation can be connected to RKHS regression.
Transformers are uninterpretable with myopic methods: a case study with bounded Dyck grammars
Interpretability methods aim to understand the algorithm implemented by a trained model (e. g., a Transofmer) by examining various aspects of the model, such as the weight matrices or the attention patterns.
TinyGSM: achieving >80% on GSM8k with small language models
Specifically for solving grade school math, the smallest model size so far required to break the 80\% barrier on the GSM8K benchmark remains to be 34B.
Ranked #58 on
Arithmetic Reasoning
on GSM8K
