Search Results for author:
Found 14 papers, 3 papers with code
Image as a Foreign Language: BEiT Pretraining for All Vision and Vision-Language Tasks
A big convergence of language, vision, and multimodal pretraining is emerging.
Ranked #1 on
Visual Reasoning
on NLVR2 Test
Language Is Not All You Need: Aligning Perception with Language Models
A big convergence of language, multimodal perception, action, and world modeling is a key step toward artificial general intelligence.
Phase-Mapper: An AI Platform to Accelerate High Throughput Materials Discovery
A key problem in materials discovery, the phase map identification problem, involves the determination of the crystal phase diagram from the materials' composition and structural characterization data.
Understanding Batch Normalization
Batch normalization (BN) is a technique to normalize activations in intermediate layers of deep neural networks.
Scalable Relaxations of Sparse Packing Constraints: Optimal Biocontrol in Predator-Prey Network
Cascades represent rapid changes in networks.
Automatic Detection and Compression for Passive Acoustic Monitoring of the African Forest Elephant
In this work, we consider applying machine learning to the analysis and compression of audio signals in the context of monitoring elephants in sub-Saharan Africa.
Dataset Curation Beyond Accuracy
Neural networks are known to be data-hungry, and collecting large labeled datasets is often a crucial step in deep learning deployment.
Understanding Decoupled and Early Weight Decay
We also show how the growth of network weights is heavily influenced by the dataset and its generalization properties.
Low-Precision Reinforcement Learning: Running Soft Actor-Critic in Half Precision
Low-precision training has become a popular approach to reduce compute requirements, memory footprint, and energy consumption in supervised learning.
Towards Deeper Deep Reinforcement Learning with Spectral Normalization
In this paper we investigate how RL agents are affected by exchanging the small MLPs with larger modern networks with skip connections and normalization, focusing specifically on actor-critic algorithms.
Is High Variance Unavoidable in RL? A Case Study in Continuous Control
In this paper, we investigate causes for this perceived instability.
Star-Convexity in Non-Negative Matrix Factorization
Non-negative matrix factorization (NMF) is a highly celebrated algorithm for matrix decomposition that guarantees strictly non-negative factors.
Image as a Foreign Language: BEiT Pretraining for Vision and Vision-Language Tasks
A big convergence of language, vision, and multimodal pretraining is emerging.
Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone
We introduce phi-3-mini, a 3. 8 billion parameter language model trained on 3. 3 trillion tokens, whose overall performance, as measured by both academic benchmarks and internal testing, rivals that of models such as Mixtral 8x7B and GPT-3. 5 (e. g., phi-3-mini achieves 69% on MMLU and 8. 38 on MT-bench), despite being small enough to be deployed on a phone.
