Search Results for author:
Found 30 papers, 20 papers with code
Compressed Context Memory For Online Language Model Interaction
This paper presents a context key/value compression method for Transformer language models in online scenarios, where the context continually expands.
Discovering Hierarchical Achievements in Reinforcement Learning via Contrastive Learning
Discovering achievements with a hierarchical structure in procedurally generated environments presents a significant challenge.
Query-Efficient Black-Box Red Teaming via Bayesian Optimization
To this end, we propose Bayesian red teaming (BRT), novel query-efficient black-box red teaming methods based on Bayesian optimization, which iteratively identify diverse positive test cases leading to model failures by utilizing the pre-defined user input pool and the past evaluations.
Direct Preference-based Policy Optimization without Reward Modeling
We apply our algorithm to offline RL tasks with actual human preference labels and show that our algorithm outperforms or is on par with the existing PbRL methods.
Neural Relation Graph: A Unified Framework for Identifying Label Noise and Outlier Data
To this end, we present scalable and effective algorithms for detecting label errors and outlier data based on the relational graph structure of data.
Efficient Latency-Aware CNN Depth Compression via Two-Stage Dynamic Programming
We propose a subset selection problem that replaces inefficient activation layers with identity functions and optimally merges consecutive convolution operations into shallow equivalent convolution operations for efficient end-to-end inference latency.
Rethinking Value Function Learning for Generalization in Reinforcement Learning
Our work focuses on training RL agents on multiple visually diverse environments to improve observational generalization performance.
Query-Efficient and Scalable Black-Box Adversarial Attacks on Discrete Sequential Data via Bayesian Optimization
We focus on the problem of adversarial attacks against models on discrete sequential data in the black-box setting where the attacker aims to craft adversarial examples with limited query access to the victim model.
Dataset Condensation via Efficient Synthetic-Data Parameterization
The great success of machine learning with massive amounts of data comes at a price of huge computation costs and storage for training and tuning.
Optimal channel selection with discrete QCQP
We first show the greedy approach of recent channel pruning methods ignores the inherent quadratic coupling between channels in the neighboring layers and cannot safely remove inactive weights during the pruning procedure.
Preemptive Image Robustification for Protecting Users against Man-in-the-Middle Adversarial Attacks
However, the vulnerability of neural networks against adversarial attacks poses a serious threat to the people affected by these systems.
Uncertainty-Based Offline Reinforcement Learning with Diversified Q-Ensemble
However, prior methods typically require accurate estimation of the behavior policy or sampling from OOD data points, which themselves can be a non-trivial problem.
Ranked #1 on
Gym halfcheetah-random
on D4RL
Co-Mixup: Saliency Guided Joint Mixup with Supermodular Diversity
While deep neural networks show great performance on fitting to the training distribution, improving the networks' generalization performance to the test distribution and robustness to the sensitivity to input perturbations still remain as a challenge.
Succinct Network Channel and Spatial Pruning via Discrete Variable QCQP
Reducing the heavy computational cost of large convolutional neural networks is crucial when deploying the networks to resource-constrained environments.
Exploiting Safe Spots in Neural Networks for Preemptive Robustness and Out-of-Distribution Detection
Recent advances on adversarial defense mainly focus on improving the classifier’s robustness against adversarially perturbed inputs.
Puzzle Mix: Exploiting Saliency and Local Statistics for Optimal Mixup
While deep neural networks achieve great performance on fitting the training distribution, the learned networks are prone to overfitting and are susceptible to adversarial attacks.
Ranked #2 on
Image Classification
on Tiny-ImageNet
Learning Discrete and Continuous Factors of Data via Alternating Disentanglement
Furthermore, we propose a method which avoids offloading the entire burden of jointly modeling the continuous and discrete factors to the variational encoder by employing a separate discrete inference procedure.
Parsimonious Black-Box Adversarial Attacks via Efficient Combinatorial Optimization
Solving for adversarial examples with projected gradient descent has been demonstrated to be highly effective in fooling the neural network based classifiers.
End-to-End Efficient Representation Learning via Cascading Combinatorial Optimization
We develop hierarchically quantized efficient embedding representations for similarity-based search and show that this representation provides not only the state of the art performance on the search accuracy but also provides several orders of speed up during inference.
EMI: Exploration with Mutual Information
Reinforcement learning algorithms struggle when the reward signal is very sparse.
EMI: Exploration with Mutual Information Maximizing State and Action Embeddings
Policy optimization struggles when the reward feedback signal is very sparse and essentially becomes a random search algorithm until the agent stumbles upon a rewarding or the goal state.
Efficient end-to-end learning for quantizable representations
To this end, we consider the problem of directly learning a quantizable embedding representation and the sparse binary hash code end-to-end which can be used to construct an efficient hash table not only providing significant search reduction in the number of data but also achieving the state of the art search accuracy outperforming previous state of the art deep metric learning methods.
Semantic Instance Segmentation via Deep Metric Learning
We propose a new method for semantic instance segmentation, by first computing how likely two pixels are to belong to the same object, and then by grouping similar pixels together.
Deep Metric Learning via Facility Location
Learning the representation and the similarity metric in an end-to-end fashion with deep networks have demonstrated outstanding results for clustering and retrieval.
Learning Transferrable Representations for Unsupervised Domain Adaptation
Supervised learning with large scale labelled datasets and deep layered models has caused a paradigm shift in diverse areas in learning and recognition.
Unsupervised Transductive Domain Adaptation
We incorporate the domain shift and the transductive target inference into our framework by jointly solving for an asymmetric similarity metric and the optimal transductive target label assignment.
Deep Metric Learning via Lifted Structured Feature Embedding
Additionally, we collected Online Products dataset: 120k images of 23k classes of online products for metric learning.
Weakly-supervised Discovery of Visual Pattern Configurations
The increasing prominence of weakly labeled data nurtures a growing demand for object detection methods that can cope with minimal supervision.
Detection Bank: An Object Detection Based Video Representation for Multimedia Event Recognition
While low-level image features have proven to be effective representations for visual recognition tasks such as object recognition and scene classification, they are inadequate to capture complex semantic meaning required to solve high-level visual tasks such as multimedia event detection and recognition.
On learning to localize objects with minimal supervision
Learning to localize objects with minimal supervision is an important problem in computer vision, since large fully annotated datasets are extremely costly to obtain.
Ranked #35 on
Weakly Supervised Object Detection
on PASCAL VOC 2007
