Search Results for author:
Found 16 papers, 7 papers with code
Enhancing Adversarial Robustness via Uncertainty-Aware Distributional Adversarial Training
To circumvent these issues, in this paper, we propose a novel uncertainty-aware distributional adversarial training method, which enforces adversary modeling by leveraging both the statistical information of adversarial examples and its corresponding uncertainty estimation, with the goal of augmenting the diversity of adversaries.
You Only Sample Once: Taming One-Step Text-to-Image Synthesis by Self-Cooperative Diffusion GANs
We show that our method can serve as a one-step generation model training from scratch with competitive performance.
Dynamic In-Context Learning from Nearest Neighbors for Bundle Generation
To enhance reliability and mitigate the hallucination issue, we develop (1) a self-correction strategy to foster mutual improvement in both tasks without supervision signals; and (2) an auto-feedback mechanism to recurrently offer dynamic supervision based on the distinct mistakes made by ChatGPT on various neighbor sessions.
Large Language Models for Intent-Driven Session Recommendations
Intent-aware session recommendation (ISR) is pivotal in discerning user intents within sessions for precise predictions.
Large Language Models as Evolutionary Optimizers
Specifically, in each generation of the evolutionary search, LMEA instructs the LLM to select parent solutions from current population, and perform crossover and mutation to generate offspring solutions.
Towards Building Voice-based Conversational Recommender Systems: Datasets, Potential Solutions, and Prospects
Conversational recommender systems (CRSs) have become crucial emerging research topics in the field of RSs, thanks to their natural advantages of explicitly acquiring user preferences via interactive conversations and revealing the reasons behind recommendations.
Policy Resilience to Environment Poisoning Attacks on Reinforcement Learning
This paper proposes such a policy-resilience mechanism based on an idea of knowledge sharing.
Importance Prioritized Policy Distillation
Given such an issue, we denote the \emph{frame importance} as its contribution to the expected reward on a particular frame, and hypothesize that adapting such frame importance could benefit the performance of the distilled student policy.
Unsupervised Video Domain Adaptation for Action Recognition: A Disentanglement Perspective
Specifically, we consider the generation of cross-domain videos from two sets of latent factors, one encoding the static information and another encoding the dynamic information.
DaisyRec 2.0: Benchmarking Recommendation for Rigorous Evaluation
Recently, one critical issue looms large in the field of recommender systems -- there are no effective benchmarks for rigorous evaluation -- which consequently leads to unreproducible evaluation and unfair comparison.
Language Adaptive Cross-lingual Speech Representation Learning with Sparse Sharing Sub-networks
It makes room for language specific modeling by pruning out unimportant parameters for each language, without requiring any manually designed language specific component.
Synthesising Audio Adversarial Examples for Automatic Speech Recognition
Adversarial examples in automatic speech recognition (ASR) are naturally sounded by humans yet capable of fooling well trained ASR models to transcribe incorrectly.
An Improved Transfer Model: Randomized Transferable Machine
Existing studies usually assume that the learned new feature representation is \emph{domain-invariant}, and thus train a transfer model $\mathcal{M}$ on the source domain.
Adversary Agnostic Robust Deep Reinforcement Learning
Motivated by this finding, we propose a new policy distillation loss with two terms: 1) a prescription gap maximization loss aiming at simultaneously maximizing the likelihood of the action selected by the teacher policy and the entropy over the remaining actions; 2) a corresponding Jacobian regularization loss that minimizes the magnitude of the gradient with respect to the input state.
Subdomain Adaptation with Manifolds Discrepancy Alignment
Specifically, we propose to use low-dimensional manifold to represent subdomain, and align the local data distribution discrepancy in each manifold across domains.
Minimalistic Attacks: How Little it Takes to Fool a Deep Reinforcement Learning Policy
Recent studies have revealed that neural network-based policies can be easily fooled by adversarial examples.
