Search Results for author:
Found 15 papers, 6 papers with code
AttackEval: How to Evaluate the Effectiveness of Jailbreak Attacking on Large Language Models
In our research, we pioneer a novel approach to evaluate the effectiveness of jailbreak attacks on Large Language Models (LLMs), such as GPT-4 and LLaMa2, diverging from traditional robustness-focused binary evaluations.
Large Language Model as a Policy Teacher for Training Reinforcement Learning Agents
By incorporating the guidance from the teacher agent, the student agent can distill the prior knowledge of the LLM into its own model.
MathAttack: Attacking Large Language Models Towards Math Solving Ability
Instead of attacking prompts in the use of LLMs, we propose a MathAttack model to attack MWP samples which are closer to the essence of security in solving math problems.
Solving Math Word Problem with Problem Type Classification
Firstly, We propose a problem type classifier that combines the strengths of the tree-based solver and the LLM solver.
Predicting Battery Lifetime Under Varying Usage Conditions from Early Aging Data
Using a newly generated dataset from 225 nickel-manganese-cobalt/graphite Li-ion cells aged under a wide range of conditions, we demonstrate a lifetime prediction of in-distribution cells with 15. 1% mean absolute percentage error using no more than the first 15% of data, for most cells.
Learning by Analogy: Diverse Questions Generation in Math Word Problem
We then feed them to a question generator together with the scenario to obtain the corresponding diverse questions, forming a new MWP with a variety of questions and equations.
Enabling Intelligent Interactions between an Agent and an LLM: A Reinforcement Learning Approach
In this paper, we explore how to enable intelligent cost-effective interactions between the agent and an LLM.
On Context Distribution Shift in Task Representation Learning for Offline Meta RL
Offline Meta Reinforcement Learning (OMRL) aims to learn transferable knowledge from offline datasets to enhance the learning process for new target tasks.
Bayesian hierarchical modelling for battery lifetime early prediction
Here, a hierarchical Bayesian linear model is proposed for battery life prediction, combining both individual cell features (reflecting manufacturing variability) with population-wide features (reflecting the impact of cycling conditions on the population average).
Towards Efficient and Stable K-Asynchronous Federated Learning with Unbounded Stale Gradients on Non-IID Data
Federated learning (FL) is an emerging privacy-preserving paradigm that enables multiple participants collaboratively to train a global model without uploading raw data.
Efficient demodulation scheme for multilevel modulation based optical camera communication
We proposed and experimentally demonstrated a new hybrid code structure based on the overlapping of two light sources to produce the effect of multi-voltage amplitudes.
Neural Point Process for Learning Spatiotemporal Event Dynamics
The key construction of our approach is the nonparametric space-time intensity function, governed by a latent process.
Multi-Frequency Wireless Channel Measurements and Characteristics Analysis in Indoor Corridor Scenarios
In this paper, we conduct wireless channel measurements in indoor corridor scenarios at 2. 4, 5 and 6 GHz bands with bandwidth of 320 MHz.
Neural Point Process for Forecasting Spatiotemporal Events
To the best of our knowledge, this is the first neural point process model that can jointly predict both the space and time of events.
Recognition and evaluation of constellation diagram using deep learning based on underwater wireless optical communication
More specifically, an constellation diagram analyzer for UWOC system based on convolutional neural network (CNN) is designed for modulation format recognition (MFR), optical signal noise ratio (OSNR) and phase error estimation.
