Search Results for author:
Found 74 papers, 46 papers with code
Fire Burns, Sword Cuts: Commonsense Inductive Bias for Exploration in Text-based Games
Text-based games (TGs) are exciting testbeds for developing deep reinforcement learning techniques due to their partially observed environments and large action spaces.
Unsupervised multiple choices question answering via universal corpus
Unsupervised question answering is a promising yet challenging task, which alleviates the burden of building large-scale annotated data in a new domain.
RetrievalQA: Assessing Adaptive Retrieval-Augmented Generation for Short-form Open-Domain Question Answering
Based on our findings, we propose Time-Aware Adaptive Retrieval (TA-ARE), a simple yet effective method that helps LLMs assess the necessity of retrieval without calibration or additional training.
PepGB: Facilitating peptide drug discovery via graph neural networks
In summary, our proposed frameworks can serve as potent tools to facilitate peptide early drug discovery.
Large Language Models Are Neurosymbolic Reasoners
A wide range of real-world applications is characterized by their symbolic nature, necessitating a strong capability for symbolic reasoning.
Cooperation on the Fly: Exploring Language Agents for Ad Hoc Teamwork in the Avalon Game
This problem motivates the area of ad hoc teamwork, in which an agent may potentially cooperate with a variety of teammates to achieve a shared goal.
MaDi: Learning to Mask Distractions for Generalization in Visual Deep Reinforcement Learning
Our algorithm improves the agent's focus with useful masks, while its efficient Masker network only adds 0. 2% more parameters to the original structure, in contrast to previous work.
ReRoGCRL: Representation-based Robustness in Goal-Conditioned Reinforcement Learning
Then, to mitigate the vulnerability of existing GCRL algorithms, we introduce Adversarial Representation Tactics, which combines Semi-Contrastive Adversarial Augmentation with Sensitivity-Aware Regularizer to improve the adversarial robustness of the underlying RL agent against various types of perturbations.
GPTBIAS: A Comprehensive Framework for Evaluating Bias in Large Language Models
In this work, we propose a bias evaluation framework named GPTBIAS that leverages the high performance of LLMs (e. g., GPT-4 \cite{openai2023gpt4}) to assess bias in models.
MACCA: Offline Multi-agent Reinforcement Learning with Causal Credit Assignment
Offline Multi-agent Reinforcement Learning (MARL) is valuable in scenarios where online interaction is impractical or risky.
REST: Enhancing Group Robustness in DNNs through Reweighted Sparse Training
These bias attributes are strongly spuriously correlated with the target variable, causing the models to be biased towards spurious correlations (i. e., \textit{bias-conflicting}).
GOPlan: Goal-conditioned Offline Reinforcement Learning by Planning with Learned Models
In this work, we propose Goal-conditioned Offline Planning (GOPlan), a novel model-based framework that contains two key phases: (1) pretraining a prior policy capable of capturing multi-modal action distribution within the multi-goal dataset; (2) employing the reanalysis method with planning to generate imagined trajectories for funetuning policies.
Turn-Level Active Learning for Dialogue State Tracking
Dialogue state tracking (DST) plays an important role in task-oriented dialogue systems.
CITB: A Benchmark for Continual Instruction Tuning
In this work, we establish a CIT benchmark consisting of learning and evaluation protocols.
Enhancing Conversational Search: Large Language Model-Aided Informative Query Rewriting
Furthermore, we propose distilling the rewriting capabilities of LLMs into smaller models to reduce rewriting latency.
How Do Large Language Models Capture the Ever-changing World Knowledge? A Review of Recent Advances
Although large language models (LLMs) are impressive in solving various tasks, they can quickly be outdated after deployment.
Towards Data-centric Graph Machine Learning: Review and Outlook
Data-centric AI, with its primary focus on the collection, management, and utilization of data to drive AI models and applications, has attracted increasing attention in recent years.
Where Would I Go Next? Large Language Models as Human Mobility Predictors
We posit that our research marks a significant paradigm shift in human mobility modelling, transitioning from building complex domain-specific models to harnessing general-purpose LLMs that yield accurate predictions through language instructions.
Eigensubspace of Temporal-Difference Dynamics and How It Improves Value Approximation in Reinforcement Learning
In ERC, we propose a regularizer that guides the approximation error tending towards the 1-eigensubspace, resulting in a more efficient and stable path of value approximation.
Enhancing Adversarial Training via Reweighting Optimization Trajectory
Despite the fact that adversarial training has become the de facto method for improving the robustness of deep neural networks, it is well-known that vanilla adversarial training suffers from daunting robust overfitting, resulting in unsatisfactory robust generalization.
Are Large Kernels Better Teachers than Transformers for ConvNets?
We hereby carry out a first-of-its-kind study unveiling that modern large-kernel ConvNets, a compelling competitor to Vision Transformers, are remarkably more effective teachers for small-kernel ConvNets, due to more similar architectures.
Interpretable Reward Redistribution in Reinforcement Learning: A Causal Approach
While the majority of current approaches construct the reward redistribution in an uninterpretable manner, we propose to explicitly model the contributions of state and action from a causal perspective, resulting in an interpretable reward redistribution and preserving policy invariance.
CHBias: Bias Evaluation and Mitigation of Chinese Conversational Language Models
We evaluate two popular pretrained Chinese conversational models, CDial-GPT and EVA2. 0, using CHBias.
NLG Evaluation Metrics Beyond Correlation Analysis: An Empirical Metric Preference Checklist
Our proposed framework provides access: (i) for verifying whether automatic metrics are faithful to human preference, regardless of their correlation level to human; and (ii) for inspecting the strengths and limitations of NLG systems via pairwise evaluation.
A Minimal Approach for Natural Language Action Space in Text-based Games
Text-based games (TGs) are language-based interactive environments for reinforcement learning.
You Can Have Better Graph Neural Networks by Not Training Weights at All: Finding Untrained GNNs Tickets
Recent works have impressively demonstrated that there exists a subnetwork in randomly initialized convolutional neural networks (CNNs) that can match the performance of the fully trained dense networks at initialization, without any optimization of the weights of the network (i. e., untrained networks).
A Survey for Efficient Open Domain Question Answering
Thus, a trade-off between accuracy, memory consumption and processing speed is pursued.
TASA: Deceiving Question Answering Models by Twin Answer Sentences Attack
We present Twin Answer Sentences Attack (TASA), an adversarial attack method for question answering (QA) models that produces fluent and grammatical adversarial contexts while maintaining gold answers.
Lottery Pools: Winning More by Interpolating Tickets without Increasing Training or Inference Cost
We call our method Lottery Pools.
Learning Granularity-Unified Representations for Text-to-Image Person Re-identification
In PGU, we adopt a set of shared and learnable prototypes as the queries to extract diverse and semantically aligned features for both modalities in the granularity-unified feature space, which further promotes the ReID performance.
Dynamic Contrastive Distillation for Image-Text Retrieval
Although the vision-and-language pretraining (VLP) equipped cross-modal image-text retrieval (ITR) has achieved remarkable progress in the past two years, it suffers from a major drawback: the ever-increasing size of VLP models restricts its deployment to real-world search scenarios (where the high latency is unacceptable).
Discourse-Aware Graph Networks for Textual Logical Reasoning
In this work, we propose logic structural-constraint modeling to solve the logical reasoning QA and introduce discourse-aware graph networks (DAGNs).
Superposing Many Tickets into One: A Performance Booster for Sparse Neural Network Training
Recent works on sparse neural network training (sparse training) have shown that a compelling trade-off between performance and efficiency can be achieved by training intrinsically sparse neural networks from scratch.
Phrase-level Textual Adversarial Attack with Label Preservation
Generating high-quality textual adversarial examples is critical for investigating the pitfalls of natural language processing (NLP) models and further promoting their robustness.
A Model-Agnostic Data Manipulation Method for Persona-based Dialogue Generation
To alleviate the above data issues, we propose a data manipulation method, which is model-agnostic to be packed with any persona-based dialogue generation model to improve its performance.
Is Neural Topic Modelling Better than Clustering? An Empirical Study on Clustering with Contextual Embeddings for Topics
Recent work incorporates pre-trained word embeddings such as BERT embeddings into Neural Topic Models (NTMs), generating highly coherent topics.
Perceiving the World: Question-guided Reinforcement Learning for Text-based Games
Text-based games provide an interactive way to study natural language processing.
Rethinking Goal-conditioned Supervised Learning and Its Connection to Offline RL
In this paper, we revisit the theoretical property of GCSL -- optimizing a lower bound of the goal reaching objective, and extend GCSL as a novel offline goal-conditioned RL algorithm.
Goal Randomization for Playing Text-based Games without a Reward Function
In a variety of text-based games, we show that this simple method results in competitive performance for agents.
Lagrangian Generative Adversarial Imitation Learning with Safety
Imitation Learning (IL) merely concentrates on reproducing expert behaviors and could take dangerous actions, which is unbearable in safety-critical scenarios.
Generalization in Text-based Games via Hierarchical Reinforcement Learning
Deep reinforcement learning provides a promising approach for text-based games in studying natural language communication between humans and artificial agents.
Hierarchical Reinforcement Learning
reinforcement-learning
+2
ProtoInfoMax: Prototypical Networks with Mutual Information Maximization for Out-of-Domain Detection
The ability to detect Out-of-Domain (OOD) inputs has been a critical requirement in many real-world NLP applications.
Safe Exploration by Solving Early Terminated MDP
Safe exploration is crucial for the real-world application of reinforcement learning (RL).
MHER: Model-based Hindsight Experience Replay
Replacing original goals with virtual goals generated from interaction with a trained dynamics model leads to a novel relabeling method, model-based relabeling (MBR).
DAGN: Discourse-Aware Graph Network for Logical Reasoning
The model encodes discourse information as a graph with elementary discourse units (EDUs) and discourse relations, and learns the discourse-aware features via a graph network for downstream QA tasks.
Ranked #24 on
Reading Comprehension
on ReClor
Towards Efficiently Diversifying Dialogue Generation via Embedding Augmentation
Dialogue generation models face the challenge of producing generic and repetitive responses.
Learning Predictive Communication by Imagination in Networked System Control
Dealing with multi-agent control in networked systems is one of the biggest challenges in Reinforcement Learning (RL) and limited success has been presented compared to recent deep reinforcement learning in single-agent domain.
Self-Supervised Continuous Control without Policy Gradient
Despite the remarkable progress made by the policy gradient algorithms in reinforcement learning (RL), sub-optimal policies usually result from the local exploration property of the policy gradient update.
REM-Net: Recursive Erasure Memory Network for Commonsense Evidence Refinement
It is crucial since the quality of the evidence is the key to answering commonsense questions, and even determines the upper bound on the QA systems performance.
TStarBot-X: An Open-Sourced and Comprehensive Study for Efficient League Training in StarCraft II Full Game
We show that with orders of less computation scale, a faithful reimplementation of AlphaStar's methods can not succeed and the proposed techniques are necessary to ensure TStarBot-X's competitive performance.
TLeague: A Framework for Competitive Self-Play based Distributed Multi-Agent Reinforcement Learning
This poses non-trivial difficulties for researchers or engineers and prevents the application of MARL to a broader range of real-world problems.
Deep Reinforcement Learning with Stacked Hierarchical Attention for Text-based Games
We study reinforcement learning (RL) for text-based games, which are interactive simulations in the context of natural language.
On the Guaranteed Almost Equivalence between Imitation Learning from Observation and Demonstration
By contrast, this paper proves that LfO is almost equivalent to LfD in the deterministic robot environment, and more generally even in the robot environment with bounded randomness.
Pretrained Language Models for Dialogue Generation with Multiple Input Sources
In this work, we study dialogue models with multiple input sources adapted from the pretrained language model GPT2.
Zeroth-Order Supervised Policy Improvement
However, PG algorithms rely on exploiting the value function being learned with the first-order update locally, which results in limited sample efficiency.
LIIR: Learning Individual Intrinsic Reward in Multi-Agent Reinforcement Learning
A great challenge in cooperative decentralized multi-agent reinforcement learning (MARL) is generating diversified behaviors for each individual agent when receiving only a team reward.
Multi-agent Reinforcement Learning
reinforcement-learning
+3
Curriculum-guided Hindsight Experience Replay
This ``Goal-and-Curiosity-driven Curriculum Learning'' leads to ``Curriculum-guided HER (CHER)'', which adaptively and dynamically controls the exploration-exploitation trade-off during the learning process via hindsight experience selection.
Unsupervised Domain Adaptation on Reading Comprehension
On the other hand, it further reduces domain distribution discrepancy through conditional adversarial learning across domains.
A Corpus-free State2Seq User Simulator for Task-oriented Dialogue
The framework builds a user simulator by first generating diverse dialogue data from templates and then build a new State2Seq user simulator on the data.
Learning to Solve a Rubik's Cube with a Dexterous Hand
We present a learning-based approach to solving a Rubik's cube with a multi-fingered dexterous hand.
Robotics
Arena: a toolkit for Multi-Agent Reinforcement Learning
We introduce Arena, a toolkit for multi-agent reinforcement learning (MARL) research.
Revisiting Metric Learning for Few-Shot Image Classification
However, the importance of feature embedding, i. e., exploring the relationship among training samples, is neglected.
Dual Adversarial Neural Transfer for Low-Resource Named Entity Recognition
We propose a new neural transfer method termed Dual Adversarial Transfer Network (DATNet) for addressing low-resource Named Entity Recognition (NER).
DHER: Hindsight Experience Replay for Dynamic Goals
Dealing with sparse rewards is one of the most important challenges in reinforcement learning (RL), especially when a goal is dynamic (e. g., to grasp a moving object).
BAG: Bi-directional Attention Entity Graph Convolutional Network for Multi-hop Reasoning Question Answering
Graph convolutional networks are used to obtain a relation-aware representation of nodes for entity graphs built from documents with multi-level features.
Towards Query Efficient Black-box Attacks: An Input-free Perspective
First, we initialize an adversarial example with a gray color image on which every pixel has roughly the same importance for the target model.
A Deep Network for Arousal-Valence Emotion Prediction with Acoustic-Visual Cues
In this paper, we comprehensively describe the methodology of our submissions to the One-Minute Gradual-Emotion Behavior Challenge 2018.
Learning how to Active Learn: A Deep Reinforcement Learning Approach
Active learning aims to select a small subset of data for annotation such that a classifier learned on the data is highly accurate.
Model Transfer for Tagging Low-resource Languages using a Bilingual Dictionary
Cross-lingual model transfer is a compelling and popular method for predicting annotations in a low-resource language, whereby parallel corpora provide a bridge to a high-resource language and its associated annotated corpora.
Iterative Views Agreement: An Iterative Low-Rank based Structured Optimization Method to Multi-View Spectral Clustering
Multi-view spectral clustering, which aims at yielding an agreement or consensus data objects grouping across multi-views with their graph laplacian matrices, is a fundamental clustering problem.
Learning when to trust distant supervision: An application to low-resource POS tagging using cross-lingual projection
Cross lingual projection of linguistic annotation suffers from many sources of bias and noise, leading to unreliable annotations that cannot be used directly.
Saliency Propagation From Simple to Difficult
In the teaching-to-learn step, a teacher is designed to arrange the regions from simple to difficult and then assign the simplest regions to the learner.
Transfer Learning across Networks for Collective Classification
In this paper, we propose a new transfer learning algorithm that attempts to transfer common latent structure features across the source and target networks.
