Search Results for author:
Found 173 papers, 88 papers with code
Finite State Automata Inside Transformers with Chain-of-Thought: A Mechanistic Study on State Tracking
Chain-of-Thought (CoT) significantly enhances the performance of large language models (LLMs) across a wide range of tasks, and prior research shows that CoT can theoretically increase expressiveness.
Synthesis of Dynamic Masks for Information-Theoretic Opacity in Stochastic Systems
In this work, we investigate the synthesis of dynamic information releasing mechanisms, referred to as ''masks'', to minimize information leakage from a stochastic system to an external observer.
Active Inference through Incentive Design in Markov Decision Processes
We show the problem of active inference through incentive design can be formulated as a special class of leader-follower games, where the leader's objective is to balance the information gain and cost of incentive design.
Generating Symbolic World Models via Test-time Scaling of Large Language Models
Solving complex planning problems requires Large Language Models (LLMs) to explicitly model the state transition to avoid rule violations, comply with constraints, and ensure optimality-a task hindered by the inherent ambiguity of natural language.
CBNN: 3-Party Secure Framework for Customized Binary Neural Networks Inference
Binarized Neural Networks (BNN) offer efficient implementations for machine learning tasks and facilitate Privacy-Preserving Machine Learning (PPML) by simplifying operations with binary values.
OpenCoder: The Open Cookbook for Top-Tier Code Large Language Models
To address the gap, we introduce OpenCoder, a top-tier code LLM that not only achieves performance comparable to leading models but also serves as an "open cookbook" for the research community.
PopAlign: Diversifying Contrasting Patterns for a More Comprehensive Alignment
Alignment of large language models (LLMs) involves training models on preference-contrastive output pairs to adjust their responses according to human preferences.
PositionID: LLMs can Control Lengths, Copy and Paste with Explicit Positional Awareness
Large Language Models (LLMs) demonstrate impressive capabilities across various domains, including role-playing, creative writing, mathematical reasoning, and coding.
MIO: A Foundation Model on Multimodal Tokens
In this paper, we introduce MIO, a novel foundation model built on multimodal tokens, capable of understanding and generating speech, text, images, and videos in an end-to-end, autoregressive manner.
Active Perception with Initial-State Uncertainty: A Policy Gradient Method
This paper studies the synthesis of an active perception policy that maximizes the information leakage of the initial state in a stochastic system modeled as a hidden Markov model (HMM).
Coral Model Generation from Single Images for Virtual Reality Applications
With the rapid development of VR technology, the demand for high-quality 3D models is increasing.
Single-cell Curriculum Learning-based Deep Graph Embedding Clustering
The swift advancement of single-cell RNA sequencing (scRNA-seq) technologies enables the investigation of cellular-level tissue heterogeneity.
Layerwise Recurrent Router for Mixture-of-Experts
The scaling of large language models (LLMs) has revolutionized their capabilities in various tasks, yet this growth must be matched with efficient computational strategies.
A Closer Look into Mixture-of-Experts in Large Language Models
Mixture-of-experts (MoE) is gaining increasing attention due to its unique properties and remarkable performance, especially for language tasks.
Unlocking Continual Learning Abilities in Language Models
To address this limitation, we introduce $\textbf{MIGU}$ ($\textbf{M}$agn$\textbf{I}$tude-based $\textbf{G}$radient $\textbf{U}$pdating for continual learning), a rehearsal-free and task-label-free method that only updates the model parameters with large magnitudes of output in LMs' linear layers.
LLMs Assist NLP Researchers: Critique Paper (Meta-)Reviewing
This study focuses on the topic of LLMs assist NLP Researchers, particularly examining the effectiveness of LLM in assisting paper (meta-)reviewing and its recognizability.
Efficient Continual Pre-training by Mitigating the Stability Gap
This process involves updating the pre-trained LLM with a corpus from a new domain, resulting in a shift in the training distribution.
PIN: A Knowledge-Intensive Dataset for Paired and Interleaved Multimodal Documents
Recent advancements in Large Multimodal Models (LMMs) have leveraged extensive multimodal datasets to enhance capabilities in complex knowledge-driven tasks.
GW-MoE: Resolving Uncertainty in MoE Router with Global Workspace Theory
Therefore, these tokens can acquire the necessary knowledge from any expert during inference and become less sensitive to the choice.
Input Conditioned Graph Generation for Language Agents
Within this graph framework, we aim to learn a model that can generate edges for every given input to the language agent.
MAP: Low-compute Model Merging with Amortized Pareto Fronts via Quadratic Approximation
MAP efficiently identifies a Pareto set of scaling coefficients for merging multiple models, reflecting the trade-offs involved.
A Survey of Recent Backdoor Attacks and Defenses in Large Language Models
Large Language Models (LLMs), which bridge the gap between human language understanding and complex problem-solving, achieve state-of-the-art performance on several NLP tasks, particularly in few-shot and zero-shot settings.
VCR: Visual Caption Restoration
This task stems from the observation that text embedded in images is intrinsically different from common visual elements and natural language due to the need to align the modalities of vision, text, and text embedded in images.
Robust Reward Design for Markov Decision Processes
The problem of reward design examines the interaction between a leader and a follower, where the leader aims to shape the follower's behavior to maximize the leader's payoff by modifying the follower's reward function.
D-CPT Law: Domain-specific Continual Pre-Training Scaling Law for Large Language Models
To address the limitations of existing methods, inspired by the Scaling Law for performance prediction, we propose to investigate the Scaling Law of the Domain-specific Continual Pre-Training (D-CPT Law) to decide the optimal mixture ratio with acceptable training costs for LLMs of different sizes.
LoGAH: Predicting 774-Million-Parameter Transformers using Graph HyperNetworks with 1/100 Parameters
Unfortunately, predicting parameters of very wide networks relies on copying small chunks of parameters multiple times and requires an extremely large number of parameters to support full prediction, which greatly hinders its adoption in practice.
Stacking Your Transformers: A Closer Look at Model Growth for Efficient LLM Pre-Training
For example, compared to a conventionally trained 7B model using 300B tokens, our $G_{\text{stack}}$ model converges to the same loss with 194B tokens, resulting in a 54. 6\% speedup.
Differentially Private Federated Learning: A Systematic Review
Our work presents a systematic overview of the differentially private federated learning.
Information-Theoretic Opacity-Enforcement in Markov Decision Processes
The goal of the observer is to infer some secret, represented by a random variable, from its partial observations, while the goal of the planning agent is to make the secret maximally opaque to the observer while achieving a satisfactory total return.
ComposerX: Multi-Agent Symbolic Music Composition with LLMs
Music composition represents the creative side of humanity, and itself is a complex task that requires abilities to understand and generate information with long dependency and harmony constraints.
Dynamic Generation of Personalities with Large Language Models
We propose a new metric to assess personality generation capability based on this evaluation method.
MuPT: A Generative Symbolic Music Pretrained Transformer
In this paper, we explore the application of Large Language Models (LLMs) to the pre-training of music.
CodeEditorBench: Evaluating Code Editing Capability of Large Language Models
Large Language Models (LLMs) for code are rapidly evolving, with code editing emerging as a critical capability.
RQ-RAG: Learning to Refine Queries for Retrieval Augmented Generation
To this end, we propose learning to Refine Query for Retrieval Augmented Generation (RQ-RAG) in this paper, endeavoring to enhance the model by equipping it with capabilities for explicit rewriting, decomposition, and disambiguation.
Preference-Based Planning in Stochastic Environments: From Partially-Ordered Temporal Goals to Most Preferred Policies
In the second step, we prove that finding a most preferred policy is equivalent to computing a Pareto-optimal policy in a multi-objective MDP that is constructed from the original MDP, the preference automaton, and the chosen stochastic ordering relation.
COIG-CQIA: Quality is All You Need for Chinese Instruction Fine-tuning
Remarkable progress on English instruction tuning has facilitated the efficacy and reliability of large language models (LLMs).
MEIT: Multi-Modal Electrocardiogram Instruction Tuning on Large Language Models for Report Generation
Electrocardiogram (ECG) is the primary non-invasive diagnostic tool for monitoring cardiac conditions and is crucial in assisting clinicians.
TEGEE: Task dEfinition Guided Expert Ensembling for Generalizable and Few-shot Learning
Our framework employs a dual 3B model approach, with each model assigned a distinct role: one focuses on task definition extraction, while the other handles learning from demonstrations.
StructLM: Towards Building Generalist Models for Structured Knowledge Grounding
Utilizing this dataset, we train a series of models, referred to as StructLM, based on the Mistral and the CodeLlama model family, ranging from 7B to 34B parameters.
m2mKD: Module-to-Module Knowledge Distillation for Modular Transformers
Additionally, the V-MoE-Base model trained with m2mKD achieves 3. 5% higher accuracy than end-to-end training on ImageNet-1k.
Multi-Task Contrastive Learning for 8192-Token Bilingual Text Embeddings
We introduce a novel suite of state-of-the-art bilingual text embedding models that are designed to support English and another target language.
ChatMusician: Understanding and Generating Music Intrinsically with LLM
It is based on continual pre-training and finetuning LLaMA2 on a text-compatible music representation, ABC notation, and the music is treated as a second language.
OpenCodeInterpreter: Integrating Code Generation with Execution and Refinement
However, open-source models often lack the execution capabilities and iterative refinement of advanced systems like the GPT-4 Code Interpreter.
CMDAG: A Chinese Metaphor Dataset with Annotated Grounds as CoT for Boosting Metaphor Generation
These models are able to generate creative and fluent metaphor sentences more frequently induced by selected samples from our dataset, demonstrating the value of our corpus for Chinese metaphor research.
CIF-Bench: A Chinese Instruction-Following Benchmark for Evaluating the Generalizability of Large Language Models
The advancement of large language models (LLMs) has enhanced the ability to generalize across a wide range of unseen natural language processing (NLP) tasks through instruction-following.
HyperMoE: Towards Better Mixture of Experts via Transferring Among Experts
The Mixture of Experts (MoE) for language models has been proven effective in augmenting the capacity of models by dynamically routing each input token to a specific subset of experts for processing.
Defending Against Weight-Poisoning Backdoor Attacks for Parameter-Efficient Fine-Tuning
Motivated by this insight, we developed a Poisoned Sample Identification Module (PSIM) leveraging PEFT, which identifies poisoned samples through confidence, providing robust defense against weight-poisoning backdoor attacks.
AnyGPT: Unified Multimodal LLM with Discrete Sequence Modeling
We introduce AnyGPT, an any-to-any multimodal language model that utilizes discrete representations for the unified processing of various modalities, including speech, text, images, and music.
Empirical Study on Updating Key-Value Memories in Transformer Feed-forward Layers
The feed-forward networks (FFNs) in transformers are recognized as a group of key-value neural memories to restore abstract high-level knowledge.
Pixel Sentence Representation Learning
To our knowledge, this is the first representation learning method devoid of traditional language models for understanding sentence and document semantics, marking a stride closer to human-like textual comprehension.
Read to Play (R2-Play): Decision Transformer with Multimodal Game Instruction
Drawing inspiration from the success of multimodal instruction tuning in visual tasks, we treat the visual-based RL task as a long-horizon vision task and construct a set of multimodal game instructions to incorporate instruction tuning into a decision transformer.
SciMMIR: Benchmarking Scientific Multi-modal Information Retrieval
We further annotate the image-text pairs with two-level subset-subcategory hierarchy annotations to facilitate a more comprehensive evaluation of the baselines.
CMMMU: A Chinese Massive Multi-discipline Multimodal Understanding Benchmark
We introduce CMMMU, a new Chinese Massive Multi-discipline Multimodal Understanding benchmark designed to evaluate LMMs on tasks demanding college-level subject knowledge and deliberate reasoning in a Chinese context.
E^2-LLM: Efficient and Extreme Length Extension of Large Language Models
Typically, training LLMs with long context sizes is computationally expensive, requiring extensive training hours and GPU resources.
Kun: Answer Polishment for Chinese Self-Alignment with Instruction Back-Translation
In this paper, we introduce Kun, a novel approach for creating high-quality instruction-tuning datasets for large language models (LLMs) without relying on manual annotations.
Align on the Fly: Adapting Chatbot Behavior to Established Norms
In this paper, we aim to align large language models with the ever-changing, complex, and diverse human values (e. g., social norms) across time and locations.
TACO: Topics in Algorithmic COde generation dataset
Moreover, each TACO problem includes several fine-grained labels such as task topics, algorithms, programming skills, and difficulty levels, providing a more precise reference for the training and evaluation of code generation models.
Ranked #1 on
Code Generation
on TACO-Code
Scalable Geometric Fracture Assembly via Co-creation Space among Assemblers
Therefore, there is a need to develop a scalable framework for geometric fracture assembly without relying on semantic information.
A Survey of Reasoning with Foundation Models
Reasoning, a crucial ability for complex problem-solving, plays a pivotal role in various real-world settings such as negotiation, medical diagnosis, and criminal investigation.
T3D: Advancing 3D Medical Vision-Language Pre-training by Learning Multi-View Visual Consistency
To bridge this gap, we introduce **CT-3DVLP**, the first and largest **public** 3D volume-report dataset, establishing a comprehensive benchmark for 3D MedVLP research.
SynFundus-1M: A High-quality Million-scale Synthetic fundus images Dataset with Fifteen Types of Annotation
Large-scale public datasets with high-quality annotations are rarely available for intelligent medical imaging research, due to data privacy concerns and the cost of annotations.
UniIR: Training and Benchmarking Universal Multimodal Information Retrievers
Existing information retrieval (IR) models often assume a homogeneous format, limiting their applicability to diverse user needs, such as searching for images with text descriptions, searching for a news article with a headline image, or finding a similar photo with a query image.
DPSUR: Accelerating Differentially Private Stochastic Gradient Descent Using Selective Update and Release
Motivated by this, this paper proposes DPSUR, a Differentially Private training framework based on Selective Updates and Release, where the gradient from each iteration is evaluated based on a validation test, and only those updates leading to convergence are applied to the model.
Massive Editing for Large Language Models via Meta Learning
While large language models (LLMs) have enabled learning knowledge from the pre-training corpora, the acquired knowledge may be fundamentally incorrect or outdated over time, which necessitates rectifying the knowledge of the language model (LM) after the training.
DP-DCAN: Differentially Private Deep Contrastive Autoencoder Network for Single-cell Clustering
Single-cell RNA sequencing (scRNA-seq) is important to transcriptomic analysis of gene expression.
AI Alignment: A Comprehensive Survey
The former aims to make AI systems aligned via alignment training, while the latter aims to gain evidence about the systems' alignment and govern them appropriately to avoid exacerbating misalignment risks.
Covert Planning against Imperfect Observers
This paper studies how covert planning can leverage the coupling of stochastic dynamics and the observer's imperfect observation to achieve optimal task performance without being detected.
Prototype-based HyperAdapter for Sample-Efficient Multi-task Tuning
Parameter-efficient fine-tuning (PEFT) has shown its effectiveness in adapting the pre-trained language models to downstream tasks while only updating a small number of parameters.
Unlocking Emergent Modularity in Large Language Models
Despite the benefits of modularity, most Language Models (LMs) are still treated as monolithic models in the pre-train and fine-tune paradigm, with their emergent modularity locked and underutilized.
Heterogenous Memory Augmented Neural Networks
It has been shown that semi-parametric methods, which combine standard neural networks with non-parametric components such as external memory modules and data retrieval, are particularly helpful in data scarcity and out-of-distribution (OOD) scenarios.
Improving Discriminative Multi-Modal Learning with Large-Scale Pre-Trained Models
To this end, we introduce Multi-Modal Low-Rank Adaptation learning (MMLoRA).
ReForm-Eval: Evaluating Large Vision Language Models via Unified Re-Formulation of Task-Oriented Benchmarks
Recent years have witnessed remarkable progress in the development of large vision-language models (LVLMs).
RoleLLM: Benchmarking, Eliciting, and Enhancing Role-Playing Abilities of Large Language Models
The advent of Large Language Models (LLMs) has paved the way for complex tasks such as role-playing, which enhances user interactions by enabling models to imitate various characters.
AutoAgents: A Framework for Automatic Agent Generation
Therefore, we introduce AutoAgents, an innovative framework that adaptively generates and coordinates multiple specialized agents to build an AI team according to different tasks.
Mixup-Augmented Meta-Learning for Sample-Efficient Fine-Tuning of Protein Simulators
Molecular dynamics simulations have emerged as a fundamental instrument for studying biomolecules.
ALI-DPFL: Differentially Private Federated Learning with Adaptive Local Iterations
Federated Learning (FL) is a distributed machine learning technique that allows model training among multiple devices or organizations by sharing training parameters instead of raw data.
ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate
Text evaluation has historically posed significant challenges, often demanding substantial labor and time cost.
On the Effectiveness of Speech Self-supervised Learning for Music
Our findings suggest that training with music data can generally improve performance on MIR tasks, even when models are trained using paradigms designed for speech.
Multimodal Imbalance-Aware Gradient Modulation for Weakly-supervised Audio-Visual Video Parsing
In this paper, to balance the feature learning processes of different modalities, a dynamic gradient modulation (DGM) mechanism is explored, where a novel and effective metric function is designed to measure the imbalanced feature learning between audio and visual modalities.
LyricWhiz: Robust Multilingual Zero-shot Lyrics Transcription by Whispering to ChatGPT
We introduce LyricWhiz, a robust, multilingual, and zero-shot automatic lyrics transcription method achieving state-of-the-art performance on various lyrics transcription datasets, even in challenging genres such as rock and metal.
NIPD: A Federated Learning Person Detection Benchmark Based on Real-World Non-IID Data
Therefore, we open source a non-IID IoT person detection (NIPD) data set, which is collected from five different cameras.
Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs
To better break down the problem, we define a systematic framework with three components: prompting strategies for eliciting verbalized confidence, sampling methods for generating multiple responses, and aggregation techniques for computing consistency.
Deep Reinforcement Learning with Task-Adaptive Retrieval via Hypernetwork
Deep reinforcement learning algorithms are usually impeded by sampling inefficiency, heavily depending on multiple interactions with the environment to acquire accurate decision-making capabilities.
MARBLE: Music Audio Representation Benchmark for Universal Evaluation
This is evident in the limited work on deep music representations, the scarcity of large-scale datasets, and the absence of a universal and community-driven benchmark.
ChatDB: Augmenting LLMs with Databases as Their Symbolic Memory
Large language models (LLMs) with memory are computationally universal.
MERT: Acoustic Music Understanding Model with Large-Scale Self-supervised Training
Although SSL has been proven effective in speech and audio, its application to music audio has yet to be thoroughly explored.
Med-UniC: Unifying Cross-Lingual Medical Vision-Language Pre-Training by Diminishing Bias
Med-UniC reaches superior performance across 5 medical image tasks and 10 datasets encompassing over 30 diseases, offering a versatile framework for unifying multi-modal medical data within diverse linguistic communities.
TPDM: Selectively Removing Positional Information for Zero-shot Translation via Token-Level Position Disentangle Module
Due to Multilingual Neural Machine Translation's (MNMT) capability of zero-shot translation, many works have been carried out to fully exploit the potential of MNMT in zero-shot translation.
GIMLET: A Unified Graph-Text Model for Instruction-Based Molecule Zero-Shot Learning
We pretrain GIMLET on the molecule tasks along with instructions, enabling the model to transfer effectively to a broad range of tasks.
HUB: Guiding Learned Optimizers with Continuous Prompt Tuning
By incorporating hand-designed optimizers as the second component in our hybrid approach, we are able to retain the benefits of learned optimizers while stabilizing the training process and, more importantly, improving testing performance.
Think Before You Act: Decision Transformers with Working Memory
We argue that this inefficiency stems from the forgetting phenomenon, in which a model memorizes its behaviors in parameters throughout training.
Interactive Natural Language Processing
Interactive Natural Language Processing (iNLP) has emerged as a novel paradigm within the field of NLP, aimed at addressing limitations in existing frameworks while aligning with the ultimate goals of artificial intelligence.
Assessing Hidden Risks of LLMs: An Empirical Study on Robustness, Consistency, and Credibility
With most of the related literature in the era of LLM uncharted, we propose an automated workflow that copes with an upscaled number of queries/responses.
Prompt as Triggers for Backdoor Attack: Examining the Vulnerability in Language Models
Our method does not require external triggers and ensures correct labeling of poisoned samples, improving the stealthy nature of the backdoor attack.
Huatuo-26M, a Large-scale Chinese Medical QA Dataset
Moreover, we also experimentally show the benefit of the proposed dataset in many aspects: (i) trained models for other QA datasets in a zero-shot fashion; and (ii) as external knowledge for retrieval-augmented generation (RAG); and (iii) improving existing pre-trained language models by using the QA pairs as a pre-training corpus in continued training manner.
MUDiff: Unified Diffusion for Complete Molecule Generation
Our model is a promising approach for designing stable and diverse molecules and can be applied to a wide range of tasks in molecular modeling.
When Do Graph Neural Networks Help with Node Classification? Investigating the Impact of Homophily Principle on Node Distinguishability
Homophily principle, i. e., nodes with the same labels are more likely to be connected, has been believed to be the main reason for the performance superiority of Graph Neural Networks (GNNs) over Neural Networks on node classification tasks.
Probabilistic Planning with Prioritized Preferences over Temporal Logic Objectives
We demonstrate the efficacy and applicability of the logic and the algorithm on several case studies with detailed analyses for each.
Chinese Open Instruction Generalist: A Preliminary Release
Instruction tuning is widely recognized as a key technique for building generalist language models, which has attracted the attention of researchers and the public with the release of InstructGPT~\citep{ouyang2022training} and ChatGPT\footnote{\url{https://chat. openai. com/}}.
Chain of Thought Prompt Tuning in Vision Language Models
Chain of Thought is a simple and effective approximation to human reasoning process and has been proven useful for natural language processing (NLP) tasks.
Synthesis of Opacity-Enforcing Winning Strategies Against Colluded Opponent
Furthermore, if such a strategy does not exist, winning for P1 must entail the price of revealing his secret to the observer.
Modular Retrieval for Generalization and Interpretation
Built upon the paradigm, we propose a retrieval model with modular prompt tuning named REMOP.
A Pathway Towards Responsible AI Generated Content
AI Generated Content (AIGC) has received tremendous attention within the past few years, with content generated in the format of image, text, audio, video, etc.
Quantitative Planning with Action Deception in Concurrent Stochastic Games
In this setup, we investigate P1's strategic planning of action deception that decides when to deviate from the Nash equilibrium in P2's game model and employ a hidden action, so that P1 can maximize the value of action deception, which is the additional payoff compared to P1's payoff in the game where P2 has complete information.
CORGI-PM: A Chinese Corpus For Gender Bias Probing and Mitigation
As natural language processing (NLP) for gender bias becomes a significant interdisciplinary topic, the prevalent data-driven techniques such as large-scale language models suffer from data inadequacy and biased corpus, especially for languages with insufficient resources such as Chinese.
A Close Look at Spatial Modeling: From Attention to Convolution
Vision Transformers have shown great promise recently for many vision tasks due to the insightful architecture design and attention mechanism.
MAP-Music2Vec: A Simple and Effective Baseline for Self-Supervised Music Audio Representation Learning
The deep learning community has witnessed an exponentially growing interest in self-supervised learning (SSL).
Adap DP-FL: Differentially Private Federated Learning with Adaptive Noise
The heterogeneity and convergence of training parameters were simply not considered.
SA-DPSGD: Differentially Private Stochastic Gradient Descent based on Simulated Annealing
Differentially private stochastic gradient descent (DPSGD) is the most popular training method with differential privacy in image recognition.
Reconciliation of Pre-trained Models and Prototypical Neural Networks in Few-shot Named Entity Recognition
Incorporating large-scale pre-trained models with the prototypical neural networks is a de-facto paradigm in few-shot named entity recognition.
HERB: Measuring Hierarchical Regional Bias in Pre-trained Language Models
In addition to verifying the existence of regional bias in LMs, we find that the biases on regional groups can be strongly influenced by the geographical clustering of the groups.
1Cademy @ Causal News Corpus 2022: Leveraging Self-Training in Causality Classification of Socio-Political Event Data
This paper details our participation in the Challenges and Applications of Automated Extraction of Socio-political Events from Text (CASE) workshop @ EMNLP 2022, where we take part in Subtask 1 of Shared Task 3.
1Cademy @ Causal News Corpus 2022: Enhance Causal Span Detection via Beam-Search-based Position Selector
In this paper, we present our approach and empirical observations for Cause-Effect Signal Span Detection -- Subtask 2 of Shared task 3~\cite{tan-etal-2022-event} at CASE 2022.
Text Editing as Imitation Game
Text editing, such as grammatical error correction, arises naturally from imperfect textual data.
Opportunistic Qualitative Planning in Stochastic Systems with Incomplete Preferences over Reachability Objectives
We construct a model called an improvement MDP, in which the synthesis of SPI and SASI strategies that guarantee at least one improvement reduces to computing positive and almost-sure winning strategies in an MDP.
Probabilistic Planning with Partially Ordered Preferences over Temporal Goals
We prove that a weak-stochastic nondominated policy given the preference specification is Pareto-optimal in the constructed multi-objective MDP, and vice versa.
On Almost-Sure Intention Deception Planning that Exploits Imperfect Observers
The synthesized attack strategy not only ensures the attack objective is satisfied almost surely but also deceives the defender into believing that the observed behavior is generated by a normal/legitimate user and thus failing to detect the presence of an attack.
Pathway to Future Symbiotic Creativity
This report presents a comprehensive view of our vision on the development path of the human-machine symbiotic art creation.
Graph Neural Networks Intersect Probabilistic Graphical Models: A Survey
Graph Neural Networks (GNNs) are new inference methods developed in recent years and are attracting growing attention due to their effectiveness and flexibility in solving inference and learning problems over graph-structured data.
Biological Sequence Design with GFlowNets
In this work, we propose an active learning algorithm leveraging epistemic uncertainty estimation and the recently proposed GFlowNets as a generator of diverse candidate solutions, with the objective to obtain a diverse batch of useful (as defined by some utility function, for example, the predicted anti-microbial activity of a peptide) and informative candidates after each round.
MentalBERT: Publicly Available Pretrained Language Models for Mental Healthcare
Mental health is a critical issue in modern society, and mental disorders could sometimes turn to suicidal ideation without adequate treatment.
Pre-trained Language Models in Biomedical Domain: A Systematic Survey
In this paper, we summarize the recent progress of pre-trained language models in the biomedical domain and their applications in biomedical downstream tasks.
Learning Multi-Objective Curricula for Robotic Policy Learning
Various automatic curriculum learning (ACL) methods have been proposed to improve the sample efficiency and final performance of deep reinforcement learning (DRL).
Unifying Likelihood-free Inference with Black-box Optimization and Beyond
Black-box optimization formulations for biological sequence design have drawn recent attention due to their promising potential impact on the pharmaceutical industry.
Evolving Decomposed Plasticity Rules for Information-Bottlenecked Meta-Learning
In contrast, biological neural networks (BNNs) can adapt to various new tasks by continually updating the neural connections based on the inputs, which is aligned with the paradigm of learning effective learning rules in addition to static parameters, e. g., meta-learning.
On Orthogonality Constraints for Transformers
Orthogonality constraints encourage matrices to be orthogonal for numerical stability.
Pruning Ternary Quantization
To simultaneously optimize bit-width, model size, and accuracy, we propose pruning ternary quantization (PTQ): a simple, effective, symmetric ternary quantization method.
Towards Representation Identical Privacy-Preserving Graph Neural Network via Split Learning
In recent years, the fast rise in number of studies on graph neural network (GNN) has put it from the theories research to reality application stage.
Few-Shot Domain Adaptation with Polymorphic Transformers
Thus, the chance of overfitting the annotations is greatly reduced, and the model can perform robustly on the target domain after being trained on a few annotated images.
Probabilistic Planning with Preferences over Temporal Goals
We present a formal language for specifying qualitative preferences over temporal goals and a preference-based planning method in stochastic systems.
Beyond Fully-Connected Layers with Quaternions: Parameterization of Hypercomplex Multiplications with $1/n$ Parameters
Recent works have demonstrated reasonable success of representation learning in hypercomplex space.
Parameterization of Hypercomplex Multiplications
Recent works have demonstrated reasonable success of representation learning in hypercomplex space.
FloW: A Dataset and Benchmark for Floating Waste Detection in Inland Waters
To promote the practical application for autonomous floating wastes cleaning, we present FloW, the first dataset for floating waste detection in inland water areas.
Attention-Based Planning with Active Perception
By switching between different attention modes, the robot actively perceives task-relevant information to reduce the cost of information acquisition and processing, while achieving near-optimal task performance.
GLGE: A New General Language Generation Evaluation Benchmark
Multi-task benchmarks such as GLUE and SuperGLUE have driven great progress of pretraining and transfer learning in Natural Language Processing (NLP).
Semantic SLAM with Autonomous Object-Level Data Association
It is often desirable to capture and map semantic information of an environment during simultaneous localization and mapping (SLAM).
Tell Me How to Ask Again: Question Data Augmentation with Controllable Rewriting in Continuous Space
In this paper, we propose a novel data augmentation method, referred to as Controllable Rewriting based Question Data Augmentation (CRQDA), for machine reading comprehension (MRC), question generation, and question-answering natural language inference tasks.
A Theory of Hypergames on Graphs for Synthesizing Dynamic Cyber Defense with Deception
Given qualitative security specifications in formal logic, we show that the solution concepts from hypergames and reactive synthesis in formal methods can be extended to synthesize effective dynamic defense strategy using cyber deception.
Would you Rather? A New Benchmark for Learning Machine Alignment with Cultural Values and Social Preferences
Understanding human preferences, along with cultural and social nuances, lives at the heart of natural language understanding.
CoCon: A Self-Supervised Approach for Controlled Text Generation
While there are studies that seek to control high-level attributes (such as sentiment and topic) of generated text, there is still a lack of more precise control over its content at the word- and phrase-level.
RikiNet: Reading Wikipedia Pages for Natural Question Answering
The representations are then fed into the predictor to obtain the span of the short answer, the paragraph of the long answer, and the answer type in a cascaded manner.
Role-Wise Data Augmentation for Knowledge Distillation
To our knowledge, existing methods overlook the fact that although the student absorbs extra knowledge from the teacher, both models share the same input data -- and this data is the only medium by which the teacher's knowledge can be demonstrated.
Feature Lenses: Plug-and-play Neural Modules for Transformation-Invariant Visual Representations
To make CNNs more invariant to transformations, we propose "Feature Lenses", a set of ad-hoc modules that can be easily plugged into a trained model (referred to as the "host model").
Diverse, Controllable, and Keyphrase-Aware: A Corpus and Method for News Multi-Headline Generation
Furthermore, we propose a simple and effective method to mine the keyphrases of interest in the news article and build a first large-scale keyphrase-aware news headline corpus, which contains over 180K aligned triples of $<$news article, headline, keyphrase$>$.
A Multi-Agent Reinforcement Learning Approach For Safe and Efficient Behavior Planning Of Connected Autonomous Vehicles
The truncated Q-function utilizes the shared information from neighboring CAVs such that the joint state and action spaces of the Q-function do not grow in our algorithm for a large-scale CAV system.
Learning to Locomote with Deep Neural-Network and CPG-based Control in a Soft Snake Robot
Inspired by biological snakes, our control architecture is composed of two key modules: A deep reinforcement learning (RL) module for achieving adaptive goal-tracking behaviors with changing goals, and a central pattern generator (CPG) system with Matsuoka oscillators for generating stable and diverse locomotion patterns.
Jacobian Adversarially Regularized Networks for Robustness
Adversarial examples are crafted with imperceptible perturbations with the intent to fool neural networks.
Learning Sparse Mixture of Experts for Visual Question Answering
We aim to tackle this issue for the specific task of Visual Question Answering (VQA).
Deep Learning-based Radiomic Features for Improving Neoadjuvant Chemoradiation Response Prediction in Locally Advanced Rectal Cancer
The model built with handcrafted features achieved the mean area under the ROC curve (AUC) of 0. 64, while the one built with DL-based features yielded the mean AUC of 0. 73.
Exploring Domain Shift in Extractive Text Summarization
Although domain shift has been well explored in many NLP applications, it still has received little attention in the domain of extractive text summarization.
Interactive Language Learning by Question Answering
In QAit, an agent must interact with a partially observable text-based environment to gather information required to answer questions.
Deep Reinforcement Learning
Machine Reading Comprehension
+1
Interactive Machine Comprehension with Information Seeking Agents
Existing machine reading comprehension (MRC) models do not scale effectively to real-world applications like web-level information retrieval and question answering (QA).
Conditional Computation for Continual Learning
In this study, we analyze parameter sharing under the conditional computation framework where the parameters of a neural network are conditioned on each input example.
Lightweight and Efficient Neural Natural Language Processing with Quaternion Networks
Many state-of-the-art neural models for NLP are heavily parameterized and thus memory inefficient.
Revision in Continuous Space: Unsupervised Text Style Transfer without Adversarial Learning
We propose a new framework that utilizes the gradients to revise the sentence in a continuous space during inference to achieve text style transfer.
Structure Learning for Neural Module Networks
In current formulations of such networks only the parameters of the neural modules and/or the order of their execution is learned.
TIGS: An Inference Algorithm for Text Infilling with Gradient Search
Text infilling is defined as a task for filling in the missing part of a sentence or paragraph, which is suitable for many real-world natural language generation scenarios.
Simple and Effective Curriculum Pointer-Generator Networks for Reading Comprehension over Long Narratives
This paper tackles the problem of reading comprehension over long narratives where documents easily span over thousands of tokens.
Language Modeling with Graph Temporal Convolutional Networks
Recently, there have been some attempts to use non-recurrent neural models for language modeling.
Graph Neural Networks with Generated Parameters for Relation Extraction
Recently, progress has been made towards improving relational reasoning in machine learning field.
Dataflow-based Joint Quantization of Weights and Activations for Deep Neural Networks
This paper addresses a challenging problem - how to reduce energy consumption without incurring performance drop when deploying deep neural networks (DNNs) at the inference stage.
Multi-task Learning over Graph Structures
We present two architectures for multi-task learning with neural sequence models.
Compositional planning in Markov decision processes: Temporal abstraction meets generalized logic composition
Thus, a synthesis algorithm is developed to compute optimal policies efficiently by planning with primitive actions, policies for sub-tasks, and the compositions of sub-policies, for maximizing the probability of satisfying temporal logic specifications.
BFGAN: Backward and Forward Generative Adversarial Networks for Lexically Constrained Sentence Generation
Incorporating prior knowledge like lexical constraints into the model's output to generate meaningful and coherent sentences has many applications in dialogue system, machine translation, image captioning, etc.
Human-in-the-Loop Synthesis for Partially Observable Markov Decision Processes
The efficient verification of this MC gives quantitative insights into the quality of the inferred human strategy by proving or disproving given system specifications.
Inverse Reinforce Learning with Nonparametric Behavior Clustering
In this paper, we introduce the Non-parametric Behavior Clustering IRL algorithm to simultaneously cluster demonstrations and learn multiple reward functions from demonstrations that may be generated from more than one behaviors.
Environment-Independent Task Specifications via GLTL
We propose a new task-specification language for Markov decision processes that is designed to be an improvement over reward functions by being environment independent.
Adaptive Bidirectional Backpropagation: Towards Biologically Plausible Error Signal Transmission in Neural Networks
However, it has been argued that this is not biologically plausible because back-propagating error signals with the exact incoming weights are not considered possible in biological neural systems.
Importance sampling-based approximate optimal planning and control
In this paper, we propose a sampling-based planning and optimal control method of nonlinear systems under non-differentiable constraints.
Systems and Control Robotics 70E60
Deep Q-Networks for Accelerating the Training of Deep Neural Networks
With our approach, a deep RL agent (synonym for optimizer in this work) is used to automatically learn policies about how to schedule learning rates during the optimization of a DNN.
DrMAD: Distilling Reverse-Mode Automatic Differentiation for Optimizing Hyperparameters of Deep Neural Networks
The performance of deep neural networks is well-known to be sensitive to the setting of their hyperparameters.
Integrating active sensing into reactive synthesis with temporal logic constraints under partial observations
We show that by alternating between the observation-based strategy and the active sensing strategy, under a mild technical assumption of the set of sensors in the system, the given temporal logic specification can be satisfied with probability 1.
Probably Approximately Correct MDP Learning and Control With Temporal Logic Constraints
We model the interaction between the system and its environment as a Markov decision process (MDP) with initially unknown transition probabilities.
