Searcharxiv⌕ Search

arXiv subjects

Jie Fu

Publications and source records attributed to Jie Fu.

At least 181 records · Page 10Linked to original sources
arXiv2023

Reinforcement Learning of CPG-regulated Locomotion Controller for a Soft Snake Robot

Intelligent control of soft robots is challenging due to the nonlinear and difficult-to-model dynamics. One promising model-free approach for soft robot control is reinforcement learning (RL). However, model-free RL methods tend to be computationally expensive and data-inefficient and may not yield natural and smooth locomotion patterns for soft robots. In this work, we develop a bio-inspired design of a learning-based goal-tracking controller for a soft snake robot. The controller is composed of two modules: An RL module for learning goal-tracking behaviors given the unmodeled and stochastic dynamics of the robot, and a central pattern generator (CPG) with the Matsuoka oscillators for generating stable and diverse locomotion patterns. We theoretically investigate the maneuverability of Matsuoka CPG's oscillation bias, frequency, and amplitude for steering control, velocity control, and sim-to-real adaptation of the soft snake robot. Based on this analysis, we proposed a composition of RL and CPG modules such that the RL module regulates the tonic inputs to the CPG system given state feedback from the robot, and the output of the CPG module is then transformed into pressure inputs to pneumatic actuators of the soft snake robot. This design allows the RL agent to naturally learn to entrain the desired locomotion patterns determined by the CPG maneuverability. We validated the optimality and robustness of the control design in both simulation and real experiments, and performed extensive comparisons with state-of-art RL methods to demonstrate the benefit of our bio-inspired control design.

cs.RO↗
arXiv2023

Multimodal Imbalance-Aware Gradient Modulation for Weakly-supervised Audio-Visual Video Parsing

Weakly-supervised audio-visual video parsing (WS-AVVP) aims to localize the temporal extents of audio, visual and audio-visual event instances as well as identify the corresponding event categories with only video-level category labels for training. Most previous methods pay much attention to refining the supervision for each modality or extracting fruitful cross-modality information for more reliable feature learning. None of them have noticed the imbalanced feature learning between different modalities in the task. 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. Furthermore, principle analysis indicates that the multimodal confusing calculation will hamper the precise measurement of multimodal imbalanced feature learning, which further weakens the effectiveness of our DGM mechanism. To cope with this issue, a modality-separated decision unit (MSDU) is designed for more precise measurement of imbalanced feature learning between audio and visual modalities. Comprehensive experiments are conducted on public benchmarks and the corresponding experimental results demonstrate the effectiveness of our proposed method.

cs.CV↗
arXiv2023

Optimizing Sensor Allocation against Attackers with Uncertain Intentions: A Worst-Case Regret Minimization Approach

This paper is concerned with the optimal allocation of detection resources (sensors) to mitigate multi-stage attacks, in the presence of the defender's uncertainty in the attacker's intention. We model the attack planning problem using a Markov decision process and characterize the uncertainty in the attacker's intention using a finite set of reward functions -- each reward represents a type of the attacker. Based on this modeling framework, we employ the paradigm of the worst-case absolute regret minimization from robust game theory and develop mixed-integer linear program (MILP) formulations for solving the worst-case regret minimizing sensor allocation strategies for two classes of attack-defend interactions: one where the defender and attacker engage in a zero-sum game, and another where they engage in a non-zero-sum game. We demonstrate the effectiveness of our framework using a stochastic gridworld example.

cs.GT↗
arXiv2023

Chain of Thought Prompt Tuning in Vision Language Models

Language-Image Pre-training has demonstrated promising results on zero-shot and few-shot downstream tasks by prompting visual models with natural language prompts. However, most recent studies only use a single prompt for tuning, neglecting the inherent step-to-step cognitive reasoning process that humans conduct in complex task settings, for example, when processing images from unfamiliar domains. Chain of Thought is a simple and effective approximation to human reasoning process and has been proven useful for natural language processing (NLP) tasks. Based on this cognitive intuition, we believe that conducting effective reasoning is also an important problem in visual tasks, and a chain of thought could be a solution to this problem. In this work, we propose a novel chain of thought prompt tuning for vision-language modeling. Extensive experiments show that our method not only generalizes better in image classification tasks, has greater transferability beyond a single dataset, and has stronger domain generalization performance, but also performs much better in imagetext retrieval and visual question answering, which require more reasoning capabilities. We are the first to successfully adapt chain-of-thought prompting that combines visual and textual embeddings. We will release our codes

cs.CV↗
arXiv2023

ChatDB: Augmenting LLMs with Databases as Their Symbolic Memory

Large language models (LLMs) with memory are computationally universal. However, mainstream LLMs are not taking full advantage of memory, and the designs are heavily influenced by biological brains. Due to their approximate nature and proneness to the accumulation of errors, conventional neural memory mechanisms cannot support LLMs to simulate complex reasoning. In this paper, we seek inspiration from modern computer architectures to augment LLMs with symbolic memory for complex multi-hop reasoning. Such a symbolic memory framework is instantiated as an LLM and a set of SQL databases, where the LLM generates SQL instructions to manipulate the SQL databases. We validate the effectiveness of the proposed memory framework on a synthetic dataset requiring complex reasoning. The project website is available at https://chatdatabase.github.io/ .

cs.AI↗
arXiv2023

HUB: Guiding Learned Optimizers with Continuous Prompt Tuning

Learned optimizers are a crucial component of meta-learning. Recent advancements in scalable learned optimizers have demonstrated their superior performance over hand-designed optimizers in various tasks. However, certain characteristics of these models, such as an unstable learning curve, limited ability to handle unseen tasks and network architectures, difficult-to-control behaviours, and poor performance in fine-tuning tasks impede their widespread adoption. To tackle the issue of generalization in scalable learned optimizers, we propose a hybrid-update-based (HUB) optimization strategy inspired by recent advancements in hard prompt tuning and result selection techniques used in large language and vision models. This approach can be easily applied to any task that involves hand-designed or learned optimizer. 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. We validate our design through a total of 17 tasks, consisting of thirteen training from scratch and four fine-tuning settings. These tasks vary in model sizes, architectures, or dataset sizes, and the competing optimizers are hyperparameter-tuned. We outperform all competitors in 94% of the tasks with better testing performance. Furthermore, we conduct a theoretical analysis to examine the potential impact of our hybrid strategy on the behaviours and inherited traits of learned optimizers.

cs.LG↗
arXiv2023

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. It is often hypothesized that positional information may hinder the MNMT from outputting a robust encoded representation for decoding. However, previous approaches treat all the positional information equally and thus are unable to selectively remove certain positional information. In sharp contrast, this paper investigates how to learn to selectively preserve useful positional information. We describe the specific mechanism of positional information influencing MNMT from the perspective of linguistics at the token level. We design a token-level position disentangle module (TPDM) framework to disentangle positional information at the token level based on the explanation. Our experiments demonstrate that our framework improves zero-shot translation by a large margin while reducing the performance loss in the supervised direction compared to previous works.

cs.CL↗
arXiv2023

Biological Sequence Design with GFlowNets

Design of de novo biological sequences with desired properties, like protein and DNA sequences, often involves an active loop with several rounds of molecule ideation and expensive wet-lab evaluations. These experiments can consist of multiple stages, with increasing levels of precision and cost of evaluation, where candidates are filtered. This makes the diversity of proposed candidates a key consideration in the ideation phase. 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. We also propose a scheme to incorporate existing labeled datasets of candidates, in addition to a reward function, to speed up learning in GFlowNets. We present empirical results on several biological sequence design tasks, and we find that our method generates more diverse and novel batches with high scoring candidates compared to existing approaches.

q-bio.BM↗
arXiv2023

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. This paradigm considers language models as agents capable of observing, acting, and receiving feedback iteratively from external entities. Specifically, language models in this context can: (1) interact with humans for better understanding and addressing user needs, personalizing responses, aligning with human values, and improving the overall user experience; (2) interact with knowledge bases for enriching language representations with factual knowledge, enhancing the contextual relevance of responses, and dynamically leveraging external information to generate more accurate and informed responses; (3) interact with models and tools for effectively decomposing and addressing complex tasks, leveraging specialized expertise for specific subtasks, and fostering the simulation of social behaviors; and (4) interact with environments for learning grounded representations of language, and effectively tackling embodied tasks such as reasoning, planning, and decision-making in response to environmental observations. This paper offers a comprehensive survey of iNLP, starting by proposing a unified definition and framework of the concept. We then provide a systematic classification of iNLP, dissecting its various components, including interactive objects, interaction interfaces, and interaction methods. We proceed to delve into the evaluation methodologies used in the field, explore its diverse applications, scrutinize its ethical and safety issues, and discuss prospective research directions. This survey serves as an entry point for researchers who are interested in this rapidly evolving area and offers a broad view of the current landscape and future trajectory of iNLP.

cs.CL↗
arXiv2023

Huatuo-26M, a Large-scale Chinese Medical QA Dataset

In this paper, we release a largest ever medical Question Answering (QA) dataset with 26 million QA pairs. We benchmark many existing approaches in our dataset in terms of both retrieval and generation. Experimental results show that the existing models perform far lower than expected and the released dataset is still challenging in the pre-trained language model era. 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. We believe that this dataset will not only contribute to medical research but also facilitate both the patients and clinical doctors. See \url{https://github.com/FreedomIntelligence/Huatuo-26M}.

cs.CL↗
arXiv2023

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/}}. Despite impressive progress in English-oriented large-scale language models (LLMs), it is still under-explored whether English-based foundation LLMs can perform similarly on multilingual tasks compared to English tasks with well-designed instruction tuning and how we can construct the corpora needed for the tuning. To remedy this gap, we propose the project as an attempt to create a Chinese instruction dataset by various methods adapted to the intrinsic characteristics of 4 sub-tasks. We collect around 200k Chinese instruction tuning samples, which have been manually checked to guarantee high quality. We also summarize the existing English and Chinese instruction corpora and briefly describe some potential applications of the newly constructed Chinese instruction corpora. The resulting \textbf{C}hinese \textbf{O}pen \textbf{I}nstruction \textbf{G}eneralist (\textbf{COIG}) corpora are available in Huggingface\footnote{\url{https://huggingface.co/datasets/BAAI/COIG}} and Github\footnote{\url{https://github.com/BAAI-Zlab/COIG}}, and will be continuously updated.

cs.CL↗
arXiv2023

Probabilistic Planning with Prioritized Preferences over Temporal Logic Objectives

This paper studies temporal planning in probabilistic environments, modeled as labeled Markov decision processes (MDPs), with user preferences over multiple temporal goals. Existing works reflect such preferences as a prioritized list of goals. This paper introduces a new specification language, termed prioritized qualitative choice linear temporal logic on finite traces, which augments linear temporal logic on finite traces with prioritized conjunction and ordered disjunction from prioritized qualitative choice logic. This language allows for succinctly specifying temporal objectives with corresponding preferences accomplishing each temporal task. The finite traces that describe the system's behaviors are ranked based on their dissatisfaction scores with respect to the formula. We propose a systematic translation from the new language to a weighted deterministic finite automaton. Utilizing this computational model, we formulate and solve a problem of computing an optimal policy that minimizes the expected score of dissatisfaction given user preferences. We demonstrate the efficacy and applicability of the logic and the algorithm on several case studies with detailed analyses for each.

cs.FL↗
arXiv2023

Synthesis of Opacity-Enforcing Winning Strategies Against Colluded Opponent

This paper studies a language-based opacity enforcement in a two-player, zero-sum game on a graph. In this game, player 1 (P1) wins if it can achieve a secret temporal goal described by the language of a finite automaton, no matter what strategy the opponent player 2 (P2) selects. In addition, P1 aims to win while making its goal opaque to a passive observer with imperfect information. However, P2 colludes with the observer to reveal P1's secret whenever P2 cannot prevent P1 from achieving its goal, and therefore, opacity must be enforced against P2. We show that a winning and opacity-enforcing strategy for P1 can be computed by reducing the problem to solving a reachability game augmented with observer's belief states. Furthermore, if such a strategy does not exist, winning for P1 must entail the price of revealing his secret to the observer. We demonstrate our game-theoretic solution of opacity-enforcement control through a small illustrative example and in a robot motion planning problem.

eess.SY↗
arXiv2023

Quantitative Planning with Action Deception in Concurrent Stochastic Games

We study a class of two-player competitive concurrent stochastic games on graphs with reachability objectives. Specifically, player 1 aims to reach a subset $F_1$ of game states, and player 2 aims to reach a subset $F_2$ of game states where $F_2\cap F_1=\emptyset$. Both players aim to satisfy their reachability objectives before their opponent does. Yet, the information players have about the game dynamics is asymmetric: P1 has a (set of) hidden actions unknown to P2 at the beginning of their interaction. 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. Anticipating that P2 may detect his misperception about the game and adapt his strategy during interaction in unpredictable ways, we construct a planning problem for P1 to augment the game model with an incomplete model about the theory of mind of the opponent P2. While planning in the augmented game, P1 can effectively influence P2's perception so as to entice P2 to take actions that benefit P1. We prove that the proposed deceptive planning algorithm maximizes a lower bound on the value of action deception and demonstrate the effectiveness of our deceptive planning algorithm using a robot motion planning problem inspired by soccer games.

eess.SY↗
arXiv2023

Modular Retrieval for Generalization and Interpretation

New retrieval tasks have always been emerging, thus urging the development of new retrieval models. However, instantiating a retrieval model for each new retrieval task is resource-intensive and time-consuming, especially for a retrieval model that employs a large-scale pre-trained language model. To address this issue, we shift to a novel retrieval paradigm called modular retrieval, which aims to solve new retrieval tasks by instead composing multiple existing retrieval modules. Built upon the paradigm, we propose a retrieval model with modular prompt tuning named REMOP. It constructs retrieval modules subject to task attributes with deep prompt tuning, and yields retrieval models subject to tasks with module composition. We validate that, REMOP inherently with modularity not only has appealing generalizability and interpretability in preliminary explorations, but also achieves comparable performance to state-of-the-art retrieval models on a zero-shot retrieval benchmark.\footnote{Our code is available at \url{https://github.com/FreedomIntelligence/REMOP}}

cs.IR↗
arXiv2023

Probabilistic Planning with Partially Ordered Preferences over Temporal Goals

In this paper, we study planning in stochastic systems, modeled as Markov decision processes (MDPs), with preferences over temporally extended goals. Prior work on temporal planning with preferences assumes that the user preferences form a total order, meaning that every pair of outcomes are comparable with each other. In this work, we consider the case where the preferences over possible outcomes are a partial order rather than a total order. We first introduce a variant of deterministic finite automaton, referred to as a preference DFA, for specifying the user's preferences over temporally extended goals. Based on the order theory, we translate the preference DFA to a preference relation over policies for probabilistic planning in a labeled MDP. In this treatment, a most preferred policy induces a weak-stochastic nondominated probability distribution over the finite paths in the MDP. The proposed planning algorithm hinges on the construction of a multi-objective MDP. We prove that a weak-stochastic nondominated policy given the preference specification is Pareto-optimal in the constructed multi-objective MDP, and vice versa. Throughout the paper, we employ a running example to demonstrate the proposed preference specification and solution approaches. We show the efficacy of our algorithm using the example with detailed analysis, and then discuss possible future directions.

cs.RO↗
arXiv2023

Bidirectional Learning for Offline Infinite-width Model-based Optimization

In offline model-based optimization, we strive to maximize a black-box objective function by only leveraging a static dataset of designs and their scores. This problem setting arises in numerous fields including the design of materials, robots, DNA sequences, and proteins. Recent approaches train a deep neural network (DNN) on the static dataset to act as a proxy function, and then perform gradient ascent on the existing designs to obtain potentially high-scoring designs. This methodology frequently suffers from the out-of-distribution problem where the proxy function often returns poor designs. To mitigate this problem, we propose BiDirectional learning for offline Infinite-width model-based optimization (BDI). BDI consists of two mappings: the forward mapping leverages the static dataset to predict the scores of the high-scoring designs, and the backward mapping leverages the high-scoring designs to predict the scores of the static dataset. The backward mapping, neglected in previous work, can distill more information from the static dataset into the high-scoring designs, which effectively mitigates the out-of-distribution problem. For a finite-width DNN model, the loss function of the backward mapping is intractable and only has an approximate form, which leads to a significant deterioration of the design quality. We thus adopt an infinite-width DNN model, and propose to employ the corresponding neural tangent kernel to yield a closed-form loss for more accurate design updates. Experiments on various tasks verify the effectiveness of BDI. The code is available at https://github.com/GGchen1997/BDI.

cs.CE↗
arXiv2023

Graph Neural Networks Intersect Probabilistic Graphical Models: A Survey

Graphs are a powerful data structure to represent relational data and are widely used to describe complex real-world data structures. Probabilistic Graphical Models (PGMs) have been well-developed in the past years to mathematically model real-world scenarios in compact graphical representations of distributions of variables. 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. These two powerful approaches have different advantages in capturing relations from observations and how they conduct message passing, and they can benefit each other in various tasks. In this survey, we broadly study the intersection of GNNs and PGMs. Specifically, we first discuss how GNNs can benefit from learning structured representations in PGMs, generate explainable predictions by PGMs, and how PGMs can infer object relationships. Then we discuss how GNNs are implemented in PGMs for more efficient inference and structure learning. In the end, we summarize the benchmark datasets used in recent studies and discuss promising future directions.

cs.AI↗