← Search

Bin Liang

103 accepted papers

2026

Expectation Alignment of Language Models for Real-World User Expectations

ICML 2026poster

Large language models (LLMs) have demonstrated remarkable performance on standard benchmarks, yet it remains largely unexplored whether they truly meet user expectations. Existing evaluation approaches, relying on model heuristics, expert rubrics, or user simulation, fail to capture the diversity an…

Cited by 0SourceScholar
2026

HD-CDAM: A Heterogeneous Differential Cable-Driven Anthropomorphic Manipulator With High Payload-Weight Ratio

RA-L 2026

With the increasing demand for lightweight, large payload-to-weight ratio, and highly dynamic robotic arms for general-purpose applications, conventional designs inevitably face a significant trade-off among safety, payload capacity, and motion agility. This paper presents a 7 degree-of-freedom cabl

Cited by 0SourceScholar
2026

MemGuide: Intent-Driven Memory Selection for Goal-Oriented Multi-Session LLM Agents

AAAI 2026technical

Modern task-oriented dialogue (TOD) systems increasingly rely on large language model (LLM) agents, leveraging Retrieval-Augmented Generation (RAG) and long-context capabilities for long-term memory utilization. However, these methods prioritise semantic similarity over task intent, degrading multi-

Cited by 0SourcePDFScholar
2026

Memory-T1: Reinforcement Learning for Temporal Reasoning in Multi-session Agents

ICLR 2026poster

Temporal reasoning over long, multi-session dialogues is a critical capability for conversational agents. As dialogue histories grow in length and accumulate noise, existing long-context models struggle to accurately identify temporally pertinent information, significantly impairing reasoning perfor…

Cited by 0SourcecodeScholar
2026

Nav-SCOPE: Swarm Robot Cooperative Perception and Coordinated Navigation (I)

ICRA 2026poster

This paper proposes a lightweight decentralized solution for multi-robot coordinated navigation with cooperative perception. First, we introduce a rapid way to process sensory data, thus obtaining safe directions and key environmental features. Then, an information flow is created to facilitate real…

Cited by 0Scholar
2026

Shadows in the Code: Exploring the Risks and Defenses of LLM-based Multi-Agent Software Development Systems

AAAI 2026technical

The rapid advancement of Large Language Model (LLM)-driven multi-agent systems has significantly streamlined software developing tasks, enabling users with little technical expertise to develop executable applications. While these systems democratize software creation through natural language requir

Cited by 0SourcePDFScholar
2026

Single-Actuator Gripper Using an Antagonistic Cable-Driven Differential Mechanism for Adaptive Fixed-Position Grasping

RA-L 2026

Fixed-position grasping is an efficient strategy in robotic assembly. Adaptive grippers employing differential mechanisms (DMs) can passively compensate for misalignment between gripper and object. However, conventional DMs, such as gear-based differential mechanisms (GDMs), are limited by rotationa

Cited by 0SourceScholar
2026

Stroke-Based Variable-Damping with Force Attenuation for Capturing Large-Momentum Objects under Non-Zero Contact Velocity

ICRA 2026poster

Basketball players catch fast passes, and porters unload goods with apparent ease. These actions demonstrate how humans rely on intelligent regulation strategies to drive muscle activity. Replicating similar dynamic responses and strong impact absorption in robotics, however, remains a major challen…

Cited by 0Scholar
2025

A Comprehensive Evaluation on Event Reasoning of Large Language Models

AAAI 2025technical

Event reasoning is a fundamental ability that underlies many applications. It requires event schema knowledge to perform global reasoning and needs to deal with the diversity of the inter-event relations and the reasoning paradigms. The extent to which LLMs excel in event reasoning across various re…

2025

A Multi-persona Framework for Argument Quality Assessment

ACL 2025long

Argument quality assessment faces inherent challenges due to its subjective nature, where different evaluators may assign varying quality scores for an argument based on personal perspectives. Although existing datasets collect opinions from multiple annotators to model subjectivity, most existing c…

2025

A New Formula for Sticker Retrieval: Reply with Stickers in Multi-Modal and Multi-Session Conversation

AAAI 2025technical

Stickers are widely used in online chatting, which can vividly express someone's intention, emotion, or attitude. Existing conversation research typically retrieves stickers based on a single session or the previous textual information, which can not adapt to the multi-modal and multi-session nature…

Cited by 0SourcePDFScholar
2025

Bootstrapping LLM-based Fact-checking via Iterative Rationalization Finetuning

ICASSP 2025accepted

Fact-checking, the task of reasoning about a claim’s truthfulness based on evidence, has become increasingly crucial with the rapid spread of misinformation. In real-world scenarios, fact-checking often involves checking complex claims necessitating multi-step reasoning, thus imposing a high require…

Cited by 0SourceScholar
2025

COPR: Continual Human Preference Learning via Optimal Policy Regularization

ACL 2025finding

Reinforcement Learning from Human Feedback (RLHF) is effective for aligning Large Language Models (LLMs) with human preferences. However, RLHF’s complex process limits its ability to continually learn human feedback, making it impractical for real-world applications where the deployed model continuo…

Cited by 0SourcePDFScholar
2025

CS-Bench: A Comprehensive Benchmark for Large Language Models towards Computer Science Mastery

ICLR 2025poster

Large language models (LLMs) have demonstrated significant potential in advancing various fields of research and society. However, the current community of LLMs overly focuses on benchmarks for analyzing specific foundational skills (e.g. mathematics and code generation), neglecting an all-round eva…

2025

CoCoCo: Improving Text-Guided Video Inpainting for Better Consistency, Controllability and Compatibility

AAAI 2025technical

Video inpainting is a crucial task with diverse applications, including fine-grained video editing, video recovery, and video dewatermarking. However, most existing video inpainting methods primarily focus on visual content completion while neglecting text information. There are only a limited numbe…

2025

CoreEval: Automatically Building Contamination-Resilient Datasets with Real-World Knowledge toward Reliable LLM Evaluation

ACL 2025long

Data contamination poses a significant challenge to the fairness of LLM evaluations in natural language processing tasks by inadvertently exposing models to test data during training.Current studies mitigate this issue by modifying existing datasets or generating new ones from freshly collected info…

Cited by 0SourcePDFScholar
2025

Correcting Large Language Model Behavior via Influence Function

AAAI 2025technical

Recent advancements in AI alignment techniques have significantly improved the alignment of large language models (LLMs) with static human preferences. However, the dynamic nature of human preferences can render some prior training data outdated or even erroneous, ultimately causing LLMs to deviate…

Cited by 0SourcePDFScholar
2025

CushionCatch: A Compliant Catching Mechanism for Mobile Manipulators via Combined Optimization and Learning

IROS 2025

Catching flying objects with a cushioning process is a skill commonly performed by humans, yet it remains a significant challenge for robots. In this paper, we present a framework that combines optimization and learning to achieve compliant catching on mobile manipulators (CCMM). First, we propose a

Cited by 1SourceScholar
2025

Efficient Collision Detection Framework for Enhancing Collision-Free Robot Motion

ICRA 2025

Fast and efficient collision detection is essential for motion generation in robotics. In this paper, we propose an efficient collision detection framework based on the Signed Distance Field (SDF) of robots, seamlessly integrated with a self-collision detection module. Firstly, we decompose the robo

Cited by 5SourceScholar
2025

Enhancing Emotion Reasoning for Image Multi-Emotion Prediction

ICASSP 2025accepted

Image multi-emotion prediction aims to identify the emotions evoked by images in humans. In the real world, individual cognitive differences can lead to different viewers experiencing varied emotions. Most existing researchers primarily focus on analyzing image features, which are limited to the per…

Cited by 0SourceScholar
2025

Episodic Novelty Through Temporal Distance

ICLR 2025poster

Exploration in sparse reward environments remains a significant challenge in reinforcement learning, particularly in Contextual Markov Decision Processes (CMDPs), where environments differ across episodes. Existing episodic intrinsic motivation methods for CMDPs primarily rely on count-based approac…

Cited by 0SourcePDFScholar
2025

Flexibly Utilize Memory for Long-Term Conversation via a Fragment-then-Compose Framework

EMNLP 2025

Large language models (LLMs) have made significant breakthroughs in extracting useful information from conversation history to enhance the response in long-term conversations. Summarizing useful information from historical conversations has achieved remarkable performance, which, however, may introd

2025

KD-RIEKF: Kinodynamic Right-Invariant EKF for Legged Robot State Estimation

IROS 2025

We present KD-RIEKF, a novel state estimation framework that incorporates kinodynamic constraints into the Right-Invariant Extended Kalman Filter (RIEKF). Our framework integrates generalized momentum-based contact estimation, centroidal dynamics, and a noise-adaptive module, improving state estimat

Cited by 0SourceScholar
2025

Learning First-Order Logic Rules for Argumentation Mining

ACL 2025long

Argumentation Mining (AM) aims to extract argumentative structures from texts by identifying argumentation components (ACs) and their argumentative relations (ARs). While previous works focus on representation learning to encode ACs and AC pairs, they fail to explicitly model the underlying reasonin…

Cited by 0SourcePDFScholar
2025

MISCGrasp: Leveraging Multiple Integrated Scales and Contrastive Learning for Enhanced Volumetric Grasping

IROS 2025

Robotic grasping faces challenges in adapting to objects with varying shapes and sizes. In this paper, we introduce MISCGrasp, a volumetric grasping method that integrates multi-scale feature extraction with contrastive feature enhancement for self-adaptive grasping. We propose a query-based interac

Cited by 2SourcecodeScholar
2025

MemeReaCon: Probing Contextual Meme Understanding in Large Vision-Language Models

EMNLP 2025

Memes have emerged as a popular form of multimodal online communication, where their interpretation heavily depends on the specific context in which they appear. Current approaches predominantly focus on isolated meme analysis, either for harmful content detection or standalone interpretation, overl

Cited by 0SourcePDFScholar
2025

Mitigating Biases of Large Language Models in Stance Detection with Counterfactual Augmented Calibration

NAACL 2025long

Stance detection is critical for understanding the underlying position or attitude expressed toward a topic. Large language models (LLMs) have demonstrated significant advancements across various natural language processing tasks including stance detection, however, their performance in stance detec…

2025

MlingConf: A Comprehensive Study of Multilingual Confidence Estimation on Large Language Models

ACL 2025finding

The tendency of Large Language Models (LLMs) to generate hallucinations raises concerns regarding their reliability. Therefore, confidence estimations indicating the extent of trustworthiness of the generations become essential. However, current LLM confidence estimations in languages other than Eng…

2025

NeuGrasp: Generalizable Neural Surface Reconstruction with Background Priors for Material-Agnostic Object Grasp Detection

ICRA 2025

Robotic grasping in scenes with transparent and specular objects presents great challenges for methods relying on accurate depth information. In this paper, we introduce NeuGrasp, a neural surface reconstruction method that leverages background priors for material-agnostic grasp detection. NeuGrasp

Cited by 3SourcecodeScholar
2025

PEARL: Towards Permutation-Resilient LLMs

ICLR 2025poster

The in-context learning (ICL) capability of large language models (LLMs) enables them to perform challenging tasks using provided demonstrations. However, ICL is highly sensitive to the ordering of demonstrations, leading to instability in predictions. This paper shows that this vulnerability can be…

2025

ReSURE: Regularizing Supervision Unreliability for Multi-turn Dialogue Fine-tuning

EMNLP 2025

Fine-tuning multi-turn dialogue systems requires high-quality supervision but often suffers from degraded performance when exposed to low-quality data. Supervision errors in early turns can propagate across subsequent turns, undermining coherence and response quality. Existing methods typically addr

2025

Robust and High-Fidelity 3D Gaussian Splatting: Fusing Pose Priors and Geometry Constraints for Texture-Deficient Outdoor Scenes

IROS 2025

3D Gaussian Splatting (3DGS) has emerged as a key rendering pipeline for digital asset creation due to its balance between efficiency and visual quality. To address the issues of unstable pose estimation and scene representation distortion caused by geometric texture inconsistency in large outdoor s

Cited by 2SourcecodeScholar
2025

Semi-distributed Cross-modal Air-Ground Relative Localization

IROS 2025

Efficient, accurate, and flexible relative localization is crucial in air-ground collaborative tasks. However, current approaches for robot relative localization are primarily realized in the form of distributed multi-robot SLAM systems with the same sensor configuration, which are tightly coupled w

Cited by 0SourcecodeScholar
2025

Señorita-2M: A High-Quality Instruction-based Dataset for General Video Editing by Video Specialists

NeurIPS 2025poster

Video content editing has a wide range of applications. With the advancement of diffusion-based generative models, video editing techniques have made remarkable progress, yet they still remain far from practical usability. Existing inversion-based video editing methods are time-consuming and struggl…

Cited by 0SourcecodeScholar
2025

Steady-State Drifting Equilibrium Analysis of Single-Track Two-Wheeled Robots for Controller Design

IROS 2025

Drifting is an advanced driving technique where the wheeled robot’s tire-ground interaction breaks the common non-holonomic pure rolling constraint. This allows high-maneuverability tasks like quick cornering, and steady-state drifting control enhances motion stability under lateral slip conditions.

Cited by 1SourceScholar
2025

T2: An Adaptive Test-Time Scaling Strategy for Contextual Question Answering

EMNLP 2025

Recent advances in large language models have demonstrated remarkable performance on Contextual Question Answering (CQA). However, prior approaches typically employ elaborate reasoning strategies regardless of question complexity, leading to low adaptability. Recent efficient test-time scaling metho

2024

A Planar Compliant Contact Control Applied to Multi-dimensional Elastic Gripper for Unexpected Contact

ICRA 2024poster

It is difficult to guarantee an empty living environment to prevent unexpected contact between the object being manipulated by the robot and unplanned obstacles. In this paper, we propose a planar compliant contact control method for planar manipulation to cope with unexpected contact. We first use…

Cited by 0SourceScholar
2024

Adaptive Graph Learning for Multimodal Conversational Emotion Detection

AAAI 2024technical

Multimodal Emotion Recognition in Conversations (ERC) aims to identify the emotions conveyed by each utterance in a conversational video. Current efforts encounter challenges in balancing intra- and inter-speaker context dependencies when tackling intra-modal interactions. This balance is vital as i…

2024

Bounded and Uniform Energy-based Out-of-distribution Detection for Graphs

ICML 2024poster

Given the critical role of graphs in real-world applications and their high-security requirements, improving the ability of graph neural networks (GNNs) to detect out-of-distribution (OOD) data is an urgent research problem. The recent work GNNSAFE proposes a framework based on the aggregation of ne…

2024

Decomposing Argumentative Essay Generation via Dialectical Planning of Complex Reasoning

ACL 2024findings

Argumentative Essay Generation (AEG) is a challenging task in computational argumentation, where detailed logical reasoning and effective rhetorical skills are essential.Previous methods on argument generation typically involve planning prior to generation.However, the planning strategies in these m…

Cited by 1SourcePDFScholar
2024

Design and Development of Composite Linkage Mechanism for Cable-Driven Segmented Manipulator to Increase Synchronous Accuracy and Transmission Distance

RA-L 2024

Cable-driven segmented manipulators (CDSMs) have high dexterity and large bending characteristics with less motors, which have great potential for long-range manipulation in structured environment. However, as joints’ number and segments’ length increase, the synchronous performance will largely dec

Cited by 3SourceScholar
2024

Discourse Structure-Aware Prefix for Generation-Based End-to-End Argumentation Mining

ACL 2024findings

End-to-end argumentation mining (AM) aims to extract the argumentation structure including argumentation components and their argumentation relations from text. Recent developments in end-to-end AM models have demonstrated significant progress by redefining the AM task as a sequence generation task,…

2024

Efficient Multi-agent Reinforcement Learning by Planning

ICLR 2024poster

Multi-agent reinforcement learning (MARL) algorithms have accomplished remarkable breakthroughs in solving large-scale decision-making tasks. Nonetheless, most existing MARL algorithms are model-free, limiting sample efficiency and hindering their applicability in more challenging scenarios. In cont…

2024

Enhancing Argumentative Relation Classification by Multi-Granularity Retrieval and Heterogeneous Graph Reasoning

ICASSP 2024accepted

Argumentative relation classification (ARC) aims to identify the relation between arguments. Previous methods that employ structured knowledge graphs to tackle the ARC task have achieved promising results. However, the prerequisite for structured knowledge to function is that the knowledge includes…

Cited by 0SourceScholar
2024

Highly Efficient Observation Process Based on FFT Filtering for Robot Swarm Collaborative Navigation in Unknown Environments*

IROS 2024poster

Collaborative path planning for robot swarms in complex, unknown environments without external positioning is a challenging problem. This requires robots to find safe directions based on real-time environmental observations, and to efficiently transfer and fuse these observations within the swarm. T…

Cited by 1SourceScholar
2024

Hybrid Trajectory Optimization for Autonomous Terrain Traversal of Articulated Tracked Robots

RA-L 2024

Autonomous terrain traversal of articulated tracked robots can reduce operator cognitive load to enhance task efficiency and facilitate extensive deployment. We present a novel hybrid trajectory optimization method aimed at generating efficient, stable, and smooth traversal motions. To achieve this,

Cited by 12SourceScholar
2024

In-Context Example Retrieval from Multi-Perspectives for Few-Shot Aspect-Based Sentiment Analysis

COLING 2024main

In this paper, we focus on few-shot aspect-based sentiment analysis (ABSA) and try to solve it with in-context learning (ICL) paradigm. However, the effectiveness of ICL is highly affected by retrieved in-context examples. Previous works generally leverage the semantic similarity between the candida…

Cited by 6SourcePDFScholar
2024

JoTR: A Joint Transformer and Reinforcement Learning Framework for Dialogue Policy Learning

COLING 2024main

Dialogue policy learning (DPL) aims to determine an abstract representation (also known as action) to guide what the response should be. Typically, DPL is cast as a sequential decision problem across a series of predefined action candidates. However, such static and narrow actions can limit response…

2024

Learning Diverse Risk Preferences in Population-Based Self-Play

AAAI 2024technical

Among the remarkable successes of Reinforcement Learning (RL), self-play algorithms have played a crucial role in solving competitive games. However, current self-play RL methods commonly optimize the agent to maximize the expected win-rates against its current or historical copies, resulting in a l…

2024

Multi-modal Stance Detection: New Datasets and Model

ACL 2024findings

Stance detection is a challenging task that aims to identify public opinion from social media platforms with respect to specific targets. Previous work on stance detection largely focused on pure texts. In this paper, we study multi-modal stance detection for tweets consisting of texts and images, w…

2024

Multiple Knowledge-Enhanced Interactive Graph Network for Multimodal Conversational Emotion Recognition

EMNLP 2024finding

Multimodal Emotion Recognition in Conversations (ERC) aims to identify emotions in conversational videos. Current efforts focus on modeling both context-sensitive and speaker-sensitive dependencies and multimodal fusion. Despite the progress, models in Multimodal ERC (MERC) still struggle due to a l…

Cited by 1SourcePDFScholar
2024

NeuralPlane: An Efficiently Parallelizable Platform for Fixed-wing Aircraft Control with Reinforcement Learning

NeurIPS 2024poster

Reinforcement learning (RL) demonstrates superior potential over traditional flight control methods for fixed-wing aircraft, particularly under extreme operational conditions. However, the high demand for training samples and the lack of efficient computation in existing simulators hinder its furthe…

2024

PITA: Prompting Task Interaction for Argumentation Mining

ACL 2024long

Argumentation mining (AM) aims to detect the arguments and their inherent relations from argumentative textual compositions. Generally, AM comprises three key challenging subtasks, including argument component type classification (ACTC), argumentative relation identification (ARI), and argumentative…

2024

Path Generation for Wheeled Robots Autonomous Navigation on Vegetated Terrain

RA-L 2024

Wheeled robot navigation has been widely used in urban environments, but navigation in wild vegetation is still challenging. External sensors (LiDAR, camera etc.) are often used to construct point cloud map of the surrounding environment, however, the supporting rigid ground used for travelling cann

Cited by 29SourceScholar
2024

Phase Synthesis for Spatial Locomotion Control of Retractable Worm Robots

ICRA 2024poster

Retractable worm robots possess hyper-flexibility, allowing them to work in confined spaces that are difficult for humans. However, the spatial locomotion control of these robots remains challenging due to the robots’ large degrees of freedom. To address this challenge, we propose a phase synthesis…

Cited by 0SourceScholar
2024

Stiffness-Based Hybrid Motion/ Force Control for Cable-Driven Serpentine Manipulator*

ICRA 2024poster

In recent years, there has been a growing demand for robotic manipulators to perform tasks in various unstructured environments and situations requiring precision and force control. However, traditional robotic arms have limitations in fully leveraging their advantages in such scenarios. To address…

Cited by 0SourceScholar
2023

A Training-Free Debiasing Framework with Counterfactual Reasoning for Conversational Emotion Detection

EMNLP 2023long main

Unintended dataset biases typically exist in existing Emotion Recognition in Conversations (ERC) datasets, including label bias, where models favor the majority class due to imbalanced training data, as well as the speaker and neutral word bias, where models make unfair predictions because of excess…

Cited by 0SourceScholar
2023

An Empirical Study of Sentiment-Enhanced Pre-Training for Aspect-Based Sentiment Analysis

ACL 2023findings

Aspect-Based Sentiment Analysis (ABSA) aims to recognize fine-grained opinions and sentiments of users, which is an important problem in sentiment analysis. Recent work has shown that Sentiment-enhanced Pre-Training (SPT) can substantially improve the performance of various ABSA tasks. However, ther…

2023

An Empirical Study on Multiple Knowledge from ChatGPT for Emotion Recognition in Conversations

EMNLP 2023long findings

Multiple knowledge (e.g., co-reference, topics, emotional causes, etc) has been demonstrated effective for emotion detection. However, exploring this knowledge in Emotion Recognition in Conversations (ERC) is currently a blank slate due to the lack of annotated data and the high cost involved in obt…

Cited by 0SourceScholar
2023

Bipartite Graph Convolutional Networks with Adversarial Domain Transfer

ICASSP 2023accepted

Bipartite graphs have been widely used in many applications such as recommender systems, search engines and so on. Recent works consider bipartite graphs as homogeneous graphs and apply graph convolution networks for link prediction or node classification. However, in bipartite graphs, there are two…

Cited by 0SourceScholar
2023

CUE: An Uncertainty Interpretation Framework for Text Classifiers Built on Pre-Trained Language Models

UAI 2023poster

Text classifiers built on Pre-trained Language Models (PLMs) have achieved remarkable progress in various tasks including sentiment analysis, natural language inference, and question-answering. However, the occurrence of uncertain predictions by these classifiers poses a challenge to their reliabili…

2023

Context or Knowledge is Not Always Necessary: A Contrastive Learning Framework for Emotion Recognition in Conversations

ACL 2023findings

Emotion recognition in conversations (ERC) aims to detect the emotion of utterances in conversations. Existing efforts generally focus on modeling context- and knowledge-sensitive dependencies. However, it is observed that the emotions of many utterances can be correctly detected without context or…

Cited by 21SourcePDFScholar
2023

Cue-CoT: Chain-of-thought Prompting for Responding to In-depth Dialogue Questions with LLMs

EMNLP 2023long findings

Large Language Models (LLMs), such as ChatGPT, greatly empower dialogue systems with strong language understanding and generation capabilities. However, most of the previous works prompt the LLMs to directly generate a response based on the dialogue context, overlooking the underlying linguistic cue…

Cited by 0SourceScholar
2023

Dual-graph co-representation learning for knowledge-Graph Enhanced Recommendation

ICASSP 2023accepted

Knowledge graphs can help improve the performance of recommender systems by mitigating sparsity and cold-start problems. However, existing approaches usually suffer from problems of domain distribution matching and cycle consistency for co-representation learning, as the representations of items fro…

Cited by 0SourceScholar
2023

Dynamic Control Barrier Function-based Model Predictive Control to Safety-Critical Obstacle-Avoidance of Mobile Robot

ICRA 2023poster

This paper presents an efficient and safe method to avoid static and dynamic obstacles based on LiDAR. First, point cloud is used to generate a real-time local grid map for obstacle detection. Then, obstacles are clustered by DBSCAN algorithm and enclosed with minimum bounding ellipses (MBEs). In ad…

Cited by 94SourcecodeScholar
2023

Evaluation Metrics in the Era of GPT-4: Reliably Evaluating Large Language Models on Sequence to Sequence Tasks

EMNLP 2023short main

Large Language Models (LLMs) evaluation is a patchy and inconsistent landscape, and it is becoming clear that the quality of automatic evaluation metrics is not keeping up with the pace of development of generative models. We aim to improve the understanding of current models' performance by providi…

Cited by 0SourcecodeScholar
2023

Foldsformer: Learning Sequential Multi-Step Cloth Manipulation With Space-Time Attention

RA-L 2023

Sequential multi-step cloth manipulation is a challenging problem in robotic manipulation, requiring a robot to perceive the cloth state and plan a sequence of chained actions leading to the desired state. Most previous works address this problem in a goal-conditioned way, and goal observation must

Cited by 33SourcecodeScholar
2023

In-context Learning for Few-shot Multimodal Named Entity Recognition

EMNLP 2023long findings

Thanks in part to the availability of copious annotated resources for some entity categories, existing studies have achieved superior performance in multimodal named entity recognition (MNER). However, in the real-world scenario, it is infeasible to enumerate all entity categories in advance. Theref…

Cited by 0SourceScholar
2023

Learning Graph Dynamics With External Contact for Deformable Linear Objects Shape Control

RA-L 2023

This letter focuses on the shape control manipulation of deformable linear objects (DLO) with a dual-arm robotic system. One significant challenge of DLO shape control is the underactuated control system, which means that finite robotic manipulators can not fully control DLO's shape due to the lack

Cited by 19SourceScholar
2023

MMSD2.0: Towards a Reliable Multi-modal Sarcasm Detection System

ACL 2023findings

Multi-modal sarcasm detection has attracted much recent attention. Nevertheless, the existing benchmark (MMSD) has some shortcomings that hinder the development of reliable multi-modal sarcasm detection system: (1) There are some spurious cues in MMSD, leading to the model bias learning; (2) The neg…

2023

Probing Graph Decomposition for Argument Pair Extraction

ACL 2023findings

Argument pair extraction (APE) aims to extract interactive argument pairs from two passages within a discussion. The key challenge of APE is to effectively capture the complex context-aware interactive relations of arguments between the two passages. In this paper, we elicit relational semantic know…

2023

Quadruped Guidance Robot for the Visually Impaired: A Comfort-Based Approach

ICRA 2023poster

Guidance robots that can guide people and avoid various obstacles, could potentially be owned by more visually impaired people at a fairly low cost. Most of the previous guidance robots for the visually impaired ignored the human response behavior and comfort, treating the human as an appendage drag…

Cited by 45SourceScholar
2023

Reducing Spurious Correlations in Aspect-based Sentiment Analysis with Explanation from Large Language Models

EMNLP 2023long findings

Recently, aspect-based sentiment analysis (ABSA) models have yielded promising results. However, they are susceptible to learning spurious correlations between certain words of the input text and output labels while modeling the sentiment feature of the aspect. This spurious correlation will potenti…

Cited by 0SourceScholar
2023

Stance Detection on Social Media with Background Knowledge

EMNLP 2023long main

Identifying users' stances regarding specific targets/topics is a significant route to learning public opinion from social media platforms. Most existing studies of stance detection strive to learn stance information about specific targets from the context, in order to determine the user's stance on…

Cited by 0SourceScholar
2023

TGF-Net: Sim2Real Transparent Object 6D Pose Estimation Based on Geometric Fusion

RA-L 2023

Transparent objects are a common part of daily life, but their unique optical properties make estimating their 6D pose a challenging task. In this letter, we propose TGF-Net, a monocular instance-level 6D pose estimation method for transparent objects based on geometric fusion. TGF-Net learns the ed

Cited by 20SourceScholar
2023

Target-to-Source Augmentation for Aspect Sentiment Triplet Extraction

EMNLP 2023long main

Aspect Sentiment Triplet Extraction (ASTE) is an important task in sentiment analysis, aiming to extract aspect-level opinions and sentiments from user-generated reviews. The fine-grained nature of ASTE incurs a high annotation cost, while the scarcity of annotated data limits the performance of ex…

Cited by 0SourceScholar
2022

A Generative Model for End-to-End Argument Mining with Reconstructed Positional Encoding and Constrained Pointer Mechanism

EMNLP 2022main

Argument mining (AM) is a challenging task as it requires recognizing the complex argumentation structures involving multiple subtasks.To handle all subtasks of AM in an end-to-end fashion, previous works generally transform AM into a dependency parsing task.However, such methods largely require com…

Cited by 7SourcePDFScholar
2022

APD: Learning Diverse Behaviors for Reinforcement Learning Through Unsupervised Active Pre-Training

RA-L 2022

Unsupervised pre-training in reinforcement learning enables the agent to gain prior environmental knowledge, which is then fine-tuned in the supervised stage to quickly adapt to various downstream tasks. In the absence of task-related rewards, pre-training aims to acquire policies (i.e., behaviors)

Cited by 5SourceScholar
2022

Boundary-Driven Table-Filling for Aspect Sentiment Triplet Extraction

EMNLP 2022main

Aspect Sentiment Triplet Extraction (ASTE) aims to extract the aspect terms along with the corresponding opinion terms and the expressed sentiments in the review, which is an important task in sentiment analysis. Previous research efforts generally address the ASTE task in an end-to-end fashion thro…

2022

CLLE: A Benchmark for Continual Language Learning Evaluation in Multilingual Machine Translation

EMNLP 2022finding

Continual Language Learning (CLL) in multilingual translation is inevitable when new languages are required to be translated. Due to the lack of unified and generalized benchmarks, the evaluation of existing methods is greatly influenced by experimental design which usually has a big gap from the in…

2022

Domain Generalization by Learning and Removing Domain-specific Features

NeurIPS 2022accept

Deep Neural Networks (DNNs) suffer from domain shift when the test dataset follows a distribution different from the training dataset. Domain generalization aims to tackle this issue by learning a model that can generalize to unseen domains. In this paper, we propose a new approach that aims to expl…

2022

JointCL: A Joint Contrastive Learning Framework for Zero-Shot Stance Detection

ACL 2022long

Zero-shot stance detection (ZSSD) aims to detect the stance for an unseen target during the inference stage. In this paper, we propose a joint contrastive learning (JointCL) framework, which consists of stance contrastive learning and target-aware prototypical graph contrastive learning. Specificall…

2022

Modeling Intra- and Inter-Modal Relations: Hierarchical Graph Contrastive Learning for Multimodal Sentiment Analysis

COLING 2022main

The existing research efforts in Multimodal Sentiment Analysis (MSA) have focused on developing the expressive ability of neural networks to fuse information from different modalities. However, these approaches lack a mechanism to understand the complex relations within and across different modaliti…

Cited by 58SourcePDFScholar
2022

Multi-Modal Sarcasm Detection via Cross-Modal Graph Convolutional Network

ACL 2022long

With the increasing popularity of posting multimodal messages online, many recent studies have been carried out utilizing both textual and visual information for multi-modal sarcasm detection. In this paper, we investigate multi-modal sarcasm detection from a novel perspective by constructing a cros…

2022

Offline Reinforcement Learning with Value-based Episodic Memory

ICLR 2022poster

Offline reinforcement learning (RL) shows promise of applying RL to real-world problems by effectively utilizing previously collected data. Most existing offline RL algorithms use regularization or constraints to suppress extrapolation error for actions outside the dataset. In this paper, we adopt a…

Cited by 50SourcePDFScholar
2022

Orientation to Pose: Continuum Robots Shape Reconstruction Based on the Multi-Attitude Solving Approach

ICRA 2022poster

Continuum robots are typically slender and flexible with infinite freedoms in theory, which poses a challenge for their control and application. The shape reconstruction of continuum robots is vital to realize closed-loop control. This paper proposes a novel general real-time shape reconstruction fr…

Cited by 7SourceScholar
2022

PUTN: A Plane-fitting based Uneven Terrain Navigation Framework

IROS 2022poster

Autonomous navigation of ground robots has been widely used in indoor structured 2D environments, but there are still many challenges in outdoor 3D unstructured environments, especially in rough, uneven terrains. This paper proposed a plane-fitting based uneven terrain navigation framework (PUTN) to…

Cited by 59SourcecodeScholar
2022

Probing Structural Knowledge from Pre-trained Language Model for Argumentation Relation Classification

EMNLP 2022finding

Extracting fine-grained structural information between argumentation component (AC) pairs is essential for argumentation relation classification (ARC). However, most previous studies attempt to model the relationship between AC pairs using AC level similarity or semantically relevant features. They…

2022

SEMGraph: Incorporating Sentiment Knowledge and Eye Movement into Graph Model for Sentiment Analysis

EMNLP 2022main

This paper investigates the sentiment analysis task from a novel perspective by incorporating sentiment knowledge and eye movement into a graph architecture, aiming to draw the eye movement-based sentiment relationships for learning the sentiment expression of the context. To be specific, we first e…

2022

TaTa: A Universal Jamming Gripper with High-Quality Tactile Perception and Its Application to Underwater Manipulation

ICRA 2022poster

Large-area and high-precision tactile sensing information can not only improve the stability of robot grasping but also compensate for the lack of visual information in specific environments such as turbid underwater, dimness, and smoke. In this paper, we devise a universal jamming gripper with high…

Cited by 33SourceScholar
2021

An Overall Configuration Planning Method of Continuum Hyper-Redundant Manipulators Based on Improved Artificial Potential Field Method

RA-L 2021

Continuum hyper-redundant manipulators (CHRMs) have been widely applied in aerospace, medical or other fields to complete tasks in narrow and multi-obstacles environments with its unique structural advantages. Due to the redundancy, the inverse kinematics of CHRMs is rather complex and the trajector

Cited by 46SourceScholar
2021

Argument Pair Extraction with Mutual Guidance and Inter-sentence Relation Graph

EMNLP 2021main

Argument pair extraction (APE) aims to extract interactive argument pairs from two passages of a discussion. Previous work studied this task in the context of peer review and rebuttal, and decomposed it into a sequence labeling task and a sentence relation classification task. However, despite the p…

Cited by 22SourcePDFScholar
2021

Beta Distribution Guided Aspect-aware Graph for Aspect Category Sentiment Analysis with Affective Knowledge

EMNLP 2021main

In this paper, we investigate the Aspect Category Sentiment Analysis (ACSA) task from a novel perspective by exploring a Beta Distribution guided aspect-aware graph construction based on external knowledge. That is, we are no longer entangled about how to laboriously search the sentiment clues for c…

2021

Learning to Discover Task-Relevant Features for Interpretable Reinforcement Learning

RA-L 2021

Reinforcement Learning (RL) agents are often fed with large-dimensional observations to achieve the ideal performance in complex environments. Unfortunately, the massive observation space usually contains useless or even adverse features, which leads to low sample efficiency. Existing methods rely o

Cited by 5SourcecodeScholar
2021

Soft-CCD Algorithm for Inverse Kinematics of Soft Continuum Manipulators

IROS 2021poster

To date, soft robots have been increasingly designed and analyzed, especially, Soft Continuum Manipulators (SCMs). Due to dexterous deformability, their Inverse Kinematics (IK) is still difficult to solve. Cyclic Coordinate Descent (CCD) algorithm is one of the classical optimization algorithms to s…

Cited by 6SourceScholar
2020

Jointly Learning Aspect-Focused and Inter-Aspect Relations with Graph Convolutional Networks for Aspect Sentiment Analysis

COLING 2020main

In this paper, we explore a novel solution of constructing a heterogeneous graph for each instance by leveraging aspect-focused and inter-aspect contextual dependencies for the specific aspect and propose an Interactive Graph Convolutional Networks (InterGCN) model for aspect sentiment analysis. Spe…

2020

Modeling and Experimental Verification of a Cable-Constrained Synchronous Rotating Mechanism Considering Friction Effect

RA-L 2020

Cable-Constrained Synchronous Rotating Mechanism (CCSRM) has an important application prospect in the field of cable-driven robots, which can greatly reduce the number of driving motors while ensuring the light and slender body. However, there are obvious cable friction effect and elastic deformatio

Cited by 16SourceScholar
2020

Multi-task Control for a Quadruped Robot with Changeable Leg Configuration

IROS 2020poster

This paper proposes a multi-task control strategy for a quadruped robot named THU-QUAD II. The mechanical design of the robot ensures a wide range of motion for all joints, which allows it to stand and walk like a mammal as well as sprawl to the ground and crawl like a reptile. Five basic leg config…

Cited by 8SourceScholar
2019

A 3D Static Modeling Method and Experimental Verification of Continuum Robots Based on Pseudo-Rigid Body Theory

IROS 2019poster

Continuum robots composed of elastic backbones have a broad application prospect in the narrow and restricted environment because they overcome the disadvantages of traditional articulated robots, such as being bulky and inflexible. Statics plays an important role in the planning and control of the…

Cited by 35SourceScholar