← Search

Wenhao Yu

96 accepted papers

2026

Group Distributionally Robust Optimization-Driven RL for LLM Reasoning

ICML 2026poster

Reasoning post-training with GRPO is typically built on *static uniformity*: uniform prompt sampling and a fixed number of rollouts per prompt. For heterogeneous, heavy-tailed reasoning data, this wastes compute on already-solved patterns while under-training the long tail of hard problems. We cast …

Cited by 0SourceScholar
2026

Parallel-R1: Towards Parallel Thinking via Reinforcement Learning

ICLR 2026poster

Parallel thinking has emerged as a novel approach for enhancing the reasoning capabilities of large language models (LLMs) by exploring multiple reasoning paths concurrently. However, activating such capabilities through training remains challenging. Existing methods mainly rely on supervised fine-t…

Cited by 0SourcecodeScholar
2026

PerFit: Exploring Personalization Shifts in Representation Space of LLMs

ICLR 2026poster

Personalization has become a pivotal field of study in contemporary intelligent systems. While large language models (LLMs) excel at general knowledge tasks, they often struggle with personalization, i.e., adapting their outputs to individual user expectations. Existing approaches that steer LLM beh…

Cited by 0SourceScholar
2026

Probability-Entropy Calibration: An Elastic Indicator for Adaptive Fine-tuning

ICML 2026poster

Token-level reweighting is a simple yet effective mechanism for controlling supervised fine-tuning, but common indicators are largely one-dimensional: the ground-truth probability reflects downstream alignment, while token entropy reflects intrinsic uncertainty induced by the pre-training prior. Ign…

Cited by 0SourceScholar
2026

R-Zero: Self-Evolving Reasoning LLM from Zero Data

ICLR 2026poster

Self-evolving Large Language Models (LLMs) offer a scalable path toward super-intelligence by autonomously generating, refining, and learning from their own experiences. However, existing methods for training such models still rely heavily on vast human-curated tasks and labels, typically via fine-t…

Cited by 0SourcecodeScholar
2026

Self-Rewarding Vision-Language Model via Reasoning Decomposition and Multi-Reward Policy Optimization

ICLR 2026poster

Vision-Language Models (VLMs) often suffer from visual hallucinations – generating things that are not consistent with visual inputs – and language shortcuts, where they skip the visual part and just rely on text priors. These issues arise because most post-training methods for VLMs rely on simple v…

Cited by 0SourceScholar
2026

SoPE: Spherical Coordinate-Based Positional Embedding for Enhancing Spatial Perception of 3D LVLMs

CVPR 2026

3D Large Vision-Language Models (3D LVLMs) built upon Large Language Models (LLMs) have achieved remarkable progress across various multimodal tasks. However, their inherited position-dependent modeling mechanism, Rotary Position Embedding (RoPE), remains suboptimal for 3D multimodal understanding.

Cited by 0SourceScholar
2025

Agile Continuous Jumping in Discontinuous Terrains

ICRA 2025

We focus on agile, continuous, and terrain-adaptive jumping of quadrupedal robots in discontinuous terrains such as stairs and stepping stones. Unlike single-step jumping, continuous jumping requires accurately executing highly dynamic motions over long horizons, which is challenging for existing ap

Cited by 17SourcecodeScholar
2025

BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions

ICLR 2025oral

Task automation has been greatly empowered by the recent advances in Large Language Models (LLMs) via Python code, where the tasks range from software engineering development to general-purpose reasoning. While current benchmarks have shown that LLMs can solve tasks using programs like human develop…

Cited by 609SourcePDFScholar
2025

Chain-of-Modality: Learning Manipulation Programs from Multimodal Human Videos with Vision-Language-Models

ICRA 2025

Learning to perform manipulation tasks from human videos is a promising approach for teaching robots. However, many manipulation tasks require changing control parameters during task execution, such as force, which visual data alone cannot capture. In this work, we leverage sensing devices such as a

Cited by 7SourcecodeScholar
2025

Cognitive Kernel: An Open-source Agent System towards Generalist Autopilots

NAACL 2025system demonstrations

We introduce Cognitive Kernel, an open-source agent system towards the goal of generalist autopilots. Unlike copilot systems, which primarily rely on users to provide essential state information, autopilot systems complete tasks from start to finish independently. This requires the system to acquire…

2025

DSBench: How Far Are Data Science Agents from Becoming Data Science Experts?

ICLR 2025poster

Large Language Models (LLMs) and Large Vision-Language Models (LVLMs) have demonstrated impressive language/vision reasoning abilities, igniting the recent trend of building agents for targeted applications such as shopping assistants or AI software engineers. Recently, many data science benchmarks…

Cited by 2SourcePDFScholar
2025

GDiffRetro: Retrosynthesis Prediction with Dual Graph Enhanced Molecular Representation and Diffusion Generation

AAAI 2025technical

Retrosynthesis prediction focuses on identifying reactants capable of synthesizing a target product. Typically, the retrosynthesis prediction involves two phases: Reaction Center Identification and Reactant Generation. However, we argue that most existing methods suffer from two limitations in the t…

2025

Human2LocoMan: Learning Versatile Quadrupedal Manipulation with Human Pretraining

RSS 2025poster

Quadrupedal robots have demonstrated impressive locomotion capabilities in complex environments, but equipping them with autonomous versatile manipulation skills in a scalable way remains a significant challenge. In this work, we introduce a system that integrates data collection and imitation learn…

Cited by 0PDFcodeScholar
2025

LocoTouch: Learning Dynamic Quadrupedal Transport with Tactile Sensing

CoRL 2025poster

Quadrupedal robots have demonstrated remarkable agility and robustness in traversing complex terrains. However, they struggle with dynamic object interactions, where contact must be precisely sensed and controlled. To bridge this gap, we present LocoTouch, a system that equips quadrupedal robots wit…

Cited by 0SourceScholar
2025

LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory

ICLR 2025poster

Recent large language model (LLM)-driven chat assistant systems have integrated memory components to track user-assistant chat histories, enabling more accurate and personalized responses. However, their long-term memory capabilities in sustained interactions remain underexplored. We introduce LongM…

2025

MMLongBench: Benchmarking Long-Context Vision-Language Models Effectively and Thoroughly

NeurIPS 2025spotlight

The rapid extension of context windows in large vision-language models has given rise to long-context vision-language models (LCVLMs), which are capable of handling hundreds of images with interleaved text tokens in a single forward pass. In this work, we introduce MMLongBench, the first benchmark c…

Cited by 0SourcecodeScholar
2025

OpenWebVoyager: Building Multimodal Web Agents via Iterative Real-World Exploration, Feedback and Optimization

ACL 2025long

The advancement of foundation models has laid the groundwork for building autonomous agents for complex tasks such as web navigation. Recent efforts have also tried to equip the agent with the ability to explore environments and continuously improve over time. However, existing works only focused on…

2025

PoseLLaVA: Pose Centric Multimodal LLM for Fine-Grained 3D Pose Manipulation

AAAI 2025technical

Manipulating human poses based on natural language is an emerging research field that has traditionally focused on coarse commands such as “walking” or “dancing.” However, fine-grained pose manipulation, like instructing “put both hands in front of the stomach,” remains underexplored. In this paper,…

2025

QuietPaw: Learning Quadrupedal Locomotion with Versatile Noise Preference Alignment

IROS 2025

When operating at their full capacity, quadrupedal robots can produce loud footstep noise, which can be disruptive in human-centered environments like homes, offices, and hospitals. As a result, balancing locomotion performance with noise constraints is crucial for the successful real-world deployme

Cited by 1SourceScholar
2025

RepoGraph: Enhancing AI Software Engineering with Repository-level Code Graph

ICLR 2025poster

Large Language Models (LLMs) excel in code generation yet struggle with modern AI software engineering tasks. Unlike traditional function-level or file-level coding tasks, AI software engineering requires not only basic coding proficiency but also advanced skills in managing and interacting with co…

2025

Retrieval-augmented GUI Agents with Generative Guidelines

EMNLP 2025

GUI agents powered by vision-language models (VLMs) show promise in automating complex digital tasks. However, their effectiveness in real-world applications is often limited by scarce training data and the inherent complexity of these tasks, which frequently require long-tailed knowledge covering r

Cited by 0SourcePDFScholar
2025

STDArm: Transfer Visuomotor Policy From Static Data Training to Dynamic Robot Manipulation

RSS 2025poster

Learning visuomotor policy from human demonstrations serves as an effective method for robots to acquire complex tasks. However, data collection on mobile platforms such as drones is extremely challenging, resulting in most research being conducted with robots in stationary conditions for data colle…

Cited by 0PDFScholar
2025

Vision Language Models are In-Context Value Learners

ICLR 2025spotlight

Predicting temporal progress from visual trajectories is important for intelligent robots that can learn, adapt, and improve. However, learning such progress estimator, or temporal value function, across different tasks and domains requires both a large amount of diverse data and methods which can s…

Cited by 2SourcePDFScholar
2025

WebEvolver: Enhancing Web Agent Self-Improvement with Co-evolving World Model

EMNLP 2025

Agent self-improvement, where agents autonomously train their underlying Large Language Model (LLM) on self-sampled trajectories, shows promising results but often stagnates in web environments due to limited exploration and under-utilization of pretrained web knowledge. To improve the performance o

2024

Chain-of-Note: Enhancing Robustness in Retrieval-Augmented Language Models

EMNLP 2024main

Retrieval-augmented language model (RALM) represents a significant advancement in mitigating factual hallucination by leveraging external knowledge sources. However, the reliability of the retrieved information is not always guaranteed, and the retrieval of irrelevant data can mislead the response g…

Cited by 106SourcePDFScholar
2024

CoNVOI: Context-aware Navigation using Vision Language Models in Outdoor and Indoor Environments

IROS 2024

We present CoNVOI, a novel method for autonomous robot navigation in real-world indoor and outdoor environments using Vision Language Models (VLMs). We employ VLMs in two ways: first, we leverage their zero-shot image classification capability to identify the context or scenario (e.g., indoor corrid

Cited by 52SourceScholar
2024

Dense X Retrieval: What Retrieval Granularity Should We Use?

EMNLP 2024main

Dense retrieval has become a prominent method to obtain relevant context or world knowledge in open-domain NLP tasks. When we use a learned dense retriever on a retrieval corpus at inference time, an often-overlooked design choice is the retrieval unit in which the corpus is indexed, e.g. document,…

Cited by 63SourcePDFScholar
2024

Gameplay Filters: Robust Zero-Shot Safety through Adversarial Imagination

CoRL 2024poster

Despite the impressive recent advances in learning-based robot control, ensuring robustness to out-of-distribution conditions remains an open challenge. Safety filters can, in principle, keep arbitrary control policies from incurring catastrophic failures by overriding unsafe actions, but existing s…

Cited by 7SourceScholar
2024

IndoorSim-to-OutdoorReal: Learning to Navigate Outdoors Without Any Outdoor Experience

RA-L 2024

We present IndoorSim-to-OutdoorReal (I2O), an end-to-end learned visual navigation approach, trained solely in simulated short-range indoor environments, and demonstrate zero-shot sim-to-real transfer to the outdoors for long-range navigation on the Spot robot. Our method uses zero real-world experi

Cited by 19SourceScholar
2024

LDP: A Local Diffusion Planner for Efficient Robot Navigation and Collision Avoidance

IROS 2024poster

The conditional diffusion model has been demonstrated as an efficient tool for learning robot policies, owing to its advancement to accurately model the conditional distribution of policies. The intricate nature of real-world scenarios, characterized by dynamic obstacles and maze-like structures, un…

Cited by 13SourceScholar
2024

Learn Beyond The Answer: Training Language Models with Reflection for Mathematical Reasoning

EMNLP 2024main

Supervised fine-tuning enhances the problem-solving abilities of language models across various mathematical reasoning tasks. To maximize such benefits, existing research focuses on *broadening* the training set with various data augmentation techniques, which is effective for standard single-round…

2024

Learning to Learn Faster from Human Feedback with Language Model Predictive Control

RSS 2024poster

Large language models (LLMs) have been shown to exhibit a wide range of capabilities, such as writing robot code from language commands -- enabling non-experts to direct robot behaviors, modify them based on feedback, or compose them to perform new tasks. However, these capabilities (driven by in-co…

2024

LocoMan: Advancing Versatile Quadrupedal Dexterity with Lightweight Loco-Manipulators

IROS 2024poster

Quadrupedal robots have emerged as versatile agents capable of locomoting and manipulating in complex environments. Traditional designs typically rely on the robot’s inherent body parts or incorporate top-mounted arms for manipulation tasks. However, these configurations may limit the robot’s operat…

Cited by 13SourceScholar
2024

Mobility VLA: Multimodal Instruction Navigation with Long-Context VLMs and Topological Graphs

CoRL 2024poster

An elusive goal in navigation research is to build an intelligent agent that can understand multimodal instructions including natural language and image, and perform useful navigation. To achieve this, we study a widely useful category of navigation tasks we call Multimodal Instruction Navigation wi…

Cited by 20SourceScholar
2024

OASIS: Conditional Distribution Shaping for Offline Safe Reinforcement Learning

NeurIPS 2024poster

Offline safe reinforcement learning (RL) aims to train a policy that satisfies con- straints using a pre-collected dataset. Most current methods struggle with the mismatch between imperfect demonstrations and the desired safe and rewarding performance. In this paper, we mitigate this issue from a da…

2024

PIVOT: Iterative Visual Prompting Elicits Actionable Knowledge for VLMs

ICML 2024poster

Vision language models (VLMs) have shown impressive capabilities across a variety of tasks, from logical reasoning to visual understanding. This opens the door to richer interaction with the world, for example robotic control. However, VLMs produce only textual outputs, while robotic control and oth…

Cited by 95SourcePDFScholar
2024

PLUG: Leveraging Pivot Language in Cross-Lingual Instruction Tuning

ACL 2024long

Instruction tuning has remarkably advanced large language models (LLMs) in understanding and responding to diverse human instructions. Despite the success in high-resource languages, its application in lower-resource ones faces challenges due to the imbalanced foundational abilities of LLMs across d…

2024

PathRL: An End-to-End Path Generation Method for Collision Avoidance via Deep Reinforcement Learning

ICRA 2024poster

Robot navigation using deep reinforcement learning (DRL) has shown great potential in improving the performance of mobile robots. Nevertheless, most existing DRL-based navigation methods primarily focus on training a policy that directly commands the robot with low-level controls, like linear and an…

Cited by 8SourceScholar
2024

RT-Trajectory: Robotic Task Generalization via Hindsight Trajectory Sketches

ICLR 2024spotlight

Generalization remains one of the most important desiderata for robust robot learning systems. While recently proposed approaches show promise in generalization to novel objects, semantic concepts, or visual distribution shifts, generalization to new tasks remains challenging. For example, a languag…

Cited by 53SourcePDFScholar
2024

Sub-Sentence Encoder: Contrastive Learning of Propositional Semantic Representations

NAACL 2024long

We introduce sub-sentence encoder, a contrastively-learned contextual embedding model for fine-grained semantic representation of text. In contrast to the standard practice with sentence embeddings, where the meaning of an entire sequence of text is encoded into a fixed-length vector, the sub-senten…

2024

The Design of the Barkour Benchmark for Robot Agility

IROS 2024poster

In this paper, we describe the design of the Barkour benchmark for measuring robot agility in navigating complex environments. Despite the growing interest in developing agile robot locomotion skills, the field lacks systematic benchmarks to measure the performance of robotic control systems and har…

Cited by 1SourceScholar
2024

WebVoyager: Building an End-to-End Web Agent with Large Multimodal Models

ACL 2024long

The rapid advancement of large language models (LLMs) has led to a new era marked by the development of autonomous applications in real-world scenarios, which drives innovation in creating advanced web agents. Existing web agents typically only handle one input modality and are evaluated only in sim…

2023

A Survey of Deep Learning for Mathematical Reasoning

ACL 2023long

Mathematical reasoning is a fundamental aspect of human intelligence and is applicable in various fields, including science, engineering, finance, and everyday life. The development of artificial intelligence (AI) systems capable of solving math problems and proving theorems in language has garnered…

2023

A Unified Perspective on Multiple Shooting In Differential Dynamic Programming

IROS 2023poster

Differential Dynamic Programming (DDP) is an efficient computational tool for solving nonlinear optimal control problems. It was originally designed as a single shooting method and thus is sensitive to the initial guess supplied. This work considers the extension of DDP to multiple shooting (MS), im…

Cited by 16SourceScholar
2023

APOLLO: A Simple Approach for Adaptive Pretraining of Language Models for Logical Reasoning

ACL 2023long

Logical reasoning over text is an important ability that requires understanding the semantics of the text and reasoning through them to arrive at correct inferences. Prior works on pretraining language models to improve the logical reasoning ability require complex processing of training data (e.g.,…

2023

Auto-Instruct: Automatic Instruction Generation and Ranking for Black-Box Language Models

EMNLP 2023long findings

Large language models (LLMs) can perform a wide range of tasks by following natural language instructions, without the necessity of task-specific fine-tuning. Unfortunately, the performance of LLMs is greatly influenced by the quality of these instructions, and manually writing effective instruction…

Cited by 0SourceScholar
2023

CAJun: Continuous Adaptive Jumping using a Learned Centroidal Controller

CoRL 2023poster

We present CAJun, a novel hierarchical learning and control framework that enables legged robots to jump continuously with adaptive jumping distances. CAJun consists of a high-level centroidal policy and a low-level leg controller. In particular, we use reinforcement learning (RL) to train the centr…

Cited by 30SourceScholar
2023

Constrained Decision Transformer for Offline Safe Reinforcement Learning

ICML 2023poster

Safe reinforcement learning (RL) trains a constraint satisfaction policy by interacting with the environment. We aim to tackle a more challenging problem: learning a safe policy from an offline dataset. We study the offline safe RL problem from a novel multi-objective optimization perspective and pr…

2023

Constraint-Conditioned Policy Optimization for Versatile Safe Reinforcement Learning

NeurIPS 2023poster

Safe reinforcement learning (RL) focuses on training reward-maximizing agents subject to pre-defined safety constraints. Yet, learning versatile safe policies that can adapt to varying safety constraint requirements during deployment without retraining remains a largely unexplored and challenging ar…

Cited by 20SourcePDFScholar
2023

Generate rather than Retrieve: Large Language Models are Strong Context Generators

ICLR 2023poster

Knowledge-intensive tasks, such as open-domain question answering (QA), require access to a large amount of world or domain knowledge. A common approach for knowledge-intensive tasks is to employ a retrieve-then-read pipeline that first retrieves a handful of relevant contextual documents from an ex…

2023

GraphPatcher: Mitigating Degree Bias for Graph Neural Networks via Test-time Augmentation

NeurIPS 2023poster

Recent studies have shown that graph neural networks (GNNs) exhibit strong biases towards the node degree: they usually perform satisfactorily on high-degree nodes with rich neighbor information but struggle with low-degree nodes. Existing works tackle this problem by deriving either designated GNN…

2023

IfQA: A Dataset for Open-domain Question Answering under Counterfactual Presuppositions

EMNLP 2023long main

Although counterfactual reasoning is a fundamental aspect of intelligence, the lack of large-scale counterfactual open-domain question-answering (QA) benchmarks makes it difficult to evaluate and improve models on this ability. To address this void, we introduce the first such dataset, named IfQA, w…

Cited by 0SourceScholar
2023

Language to Rewards for Robotic Skill Synthesis

CoRL 2023oral

Large language models (LLMs) have demonstrated exciting progress in acquiring diverse new capabilities through in-context learning, ranging from logical reasoning to code-writing. Robotics researchers have also explored using LLMs to advance the capabilities of robotic control. However, since low-le…

Cited by 326SourceScholar
2023

Large Language Models are Built-in Autoregressive Search Engines

ACL 2023findings

Document retrieval is a key stage of standard Web search engines. Existing dual-encoder dense retrievers obtain representations for questions and documents independently, allowing for only shallow interactions between them. To overcome this limitation, recent autoregressive search engines replace th…

2023

Let GPT be a Math Tutor: Teaching Math Word Problem Solvers with Customized Exercise Generation

EMNLP 2023long main

In this paper, we present a novel approach for distilling math word problem solving capabilities from large language models (LLMs) into smaller, more efficient student models. Our approach is designed to consider the student model's weaknesses and foster a tailored learning experience by generating…

Cited by 0SourceScholar
2023

Multi-task Self-supervised Graph Neural Networks Enable Stronger Task Generalization

ICLR 2023poster

Self-supervised learning (SSL) for graph neural networks (GNNs) has attracted increasing attention from the graph machine learning community in recent years, owing to its capability to learn performant node embeddings without costly label information. One weakness of conventional SSL frameworks for…

2023

Perceptive Hexapod Legged Locomotion for Climbing Joist Environments

IROS 2023poster

Attics are one of the largest sources of energy loss in residential homes, but they are uncomfortable and dangerous for human workers to conduct air sealing and insulation. Hexapod robots are potentially suitable for carrying out those tasks in tight attic spaces since they are stable, compact, and…

Cited by 5SourceScholar
2023

SayTap: Language to Quadrupedal Locomotion

CoRL 2023poster

Large language models (LLMs) have demonstrated the potential to perform high-level planning. Yet, it remains a challenge for LLMs to comprehend low-level commands, such as joint angle targets or motor torques. This paper proposes an approach to use foot contact patterns as an interface that bridges…

Cited by 45SourcecodeScholar
2023

Transforming a Quadruped into a Guide Robot for the Visually Impaired: Formalizing Wayfinding, Interaction Modeling, and Safety Mechanism

CoRL 2023poster

This paper explores the principles for transforming a quadrupedal robot into a guide robot for individuals with visual impairments. A guide robot has great potential to resolve the limited availability of guide animals that are accessible to only two to three percent of the potential blind or visual…

Cited by 13SourceScholar
2023

Versatile Real-Time Motion Synthesis via Kino-Dynamic MPC With Hybrid-Systems DDP

ICRA 2023poster

Specialized motions such as jumping are often achieved on quadruped robots by solving a trajectory optimization problem once and executing the trajectory using a tracking controller. This approach is in parallel with Model Predictive Control (MPC) strategies that commonly control regular gaits via o…

Cited by 18SourcecodeScholar
2022

A Unified Encoder-Decoder Framework with Entity Memory

EMNLP 2022main

Entities, as important carriers of real-world knowledge, play a key role in many NLP tasks.We focus on incorporating entity knowledge into an encoder-decoder framework for informative text generation. Existing approaches tried to index, retrieve, and read external documents as evidence, but they suf…

2022

Adversarial Motion Priors Make Good Substitutes for Complex Reward Functions

IROS 2022poster

Training a high-dimensional simulated agent with an under-specified reward function often leads the agent to learn physically infeasible strategies that are ineffective when deployed in the real world. To mitigate these unnatural behaviors, reinforcement learning practitioners often utilize complex…

Cited by 123SourceScholar
2022

Dict-BERT: Enhancing Language Model Pre-training with Dictionary

ACL 2022findings

Pre-trained language models (PLMs) aim to learn universal language representations by conducting self-supervised training tasks on large-scale corpora. Since PLMs capture word semantics in different contexts, the quality of word representations highly depends on word frequency, which usually follows…

Cited by 78SourcePDFScholar
2022

Diversifying Content Generation for Commonsense Reasoning with Mixture of Knowledge Graph Experts

ACL 2022findings

Generative commonsense reasoning (GCR) in natural language is to reason about the commonsense while generating coherent text. Recent years have seen a surge of interest in improving the generation quality of commonsense reasoning tasks. Nevertheless, these approaches have seldom investigated diversi…

2022

Empowering Language Models with Knowledge Graph Reasoning for Open-Domain Question Answering

EMNLP 2022main

Answering open-domain questions requires world knowledge about in-context entities. As pre-trained Language Models (LMs) lack the power to store all required knowledge, external knowledge sources, such as knowledge graphs, are often used to augment LMs. In this work, we propose knOwledge REasOning e…

Cited by 61SourcePDFScholar
2022

Grape: Knowledge Graph Enhanced Passage Reader for Open-domain Question Answering

EMNLP 2022finding

A common thread of open-domain question answering (QA) models employs a retriever-reader pipeline that first retrieves a handful of relevant passages from Wikipedia and then peruses the passages to produce an answer. However, even state-of-the-art readers fail to capture the complex relationships be…

2022

KG-FiD: Infusing Knowledge Graph in Fusion-in-Decoder for Open-Domain Question Answering

ACL 2022long

Current Open-Domain Question Answering (ODQA) models typically include a retrieving module and a reading module, where the retriever selects potentially relevant passages from open-source documents for a given question, and the reader produces an answer based on the retrieved passages. The recently…

Cited by 128SourcePDFScholar
2022

Learning Semantics-Aware Locomotion Skills from Human Demonstration

CoRL 2022poster

The semantics of the environment, such as the terrain type and property, reveals important information for legged robots to adjust their behaviors. In this work, we present a framework that learns semantics-aware locomotion skills from perception for quadrupedal robots, such that the robot can trave…

Cited by 12SourceScholar
2022

Learning from Counterfactual Links for Link Prediction

ICML 2022spotlight

Learning to predict missing links is important for many graph-based applications. Existing methods were designed to learn the association between observed graph structure and existence of link between a pair of nodes. However, the causal relationship between the two variables was largely ignored for…

2022

PI-ARS: Accelerating Evolution-Learned Visual-Locomotion with Predictive Information Representations

IROS 2022poster

Evolution Strategy (ES) algorithms have shown promising results in training complex robotic control policies due to their massive parallelism capability, simple implementation, effective parameter-space exploration, and fast training time. However, a key limitation of ES is its scalability to large…

Cited by 12SourceScholar
2022

Retrieval Augmentation for Commonsense Reasoning: A Unified Approach

EMNLP 2022main

A common thread of retrieval-augmented methods in the existing literature focuses on retrieving encyclopedic knowledge, such as Wikipedia, which facilitates well-defined entity and relation spaces that can be modeled. However, applying such methods to commonsense reasoning tasks faces two unique cha…

2022

Safe Reinforcement Learning for Legged Locomotion

IROS 2022poster

Designing control policies for legged locomotion11In this work, we specifically consider quadruped locomotion. is complex due to the under-actuated and non-continuous robot dynamics. Model-free reinforcement learning provides promising tools to tackle this challenge. However, a major bottleneck of a…

Cited by 42SourceScholar
2022

Task Compass: Scaling Multi-task Pre-training with Task Prefix

EMNLP 2022finding

Leveraging task-aware annotated data as supervised signals to assist with self-supervised learning on large-scale unlabeled data has become a new trend in pre-training language models. Existing studies show that multi-task learning with large-scale supervised tasks suffers from negative effects acro…

2022

Zero-Shot Retargeting of Learned Quadruped Locomotion Policies Using Hybrid Kinodynamic Model Predictive Control

IROS 2022poster

Reinforcement Learning (RL) has witnessed great strides for quadruped locomotion, with continued progress in the reliable sim-to-real transfer of policies. However, it remains a challenge to reuse a policy on another robot, which could save time for retraining. In this work, we present a framework f…

Cited by 14SourceScholar
2021

COCOI: Contact-aware Online Context Inference for Generalizable Non-planar Pushing

IROS 2021poster

General contact-rich manipulation problems are long-standing challenges in robotics due to the difficulty of understanding complicated contact physics. Deep reinforcement learning (RL) has shown great potential in solving robot manipulation tasks. However, existing RL policies have limited adaptabil…

Cited by 15SourcecodeScholar
2021

Injecting Entity Types into Entity-Guided Text Generation

EMNLP 2021main

Recent successes in deep generative modeling have led to significant advances in natural language generation (NLG). Incorporating entities into neural generation models has demonstrated great improvements by assisting to infer the summary topic and to generate coherent content. To enhance the role o…

2021

Policy Transfer via Kinematic Domain Randomization and Adaptation

ICRA 2021poster

Transferring reinforcement learning policies trained in physics simulation to the real hardware remains a challenge, known as the "sim-to-real" gap. Domain randomization is a simple yet effective technique to address dynamics discrepancies across source and target domains, but its success generally…

Cited by 38SourcecodeScholar
2021

Protective Policy Transfer

ICRA 2021poster

Being able to transfer existing skills to new situations is a key capability when training robots to operate in unpredictable real-world environments. A successful transfer algorithm should not only minimize the number of samples that the robot needs to collect in the new environment, but also preve…

Cited by 6SourceScholar
2021

Technical Question Answering across Tasks and Domains

NAACL 2021industry

Building automatic technical support system is an important yet challenge task. Conceptually, to answer a user question on a technical forum, a human expert has to first retrieve relevant documents, and then read them carefully to identify the answer snippet. Despite huge success the researchers hav…

2021

Visual-Locomotion: Learning to Walk on Complex Terrains with Vision

CoRL 2021poster

Vision is one of the most important perception modalities for legged robots to safely and efficiently navigate uneven terrains, such as stairs and stepping stones. However, training robots to effectively understand high-dimensional visual input for locomotion is a challenging problem. In this work,…

Cited by 86SourceScholar
2017

Haptic simulation for robot-assisted dressing

ICRA 2017poster

There is a considerable need for assistive dressing among people with disabilities, and robots have the potential to fulfill this need. However, training such a robot would require extensive trials in order to learn the skills of assistive dressing. Such training would be time-consuming and require…

Cited by 54SourceScholar
2017

Learning to navigate cloth using haptics

IROS 2017poster

We present a controller that allows an armlike manipulator to navigate deformable cloth garments in simulation through the use of haptic information. The main challenge of such a controller is to avoid getting tangled in, tearing or punching through the deforming cloth. Our controller aggregates for…

Cited by 34SourceScholar
2017

Preparing for the Unknown: Learning a Universal Policy with Online System Identification

RSS 2017poster

We present a new method of learning control policies that successfully operate under unknown dynamic models. We create such policies by leveraging a large number of training examples that are generated using a physical simulator. Our system is made of two components: a Universal Policy (UP) and a…

2017

What does the person feel? Learning to infer applied forces during robot-assisted dressing

ICRA 2017poster

During robot-assisted dressing, a robot manipulates a garment in contact with a person's body. Inferring the forces applied to the person's body by the garment might enable a robot to provide more effective assistance and give the robot insight into what the person feels. However, complex mechanics…

Cited by 46SourceScholar