papers

Publications (32)

cs.CV2014

A Faster Method for Tracking and Scoring Videos Corresponding to Sentences

Haonan Yu, Daniel P. Barrett, Jeffrey Mark Siskind

Prior work presented the sentence tracker, a method for scoring how well a sentence describes a video clip or alternatively how well a video clip depicts a sentence. We present an…

stat.ML2020

Playing the lottery with rewards and multiple languages: lottery tickets in RL and NLP

Haonan Yu, Sergey Edunov, Yuandong Tian +1

The lottery ticket hypothesis proposes that over-parameterization of deep neural networks (DNNs) aids training by increasing the probability of a "lucky" sub-network initialization…

cs.CL2018

Interactive Language Acquisition with One-shot Visual Concept Learning through a Conversational Game

Haichao Zhang, Haonan Yu, Wei Xu

Building intelligent agents that can communicate with and learn from humans in natural language is of great value. Supervised language learning is limited by the ability of capturi…

cs.RO2015

Robot Language Learning, Generation, and Comprehension

Daniel Paul Barrett, Scott Alan Bronikowski, Haonan Yu +1

We present a unified framework which supports grounding natural-language semantics in robotic driving. This framework supports acquisition (learning grounded meanings of nouns and…

cs.CL2026

Focus-LIME: Surgical Interpretation of Long-Context Large Language Models via Proxy-Based Neighborhood Selection

Junhao Liu, Haonan Yu, Zhenyu Yan +1

As Large Language Models (LLMs) scale to handle massive context windows, achieving surgical feature-level interpretation is essential for high-stakes tasks like legal auditing and…

cs.LG2022

Hierarchical Reinforcement Learning By Discovering Intrinsic Options

Jesse Zhang, Haonan Yu, Wei Xu

We propose a hierarchical reinforcement learning method, HIDIO, that can learn task-agnostic options in a self-supervised manner while jointly learning to utilize them to solve spa…

cs.AI2018

Guided Feature Transformation (GFT): A Neural Language Grounding Module for Embodied Agents

Haonan Yu, Xiaochen Lian, Haichao Zhang +1

Recently there has been a rising interest in training agents, embodied in virtual environments, to perform language-directed tasks by deep reinforcement learning. In this paper, we…

cs.NE2018

Resource-Efficient Neural Architect

Yanqi Zhou, Siavash Ebrahimi, Sercan Ö. Arık +3

Neural Architecture Search (NAS) is a laborious process. Prior work on automated NAS targets mainly on improving accuracy, but lacks consideration of computational resource use. We…

cs.RO2025

Learning Multi-Stage Pick-and-Place with a Legged Mobile Manipulator

Haichao Zhang, Haonan Yu, Le Zhao +4

Quadruped-based mobile manipulation presents significant challenges in robotics due to the diversity of required skills, the extended task horizon, and partial observability. After…

cs.CL2026

WASD: Locating Critical Neurons as Sufficient Conditions for Explaining and Controlling LLM Behavior

Haonan Yu, Junhao Liu, Zhenyu Yan +2

Precise behavioral control of large language models (LLMs) is critical for complex applications. However, existing methods often incur high training costs, lack natural language co…

cs.LG2022

Do You Need the Entropy Reward (in Practice)?

Haonan Yu, Haichao Zhang, Wei Xu

Maximum entropy (MaxEnt) RL maximizes a combination of the original task reward and an entropy reward. It is believed that the regularization imposed by entropy, on both policy imp…

cs.LG2026

Beyond Attribution: Unified Concept-Level Explanations

Junhao Liu, Haonan Yu, Xin Zhang

There is an increasing need to integrate model-agnostic explanation techniques with concept-based approaches, as the former can explain models across different architectures while…

cs.AI2019

Why Build an Assistant in Minecraft?

Arthur Szlam, Jonathan Gray, Kavya Srinet +11

In this document we describe a rationale for a research program aimed at building an open "assistant" in the game Minecraft, in order to make progress on the problems of natural la…

cs.RO2021

MetaView: Few-shot Active Object Recognition

Wei Wei, Haonan Yu, Haichao Zhang +2

In robot sensing scenarios, instead of passively utilizing human captured views, an agent should be able to actively choose informative viewpoints of a 3D object as discriminative…

cs.LG2026

MAnchors: Memorization-Based Acceleration of Anchors via Rule Reuse and Transformation

Haonan Yu, Junhao Liu, Xin Zhang

Anchors is a popular local model-agnostic explanation technique whose applicability is limited by its computational inefficiency. To address this limitation, we propose a memorizat…

cs.AI2025

Policy Expansion for Bridging Offline-to-Online Reinforcement Learning

Haichao Zhang, We Xu, Haonan Yu

Pre-training with offline data and online fine-tuning using reinforcement learning is a promising strategy for learning control policies by leveraging the best of both worlds in te…

cs.CV2013

Discriminative Training: Learning to Describe Video with Sentences, from Video Described with Sentences

Haonan Yu, Jeffrey Mark Siskind

We present a method for learning word meanings from complex and realistic video clips by discriminatively training (DT) positive sentential labels against negative ones, and then u…

cs.CL2017

A Deep Compositional Framework for Human-like Language Acquisition in Virtual Environment

Haonan Yu, Haichao Zhang, Wei Xu

We tackle a task where an agent learns to navigate in a 2D maze-like environment called XWORLD. In each session, the agent perceives a sequence of raw-pixel frames, a natural langu…

cs.CV2015

Collecting and Annotating the Large Continuous Action Dataset

Daniel Paul Barrett, Ran Xu, Haonan Yu +1

We make available to the community a new dataset to support action-recognition research. This dataset is different from prior datasets in several key ways. It is significantly larg…

cs.LG2021

TAAC: Temporally Abstract Actor-Critic for Continuous Control

Haonan Yu, Wei Xu, Haichao Zhang

We present temporally abstract actor-critic (TAAC), a simple but effective off-policy RL algorithm that incorporates closed-loop temporal abstraction into the actor-critic framewor…

cs.LG2026

Revitalizing Black-Box Interpretability: Actionable Interpretability for LLMs via Proxy Models

Junhao Liu, Haonan Yu, Zhenyu Yan +1

Post-hoc explanations provide transparency and are essential for guiding model optimization, such as prompt engineering and data sanitation. However, applying model-agnostic techni…

cs.CL2017

Listen, Interact and Talk: Learning to Speak via Interaction

Haichao Zhang, Haonan Yu, Wei Xu

One of the long-term goals of artificial intelligence is to build an agent that can communicate intelligently with human in natural language. Most existing work on natural language…

cs.RO2025

SLIM: Sim-to-Real Legged Instructive Manipulation via Long-Horizon Visuomotor Learning

Haichao Zhang, Haonan Yu, Le Zhao +4

We present a low-cost legged mobile manipulation system that solves long-horizon real-world tasks, trained by reinforcement learning purely in simulation. This system is made possi…

stat.ML2019

One ticket to win them all: generalizing lottery ticket initializations across datasets and optimizers

Ari S. Morcos, Haonan Yu, Michela Paganini +1

The success of lottery ticket initializations (Frankle and Carbin, 2019) suggests that small, sparsified networks can be trained so long as the network is initialized appropriately…

cs.CV2016

Video Paragraph Captioning Using Hierarchical Recurrent Neural Networks

Haonan Yu, Jiang Wang, Zhiheng Huang +2

We present an approach that exploits hierarchical Recurrent Neural Networks (RNNs) to tackle the video captioning problem, i.e., generating one or multiple sentences to describe a…

cs.LG2022

Towards Safe Reinforcement Learning with a Safety Editor Policy

Haonan Yu, Wei Xu, Haichao Zhang

We consider the safe reinforcement learning (RL) problem of maximizing utility with extremely low constraint violation rates. Assuming no prior knowledge or pre-training of the env…

cs.AI2019

CraftAssist: A Framework for Dialogue-enabled Interactive Agents

Jonathan Gray, Kavya Srinet, Yacine Jernite +6

This paper describes an implementation of a bot assistant in Minecraft, and the tools and platform allowing players to interact with the bot and to record those interactions. The p…

cs.CV2024

VONet: Unsupervised Video Object Learning With Parallel U-Net Attention and Object-wise Sequential VAE

Haonan Yu, Wei Xu

Unsupervised video object learning seeks to decompose video scenes into structural object representations without any supervision from depth, optical flow, or segmentation. We pres…

cs.LG2019

EPNAS: Efficient Progressive Neural Architecture Search

Yanqi Zhou, Peng Wang, Sercan Arik +4

In this paper, we propose Efficient Progressive Neural Architecture Search (EPNAS), a neural architecture search (NAS) that efficiently handles large search space through a novel p…

cs.CV2016

Sentence Directed Video Object Codetection

Haonan Yu, Jeffrey Mark Siskind

We tackle the problem of video object codetection by leveraging the weak semantic constraint implied by sentences that describe the video content. Unlike most existing work that fo…

cs.LG2022

Generative Planning for Temporally Coordinated Exploration in Reinforcement Learning

Haichao Zhang, Wei Xu, Haonan Yu

Standard model-free reinforcement learning algorithms optimize a policy that generates the action to be taken in the current time step in order to maximize expected future return.…

cs.CL2018

Interactive Grounded Language Acquisition and Generalization in a 2D World

Haonan Yu, Haichao Zhang, Wei Xu

We build a virtual agent for learning language in a 2D maze-like world. The agent sees images of the surrounding environment, listens to a virtual teacher, and takes actions to rec…