Search Results for author:
Found 64 papers, 29 papers with code
Effective Tuning Strategies for Generalist Robot Manipulation Policies
While fine-tuning offers a practical way to quickly adapt a GMPs to novel domains and tasks with limited samples, we observe that the performance of the resulting GMPs differs significantly with respect to the design choices of fine-tuning strategies.
MECD: Unlocking Multi-Event Causal Discovery in Video Reasoning
Video causal reasoning aims to achieve a high-level understanding of video content from a causal perspective.
Ranked #1 on
Causal Discovery in Video Reasoning
on MECD
Automated Review Generation Method Based on Large Language Models
Literature research, vital for scientific advancement, is overwhelmed by the vast ocean of available information.
Mixture of Experts based Multi-task Supervise Learning from Crowds
Within this paradigm, we propose a worker behavior model at the item feature level called Mixture of Experts based Multi-task Supervised Learning from Crowds (MMLC).
BiGym: A Demo-Driven Mobile Bi-Manual Manipulation Benchmark
To validate the usability of BiGym, we thoroughly benchmark the state-of-the-art imitation learning algorithms and demo-driven reinforcement learning algorithms within the environment and discuss the future opportunities.
Green Screen Augmentation Enables Scene Generalisation in Robotic Manipulation
Current practices involve collecting data in one location, training imitation learning or reinforcement learning policies with this data, and deploying the policy in the same location.
Test-Time Generative Augmentation for Medical Image Segmentation
In this paper, we propose a novel approach to enhance medical image segmentation during test time.
Safety Alignment Should Be Made More Than Just a Few Tokens Deep
We refer to this issue as shallow safety alignment.
Redundancy-aware Action Spaces for Robot Learning
Joint space and task space control are the two dominant action modes for controlling robot arms within the robot learning literature.
Hierarchical Action Recognition: A Contrastive Video-Language Approach with Hierarchical Interactions
Video recognition remains an open challenge, requiring the identification of diverse content categories within videos.
Memory-efficient High-resolution OCT Volume Synthesis with Cascaded Amortized Latent Diffusion Models
In tandem with autoencoders, we propose cascaded diffusion processes to synthesize high-resolution OCT volumes with a global-to-local refinement process, amortizing the memory and computational demands.
DiTMoS: Delving into Diverse Tiny-Model Selection on Microcontrollers
Enabling efficient and accurate deep neural network (DNN) inference on microcontrollers is non-trivial due to the constrained on-chip resources.
Hierarchical Diffusion Policy for Kinematics-Aware Multi-Task Robotic Manipulation
This paper introduces Hierarchical Diffusion Policy (HDP), a hierarchical agent for multi-task robotic manipulation.
InsActor: Instruction-driven Physics-based Characters
Generating animation of physics-based characters with intuitive control has long been a desirable task with numerous applications.
Gemini: A Family of Highly Capable Multimodal Models
This report introduces a new family of multimodal models, Gemini, that exhibit remarkable capabilities across image, audio, video, and text understanding.
Ranked #1 on
Visual Question Answering (VQA)
on InfographicVQA
Collaborative Weakly Supervised Video Correlation Learning for Procedure-Aware Instructional Video Analysis
Our framework comprises two core modules: collaborative step mining and frame-to-step alignment.
Adjustable Robust Transformer for High Myopia Screening in Optical Coherence Tomography
Measurements of spherical equivalent and axial length are the gold standards for identifying high myopia, but the available image data for matching them is scarce.
Beyond ChatBots: ExploreLLM for Structured Thoughts and Personalized Model Responses
The study also suggests that users can more easily personalize responses with high-level preferences with ExploreLLM.
Improving Few-shot Generalization of Safety Classifiers via Data Augmented Parameter-Efficient Fine-Tuning
As large language models (LLMs) are widely adopted, new safety issues and policies emerge, to which existing safety classifiers do not generalize well.
Improving Diversity of Demographic Representation in Large Language Models via Collective-Critiques and Self-Voting
A crucial challenge for generative large language models (LLMs) is diversity: when a user's prompt is under-specified, models may follow implicit assumptions while generating a response, which may result in homogenization of the responses, as well as certain demographic groups being under-represented or even erased from the generated responses.
A global product of fine-scale urban building height based on spaceborne lidar
Our results revealed that the estimated method of building height samples based on the GEDI data was effective with 0. 78 of Pearson's r and 3. 67 m of RMSE in comparison to the reference data.
Let's Do a Thought Experiment: Using Counterfactuals to Improve Moral Reasoning
Language models still struggle on moral reasoning, despite their impressive performance in many other tasks.
Decoupled Prioritized Resampling for Offline RL
OPER is a plug-and-play component for offline RL algorithms.
Improving and Benchmarking Offline Reinforcement Learning Algorithms
Recently, Offline Reinforcement Learning (RL) has achieved remarkable progress with the emergence of various algorithms and datasets.
Efficient Diffusion Policies for Offline Reinforcement Learning
2) It is incompatible with maximum likelihood-based RL algorithms (e. g., policy gradient methods) as the likelihood of diffusion models is intractable.
Visualising Personal Data Flows: Insights from a Case Study of Booking.com
This case study can inform us about future research on more data flow-oriented privacy policy analysis and on the construction of a more comprehensive ontology on personal data flows in complicated business ecosystems.
Hi Sheldon! Creating Deep Personalized Characters from TV Shows
To support this novel task, we further collect a character centric multimodal dialogue dataset, named Deep Personalized Character Dataset (DPCD), from TV shows.
DiffMimic: Efficient Motion Mimicking with Differentiable Physics
Motion mimicking is a foundational task in physics-based character animation.
Imitation Learning As State Matching via Differentiable Physics
With the physics prior, ILD policies can not only be transferable to unseen environment specifications but also yield higher final performance on a variety of tasks.
A Human-ML Collaboration Framework for Improving Video Content Reviews
We deal with the problem of localized in-video taxonomic human annotation in the video content moderation domain, where the goal is to identify video segments that violate granular policies, e. g., community guidelines on an online video platform.
RPM: Generalizable Behaviors for Multi-Agent Reinforcement Learning
Despite the recent advancement in multi-agent reinforcement learning (MARL), the MARL agents easily overfit the training environment and perform poorly in the evaluation scenarios where other agents behave differently.
Multi-agent Reinforcement Learning
reinforcement-learning
+2
Boosting Offline Reinforcement Learning via Data Rebalancing
Therefore, we propose a simple yet effective method to boost offline RL algorithms based on the observation that resampling a dataset keeps the distribution support unchanged.
Mutual Information Regularized Offline Reinforcement Learning
In this work, we propose a novel MISA framework to approach offline RL from the perspective of Mutual Information between States and Actions in the dataset by directly constraining the policy improvement direction.
Imitation Learning via Differentiable Physics
With the physics prior, ILD policies can not only be transferable to unseen environment specifications but also yield higher final performance on a variety of tasks.
Label Adversarial Learning for Skeleton-level to Pixel-level Adjustable Vessel Segmentation
This continuous process allows us to recommend high-quality vessel segmentation with clear caliber and topology.
Towards Sustainable Satellite Edge Computing
Recently, Low Earth Orbit (LEO) satellites experience rapid development and satellite edge computing emerges to address the limitation of bent-pipe architecture in existing satellite systems.
Benchmarking of DL Libraries and Models on Mobile Devices
Deploying deep learning (DL) on mobile devices has been a notable trend in recent years.
On Exploring Pose Estimation as an Auxiliary Learning Task for Visible-Infrared Person Re-identification
Visible-infrared person re-identification (VI-ReID) has been challenging due to the existence of large discrepancies between visible and infrared modalities.
State-based Episodic Memory for Multi-Agent Reinforcement Learning
SEM adopts episodic memory (EM) to supervise the centralized training procedure of CTDE in MARL.
Ab Initio Particle-based Object Manipulation
Like the model-based analytic approaches to manipulation, the particle representation enables the robot to reason about the object's geometry and dynamics in order to choose suitable manipulation actions.
FineAction: A Fine-Grained Video Dataset for Temporal Action Localization
Temporal action localization (TAL) is an important and challenging problem in video understanding.
Learning Latent Graph Dynamics for Visual Manipulation of Deformable Objects
Manipulating deformable objects, such as ropes and clothing, is a long-standing challenge in robotics, because of their large degrees of freedom, complex non-linear dynamics, and self-occlusion in visual perception.
HAVANA: Hierarchical and Variation-Normalized Autoencoder for Person Re-identification
Person Re-Identification (Re-ID) is of great importance to the many video surveillance systems.
Towards Overcoming False Positives in Visual Relationship Detection
We observe that during training, the relationship proposal distribution is highly imbalanced: most of the negative relationship proposals are easy to identify, e. g., the inaccurate object detection, which leads to the under-fitting of low-frequency difficult proposals.
Hierarchical Federated Learning through LAN-WAN Orchestration
Our proposed FL can accelerate the learning process and reduce the monetary cost with frequent local aggregation in the same LAN and infrequent global aggregation on a cloud across WAN.
Contrastive Variational Reinforcement Learning for Complex Observations
This paper presents Contrastive Variational Reinforcement Learning (CVRL), a model-based method that tackles complex visual observations in DRL.
Balanced Meta-Softmax for Long-Tailed Visual Recognition
In our experiments, we demonstrate that Balanced Meta-Softmax outperforms state-of-the-art long-tailed classification solutions on both visual recognition and instance segmentation tasks.
Ranked #7 on
Long-tail Learning
on CIFAR-10-LT (ρ=10)
DinerDash Gym: A Benchmark for Policy Learning in High-Dimensional Action Space
It has been arduous to assess the progress of a policy learning algorithm in the domain of hierarchical task with high dimensional action space due to the lack of a commonly accepted benchmark.
Spatio-Temporal Graph Transformer Networks for Pedestrian Trajectory Prediction
In this paper, we present STAR, a Spatio-Temporal grAph tRansformer framework, which tackles trajectory prediction by only attention mechanisms.
R3: A Reading Comprehension Benchmark Requiring Reasoning Processes
Existing question answering systems can only predict answers without explicit reasoning processes, which hinder their explainability and make us overestimate their ability of understanding and reasoning over natural language.
Challenges in Supporting Exploratory Search through Voice Assistants
Compared to simple search tasks such as "How tall is the Eiffel Tower?
AI-Mediated Exchange Theory
As an extension to Social Exchange Theory (SET) in the social sciences, AI-MET views AI as influencing human-to-human relationships via a taxonomy of mediation mechanisms.
Discriminative Particle Filter Reinforcement Learning for Complex Partial Observations
The particle filter maintains a belief using learned discriminative update, which is trained end-to-end for decision making.
AMAD: Adversarial Multiscale Anomaly Detection on High-Dimensional and Time-Evolving Categorical Data
Anomaly detection is facing with emerging challenges in many important industry domains, such as cyber security and online recommendation and advertising.
Clustered Reinforcement Learning
Exploration strategy design is one of the challenging problems in reinforcement learning~(RL), especially when the environment contains a large state space or sparse rewards.
Particle Filter Recurrent Neural Networks
Recurrent neural networks (RNNs) have been extraordinarily successful for prediction with sequential data.
Differentiable Algorithm Networks for Composable Robot Learning
This paper introduces the Differentiable Algorithm Network (DAN), a composable architecture for robot learning systems.
Neural Architecture Search Over a Graph Search Space
However, the success of NAS depends on the definition of the search space.
Homogeneous Feature Transfer and Heterogeneous Location Fine-tuning for Cross-City Property Appraisal Framework
Most existing real estate appraisal methods focus on building accuracy and reliable models from a given dataset but pay little attention to the extensibility of their trained model.
Understanding Image Quality and Trust in Peer-to-Peer Marketplaces
In this work, we conducted a large-scale study on the quality of user-generated images in peer-to-peer marketplaces.
Dermoscopic Image Analysis for ISIC Challenge 2018
This short paper reports the algorithms we used and the evaluation performances for ISIC Challenge 2018.
Entire Space Multi-Task Model: An Effective Approach for Estimating Post-Click Conversion Rate
To the best of our knowledge, this is the first public dataset which contains samples with sequential dependence of click and conversion labels for CVR modeling.
Deep Interest Network for Click-Through Rate Prediction
In this way, user features are compressed into a fixed-length representation vector, in regardless of what candidate ads are.
Ranked #1 on
Click-Through Rate Prediction
on Amazon
