Tootfinder

This https://arxiv.org/abs/2405.13178 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csRO_…

One-Shot Imitation Learning with Invariance Matching for Robotic Manipulation
Learning a single universal policy that can perform a diverse set of manipulation tasks is a promising new direction in robotics. However, existing techniques are limited to learning policies that can only perform tasks that are encountered during training, and require a large number of demonstrations to learn new tasks. Humans, on the other hand, often can learn a new task from a single unannotated demonstration. In this work, we propose the Invariance-Matching One-shot Policy Learning (IMOP) …

This https://arxiv.org/abs/2309.09802 has been replaced.
link: https://scholar.google.com/scholar?q=a

DFL-TORO: A One-Shot Demonstration Framework for Learning Time-Optimal Robotic Manufacturing Tasks
This paper presents DFL-TORO, a novel Demonstration Framework for Learning Time-Optimal Robotic tasks via One-shot kinesthetic demonstration. It aims at optimizing the process of Learning from Demonstration (LfD), applied in the manufacturing sector. As the effectiveness of LfD is challenged by the quality and efficiency of human demonstrations, our approach offers a streamlined method to intuitively capture task requirements from human teachers, by reducing the need for multiple demonstrations…

One-Shot Image Restoration
Deborah Pereg
https://arxiv.org/abs/2404.17426 https://arxiv.org/pdf/2404.17426

One-Shot Image Restoration
Image restoration, or inverse problems in image processing, has long been an extensively studied topic. In recent years supervised learning approaches have become a popular strategy attempting to tackle this task. Unfortunately, most supervised learning-based methods are highly demanding in terms of computational resources and training data (sample complexity). In addition, trained models are sensitive to domain changes, such as varying acquisition systems, signal sampling rates, resolution and…

X-Shot: A Unified System to Handle Frequent, Few-shot and Zero-shot Learning Simultaneously in Classification
Hanzi Xu, Muhao Chen, Lifu Huang, Slobodan Vucetic, Wenpeng Yin
https://arxiv.org/abs/2403.03863

X-Shot: A Unified System to Handle Frequent, Few-shot and Zero-shot Learning Simultaneously in Classification
In recent years, few-shot and zero-shot learning, which learn to predict labels with limited annotated instances, have garnered significant attention. Traditional approaches often treat frequent-shot (freq-shot; labels with abundant instances), few-shot, and zero-shot learning as distinct challenges, optimizing systems for just one of these scenarios. Yet, in real-world settings, label occurrences vary greatly. Some of them might appear thousands of times, while others might only appear sporadi…

Socratic Planner: Inquiry-Based Zero-Shot Planning for Embodied Instruction Following
Suyeon Shin, Sujin jeon, Junghyun Kim, Gi-Cheon Kang, Byoung-Tak Zhang
https://arxiv.org/abs/2404.15190

Socratic Planner: Inquiry-Based Zero-Shot Planning for Embodied Instruction Following
Embodied Instruction Following (EIF) is the task of executing natural language instructions by navigating and interacting with objects in 3D environments. One of the primary challenges in EIF is compositional task planning, which is often addressed with supervised or in-context learning with labeled data. To this end, we introduce the Socratic Planner, the first zero-shot planning method that infers without the need for any training data. Socratic Planner first decomposes the instructions into …

This https://arxiv.org/abs/2309.09802 has been replaced.
link: https://scholar.google.com/scholar?q=a

DFL-TORO: A One-Shot Demonstration Framework for Learning Time-Optimal Robotic Manufacturing Tasks
This paper presents DFL-TORO, a novel Demonstration Framework for Learning Time-Optimal Robotic tasks via One-shot kinesthetic demonstration. It aims at optimizing the process of Learning from Demonstration (LfD), applied in the manufacturing sector. As the effectiveness of LfD is challenged by the quality and efficiency of human demonstrations, our approach offers a streamlined method to intuitively capture task requirements from human teachers, by reducing the need for multiple demonstrations…

Zero-Shot Relational Learning for Multimodal Knowledge Graphs
Rui Cai, Shichao Pei, Xiangliang Zhang
https://arxiv.org/abs/2404.06220 https://

Zero-Shot Relational Learning for Multimodal Knowledge Graphs
Relational learning is an essential task in the domain of knowledge representation, particularly in knowledge graph completion (KGC).While relational learning in traditional single-modal settings has been extensively studied, exploring it within a multimodal KGC context presents distinct challenges and opportunities. One of the major challenges is inference on newly discovered relations without any associated training data. This zero-shot relational learning scenario poses unique requirements f…

This https://arxiv.org/abs/2404.10702 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csMM_…

Retrieval Augmented Verification: Unveiling Disinformation with Structured Representations for Zero-Shot Real-Time Evidence-guided Fact-Checking of Multi-modal Social media posts
Social Media posts, where real images are unscrupulously reused along with provocative text to promote a particular idea, have been one of the major sources of disinformation. By design, these claims are without editorial oversight and accessible to a vast population who otherwise may not have access to multiple information sources. This implies the need to fact-check these posts and clearly explain which parts of the posts are fake. In the supervised learning setup, this is often reduced to a …

Large-Scale Label Interpretation Learning for Few-Shot Named Entity Recognition
Jonas Golde, Felix Hamborg, Alan Akbik
https://arxiv.org/abs/2403.14222 htt…

Large-Scale Label Interpretation Learning for Few-Shot Named Entity Recognition
Few-shot named entity recognition (NER) detects named entities within text using only a few annotated examples. One promising line of research is to leverage natural language descriptions of each entity type: the common label PER might, for example, be verbalized as ''person entity.'' In an initial label interpretation learning phase, the model learns to interpret such verbalized descriptions of entity types. In a subsequent few-shot tagset extension phase, this model is then given a descriptio…

This https://arxiv.org/abs/2306.11376 has been replaced.
initial toot: https://mastoxiv.page/@arX…

Coevolution of cognition and cooperation in structured populations under reinforcement learning
We study the evolution of behavior under reinforcement learning in a Prisoner's Dilemma where agents interact in a regular network and can learn about whether they play one-shot or repeatedly by incurring a cost of deliberation. With respect to other behavioral rules used in the literature, (i) we confirm the existence of a threshold value of the probability of repeated interaction, switching the emergent behavior from intuitive defector to dual-process cooperator; (ii) we find a different role…

This https://arxiv.org/abs/2404.10702 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csMM_…

Retrieval Augmented Verification: Unveiling Disinformation with Structured Representations for Zero-Shot Real-Time Evidence-guided Fact-Checking of Multi-modal Social media posts
Social Media posts, where real images are unscrupulously reused along with provocative text to promote a particular idea, have been one of the major sources of disinformation. By design, these claims are without editorial oversight and accessible to a vast population who otherwise may not have access to multiple information sources. This implies the need to fact-check these posts and clearly explain which parts of the posts are fake. In the supervised learning setup, this is often reduced to a …

Distributed Learning for Dynamic Congestion Games
Hongbo Li, Lingjie Duan
https://arxiv.org/abs/2405.03031 https://arxiv.org/pdf/2405…

Distributed Learning for Dynamic Congestion Games
Today mobile users learn and share their traffic observations via crowdsourcing platforms (e.g., Google Maps and Waze). Yet such platforms myopically recommend the currently shortest path to users, and selfish users are unwilling to travel to longer paths of varying traffic conditions to explore. Prior studies focus on one-shot congestion games without information learning, while our work studies how users learn and alter traffic conditions on stochastic paths in a distributed manner. Our analy…

This https://arxiv.org/abs/2207.09098 has been replaced.
link: https://scholar.google.com/scholar?q=a

ReBoot: Distributed statistical learning via refitting bootstrap samples
In this paper, we propose a one-shot distributed learning algorithm via refitting bootstrap samples, which we refer to as ReBoot. ReBoot refits a new model to mini-batches of bootstrap samples that are continuously drawn from each of the locally fitted models. It requires only one round of communication of model parameters without much memory. Theoretically, we analyze the statistical error rate of ReBoot for generalized linear models (GLM) and noisy phase retrieval, which represent convex and …

This https://arxiv.org/abs/2305.10300 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_ees…

One-Prompt to Segment All Medical Images
Large foundation models, known for their strong zero-shot generalization, have excelled in visual and language applications. However, applying them to medical image segmentation, a domain with diverse imaging types and target labels, remains an open challenge. Current approaches, such as adapting interactive segmentation models like Segment Anything Model (SAM), require user prompts for each sample during inference. Alternatively, transfer learning methods like few/one-shot models demand labele…

This https://arxiv.org/abs/2311.02787 has been replaced.
link: https://scholar.google.com/scholar?q=a

Make a Donut: Hierarchical EMD-Space Planning for Zero-Shot Deformable Manipulation with Tools
Deformable object manipulation stands as one of the most captivating yet formidable challenges in robotics. While previous techniques have predominantly relied on learning latent dynamics through demonstrations, typically represented as either particles or images, there exists a pertinent limitation: acquiring suitable demonstrations, especially for long-horizon tasks, can be elusive. Moreover, basing learning entirely on demonstrations can hamper the model's ability to generalize beyond the de…

This https://arxiv.org/abs/2401.16579 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csIT_…

On Channel Simulation with Causal Rejection Samplers
One-shot channel simulation has recently emerged as a promising alternative to quantization and entropy coding in machine-learning-based lossy data compression schemes. However, while there are several potential applications of channel simulation - lossy compression with realism constraints or differential privacy, to name a few - little is known about its fundamental limitations. In this paper, we restrict our attention to a subclass of channel simulation protocols called causal rejection samp…

This https://arxiv.org/abs/2403.07786 has been replaced.
initial toot: https://mastoxiv.page/@ar…

Generative deep learning-enabled ultra-large field-of-view lens-free imaging
Advancements in high-throughput biomedical applications necessitate real-time, large field-of-view (FOV) imaging capabilities. Conventional lens-free imaging (LFI) systems, while addressing the limitations of physical lenses, have been constrained by dynamic, hard-to-model optical fields, resulting in a limited one-shot FOV of approximately 20 $mm^2$. This restriction has been a major bottleneck in applications like live-cell imaging and automation of microfluidic systems for biomedical researc…

This https://arxiv.org/abs/2404.10591 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csRO_…

Learning Symbolic Task Representation from a Human-Led Demonstration: A Memory to Store, Retrieve, Consolidate, and Forget Experiences
We present a symbolic learning framework inspired by cognitive-like memory functionalities (i.e., storing, retrieving, consolidating and forgetting) to generate task representations to support high-level task planning and knowledge bootstrapping. We address a scenario involving a non-expert human, who performs a single task demonstration, and a robot, which online learns structured knowledge to re-execute the task based on experiences, i.e., observations. We consider a one-shot learning process…

Learning Symbolic Task Representation from a Human-Led Demonstration: A Memory to Store, Retrieve, Consolidate, and Forget Experiences
Luca Buoncompagni, Fulvio Mastrogiovanni
https://arxiv.org/abs/2404.10591

Learning Symbolic Task Representation from a Human-Led Demonstration: A Memory to Store, Retrieve, Consolidate, and Forget Experiences
We present a symbolic learning framework inspired by cognitive-like memory functionalities (i.e., storing, retrieving, consolidating and forgetting) to generate task representations to support high-level task planning and knowledge bootstrapping. We address a scenario involving a non-expert human, who performs a single task demonstration, and a robot, which online learns structured knowledge to re-execute the task based on experiences, i.e., observations. We consider a one-shot learning process…

This https://arxiv.org/abs/2305.10300 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_ees…

One-Prompt to Segment All Medical Images
Large foundation models, known for their strong zero-shot generalization, have excelled in visual and language applications. However, applying them to medical image segmentation, a domain with diverse imaging types and target labels, remains an open challenge. Current approaches, such as adapting interactive segmentation models like Segment Anything Model (SAM), require user prompts for each sample during inference. Alternatively, transfer learning methods like few/one-shot models demand labele…

Retrieval Augmented Verification : Unveiling Disinformation with Structured Representations for Zero-Shot Real-Time Evidence-guided Fact-Checking of Multi-modal Social media posts
Arka Ujjal Dey, Artemis Llabr\'es, Ernest Valveny, Dimosthenis Karatzas
https://arxiv.org/abs/2404.10702…

Retrieval Augmented Verification : Unveiling Disinformation with Structured Representations for Zero-Shot Real-Time Evidence-guided Fact-Checking of Multi-modal Social media posts
Social Media posts, where real images are unscrupulously reused along with provocative text to promote a particular idea, have been one of the major sources of disinformation. By design, these claims are without editorial oversight and accessible to a vast population who otherwise may not have access to multiple information sources. This implies the need to fact-check these posts and clearly explain which parts of the posts are fake. In the supervised learning setup, this is often reduced to a …

Generative deep learning-enabled ultra-large field-of-view lens-free imaging
Ronald B. Liu, Zhe Liu, Max G. A. Wolf, Krishna P. Purohit, Gregor Fritz, Yi Feng, Carsten G. Hansen, Pierre O. Bagnaninchi, Xavier Casadevall i Solvas, Yunjie Yang
https://arxiv.org/abs/2403.07786

Generative deep learning-enabled ultra-large field-of-view lens-free imaging
Advancements in high-throughput biomedical applications necessitate real-time, large field-of-view (FOV) imaging capabilities. Conventional lens-free imaging (LFI) systems, while addressing the limitations of physical lenses, have been constrained by dynamic, hard-to-model optical fields, resulting in a limited one-shot FOV of approximately 20 $mm^2$. This restriction has been a major bottleneck in applications like live-cell imaging and automation of microfluidic systems for biomedical researc…

This https://arxiv.org/abs/2403.07786 has been replaced.
initial toot: https://mastoxiv.page/@ar…

Generative deep learning-enabled ultra-large field-of-view lens-free imaging
Advancements in high-throughput biomedical applications necessitate real-time, large field-of-view (FOV) imaging capabilities. Conventional lens-free imaging (LFI) systems, while addressing the limitations of physical lenses, have been constrained by dynamic, hard-to-model optical fields, resulting in a limited one-shot FOV of approximately 20 $mm^2$. This restriction has been a major bottleneck in applications like live-cell imaging and automation of microfluidic systems for biomedical researc…