Title
Topic
-
‘Designing for Playfulness in Human-AI Authoring Tools’
“Many human-AI authoring tools are used in a playful way, while being primarily designed for task-achievement—not playfulness. We argue that playfulness is an important yet overlooked factor of user behaviour and experience when interacting with such tools. … In this paper, we motivate the importance of playfulness as user experience in human-AI authoring tools, and propose concrete strategies to design for playfulness in the human user through UI design, in the AI through algorithms or through interventions to their dialog.” Find the paper and full list of authors in the 18th International Conference on the Foundations of Digital Games proceedings.
-
‘Knowledge Transfer From High-Resource to Low-Resource Programming Languages for Code LLMs’
“Over the past few years, Large Language Models of Code (Code LLMs) have started to have a significant impact on programming practice. Code LLMs are also emerging as a building block for research in programming languages and software engineering. However, the quality of code produced by a Code LLM varies significantly by programming languages. … This paper presents an effective approach for boosting the performance of Code LLMs on low-resource languages using semi-synthetic data. Our approach generates high-quality datasets for low-resource languages, which can then be used to fine-tune any pretrained Code LLM.” Find the paper and list of authors…
-
‘Contrastive Alignment of Vision to Language Through Parameter-Efficient Transfer Learning’
“Contrastive vision-language models (e.g. CLIP) are typically created by updating all the parameters of a vision model and language model through contrastive training. Can such models be created by a small number of parameter updates to an already-trained language model and vision model? … We explore the feasibility and benefits of parameter-efficient contrastive vision-language alignment through transfer learning: creating a model such as CLIP by minimally updating an already-trained vision and language model. We find that a minimal set of parameter updates (<7%) can achieve the same performance as full-model training.” Find the paper and full list of authors at…
-
‘Frame Flexible Network’
“Existing video recognition algorithms always conduct different training pipelines for inputs with different frame numbers, which requires repetitive training operations and multiplying storage costs. If we evaluate the model using other frames which are not used in training, we observe the performance will drop significantly. … To fix this issue, we propose a general framework, named Frame Flexible Network (FFN), which not only enables the model to be evaluated at different frames to adjust its computation, but also reduces the memory costs of storing multiple models significantly.” Find the paper and full list of authors at ArXiv.
-
‘Robust Communication Complexity of Matching: EDCS Achieves 5/6 Approximation’
“We study the robust communication complexity of maximum matching. Edges of an arbitrary n-vertex graph G are randomly partitioned between Alice and Bob independently and uniformly. Alice has to send a single message to Bob such that Bob can find an (approximate) maximum matching of the whole graph G. We specifically study the best approximation ratio achievable via protocols where Alice communicates only O˜(n) bits to Bob.” Find the paper and full list of authors at ArXiv.
-
‘Streaming Edge Coloring with Asymptotically Optimal Colors’
“Given a graph G, an edge-coloring is an assignment of colors to edges of G such that any two edges sharing an endpoint receive different colors. By Vizing’s celebrated theorem, any graph of maximum degree Δ needs at least Δ and at most (Δ+1) colors to be properly edge colored. In this paper, we study edge colorings in the streaming setting. The edges arrive one by one in an arbitrary order. The algorithm takes a single pass over the input and must output a solution using a much smaller space.” Find the paper and full list of authors at ArXiv.
-
‘BEV-DG: Cross-Modal Learning Under Bird’s-Eye View for Domain Generalization of 3D Semantic Segmentation’
“Cross-modal Unsupervised Domain Adaptation (UDA) aims to exploit the complementarity of 2D-3D data to overcome the lack of annotation in a new domain. However, UDA methods rely on access to the target domain during training, meaning the trained model only works in a specific target domain. In light of this, we propose cross-modal learning under bird’s-eye view for Domain Generalization (DG) of 3D semantic segmentation, called BEV-DG. … Our approach aims to optimize domain-irrelevant representation modeling with the aid of cross-modal learning under bird’s-eye view.” Find the paper and full list of authors at ArXiv.
-
Developing eco-friendly cooling solutions
“Mechanical and industrial engineering associate professor Yi Zheng’s spinout from his lab at Northeastern, Planck Energies, has received a $275,000 NSF grant for ‘Climate-Eco-Friendly Biocoating for Passive Cooling of Infrastructure.'”
-
Dahiya speaks at AI for Good Global Summit
“Electrical and computer engineering professor Ravinder Dahiya was selected as a speaker for the AI for Good Global Summit: Accelerating the United Nations Sustainable Development Goals, which was held in Geneva, Switzerland, July 6-7, 2023. The AI for Good Global Summit is the leading action-oriented United Nations platform promoting AI to advance health, climate, gender, inclusive prosperity, sustainable infrastructure and other global development priorities.”
-
Psychology professor building ‘data science tool’ to increase the reliability of human brain research
Assistant professor of psychology Stephanie Noble is building a power calculator to help human neuroscience researchers increase the reproducibility of their experiments.
-
Researchers win best paper award for content distribution framework
“A team of researchers from Northeastern University, MIT and EURECOM won the best paper award at the 21st International Symposium on Modeling and Optimization in Mobile, Ad-hoc and Wireless Networks (WiOpt 2023) for their paper on ‘Joint Optimization of Storage and Transmission via Coding Traffic Flows for Content Distribution.'”
-
Landherr wins Best ChemE Division Paper at Annual ASEE Conference
“Chemical engineering teaching professor and associate chair of undergraduate studies Luke Landherr was named to receive the Joseph J. Martin Award for the most outstanding Chemical Engineering Division paper presented at the 2023 ASEE Annual Conference. Their paper, entitled ‘Teaching Fugacity Through Comics and Assessing the Impact on Student Confidence and Understanding,’ is based on their research using comics as visual learning tools in undergraduate education.”
-
Studying axolotls to understand how limbs develop and regrow
“Mechanical and industrial engineering and bioengineering professor Sandra Shefelbine, in collaboration with biology professor James Monaghan, was awarded a $625,000 NSF grant for ‘In Vivo Mechanotransduction During Limb Growth’ to understand the mechanical signaling involved in limb growth. The researchers will use axolotls, a type of salamander that can regrow limbs, to study how cells sense and respond to mechanical forces. They believe that this research could lead to new insights into how limbs develop and regenerate.”
-
Patent received for ‘molecularly-imprinted electrochemical sensors’ to better detect disease
Researchers in the College of Engineering have received a patent for “Molecularly-Imprinted Electrochemical Sensors.” These sensors are “useful for detecting volatile organic compounds associated with certain diseases or conditions and/or diagnosing certain diseases or conditions.” They are constructed from “layers of metal on a layer of silicon, and a layer of molecularly imprinted polymer in electrical communication with the … metal. … Methods of using the devices (e.g., to detect one or more analytes in a sample, to detect and/or diagnose a disease or condition in a subject), and methods of making the devices are also provided” in the patent.
-
Watch along with the Intellectual Property Awareness Summit
The Intellectual Property Awareness Summit, which “is a gathering of IP owners, creators, educators, lawyers, organizations and investors” took place on May 2nd “in conjunction with Northeastern University’s Center for Research Innovation.” It brought together individuals who shared “a common goal – to explore ways to make the benefits of IP rights, and the issues surrounding them, more apparent to people and society.” You can watch recordings of the summit’s panels and keynote address at YouTube.
-
Berent investigates ‘how the physical body gives rise to subjective experience’
“Consciousness presents a “hard problem” to scholars. At stake is how the physical body gives rise to subjective experience. Why consciousness is “hard”, however, is uncertain. One possibility is that the challenge arises from ontology—because consciousness is a special property/substance that is irreducible to the physical. Here, I show how the “hard problem” emerges from two intuitive biases that lie deep within human psychology: Essentialism and Dualism. To determine whether a subjective experience is transformative, people judge whether the experience pertains to one’s essence, and per Essentialism, one’s essence lies within one’s body.”
-
‘Fear-Related Psychophysiological Patterns Are Situation and Individual Dependent: A Bayesian model Comparison Approach’
“Is there a universal mapping of physiology to emotion, or do these mappings vary substantially by person or situation? Psychologists, philosophers, and neuroscientists have debated this question for decades. Most previous studies have focused on differentiating emotions on the basis of accompanying autonomic responses using analytical approaches that often assume within-category homogeneity. In the present study, we took an alternative approach to this question. We determined the extent to which the relationship between subjective experience and autonomic reactivity generalizes across, or depends upon, the individual and situation for instances of … fear.” Find the paper and full list of authors…
-
“Persisters represent a small subpopulation of cells that are tolerant of killing by antibiotics and are implicated in the recalcitrance of chronic infections to antibiotic therapy. One general theme has emerged regarding persisters formed by different bacterial species, namely, a state of relative dormancy characterized by diminished activity of antibiotic targets. Within this framework, a number of studies have linked persister formation to stochastic decreases in energy-generating components. … In this study, we screen knockouts in the main global regulators of Escherichia coli for their effect on persisters.” Find the paper and full list of authors at mBio.
-
Clark provides ‘A Generative AI Teaching Exercise for Marketing Classes’
Associate professor of marketing Bruce Clark has provided another perspective on the use of AI in the classroom. While some teachers and instructors might try to ban the tool, Clark “decided to run a couple of experiments.” After teaching with AI, Clark notes that students came away “recognizing its limitations.” Clark also suggests other potential class sessions, experiments and methodologies instructors might try with their students, while everyone adapts to how widespread this technology has become.
-
‘Collective Intelligence in Human-AI Teams: A Bayesian Theory of Mind Approach’
“We develop a network of Bayesian agents that collectively model the mental states of teammates from the observed communication. Using a generative computational approach to cognition, we make two contributions. First, we show that our agent could generate interventions that improve the collective intelligence of a human-AI team beyond what humans alone would achieve. Second, we develop a real-time measure of human’s theory of mind ability and test theories about human cognition.” Find the paper and full list of authors in the Proceedings of the AAAI Conference on Artificial Intelligence.
-
‘From Ensemble Clustering to Subspace Clustering: Cluster Structure Encoding’
“In this study, we propose a novel algorithm to encode the cluster structure by incorporating ensemble clustering (EC) into subspace clustering (SC). First, the low-rank representation (LRR) is learned from a higher order data relationship induced by ensemble K-means coding, which exploits the cluster structure in a co-association matrix of basic partitions (i.e., clustering results). Second, to provide a fast predictive coding mechanism, an encoding function parameterized by neural networks is introduced to predict the LRR derived from partitions.” Find the paper and full list of authors at IEEE Transactions on Neural Networks and Learning Systems.
-
‘Transforming Complex Problems Into K-Means Solutions’
“K-means is a fundamental clustering algorithm widely used in both academic and industrial applications. … Studies show the equivalence of K-means to principal component analysis, non-negative matrix factorization, and spectral clustering. However, these studies focus on standard K-means with squared euclidean distance. In this review paper, we unify the available approaches in generalizing K-means to solve challenging and complex problems. We show that these generalizations can be seen from four aspects: data representation, distance measure, label assignment and centroid updating.” Find the paper and full list of authors at IEEE Transactions on Pattern Analysis and Machine Intelligence.
-
‘GlueGen: Plug and Play Multi-Modal Encoders for X-to-Image Generation’
“Text-to-image (T2I) models based on diffusion processes have achieved remarkable success in controllable image generation using user-provided captions. However, the tight coupling between the current text encoder and image decoder in T2I models makes it challenging to replace or upgrade. Such changes often require massive fine-tuning or even training from scratch with the prohibitive expense. To address this problem, we propose GlueGen, which applies a newly proposed GlueNet model to align features from single-modal or multi-modal encoders with the latent space of an existing T2I model.” Find the paper and full list of authors at ArXiv.
-
‘Sturgeon-MKIII: Simultaneous Level and Example Playthrough Generation via Constraint Satisfaction With Tile Rewrite Rules’
“Completability is a key aspect of procedural level generation. In this work, we present a constraint-based approach to level generation for 2D tile-based games that simultaneously generates a level and an example playthrough of the level demonstrating its completability. … The mechanics are represented as constraints in the same problem along with the constraints used to generate the level itself. … We demonstrate the flexibilty of the system and of tile rewrite rules in several applications, including lock-and-key dungeons, platformers, puzzles and match-three style games.”
-
‘An Online Therapeutic Intervention for Veterans Patients Suffering With Chronic Pain’
“Chronic pain affects a large proportion of veterans. … However, opioid-based medication can lead to overuse or misuse. Thus, the Veteran’s Health Administration (VHA) is interested in non-pharmacological approaches that target both pain management and chronic pain-related functional issues. … This manuscript describes a project to develop and evaluate Veteran ACT for Chronic Pain (VACT-CP), an online therapy conducted by an embodied conversational agent (ECA) portraying a mental healthcare coach tasked to lessen the effects of chronic pain and improve functioning.” Find the paper and list of authors in IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and…
-
‘Continuously Accelerating Research’ through reproducible software for scientists
“Science is facing a software reproducibility crisis. Software powers experimentation, and fuels insights, yielding new scientific contributions. Yet, the research software is often difficult for other researchers to reproducibly run. … As software engineering researchers, we believe that it is our duty to create tools and processes that instill reproducibility, reusability and extensibility into research software. This paper outlines a vision for a community infrastructure that will bring the benefits of continuous integration to scientists developing research software.” Find the paper and full list of authors in the IEEE/ACM International Conference on Software Engineering proceedings.
-
‘Edge Grasp Network: A Graph-Based SE(3)-Invariant Approach to Grasp Detection’
“Given point cloud input, the problem of 6-DoF grasp pose detection is to identify a set of hand poses in SE(3) from which an object can be successfully grasped. This important problem has many practical applications. Here we propose a novel method and neural network model that enables better grasp success rates relative to what is available in the literature. The method takes standard point cloud data as input and works well with single-view point clouds observed from arbitrary viewing directions.” Find the paper and full list of authors in the IEEE International Conference on Robotics and Automation proceedings.