Title
Topic
-
‘Towards Automated Pain Assessment Using Embodied Conversational Agents’
“Narrative accounts are the ultimate authoritative source for pain assessment, and face-to-face encounters provide a rich context in which nonverbal conversational behavior can be used to enrich the detail in these descriptions. Embodied Conversational Agents—animated characters that simulate face-to-face conversation—can provide a medium for automated pain assessment in which multimodal pain narratives are elicited, clarified and grounded. … We describe work towards a conversational agent that elicits various aspects of a pain experience, followed by an empathic summary.” Find the paper and full list of authors in the Companion Publication of the 25th International Conference on Multimodal Interaction.
-
‘Improving Multiparty Interactions With a Robot Using Large Language Models’
“Speaker diarization is a key component of systems that support multiparty interactions of co-located users, such as meeting facilitation robots. The goal is to identify who spoke what, often to provide feedback, moderate participation, and personalize responses by the robot. … We leverage large language models (LLMs) to identify speaker labels from transcribed text and observe an exact match of 77% and a word level accuracy of 90%.” Find the paper and full list of authors in the Extended Abstracts of the 2023 CHI Conference on Human Factors in Computing Systems.
-
‘Sublinear Time Algorithms and Complexity of Approximate Maximum Matching’
“Sublinear time algorithms for approximating maximum matching size have long been studied. Much of the progress over the last two decades on this problem has been on the algorithmic side. … A more recent algorithm by [Behnezhad, Roghani, Rubinstein, and Saberi; SODA’23] obtains a slightly-better-than-1/2 approximation in O(n1+є) time (for arbitrarily small constant ε>0). … Proving any super-linear in n lower bound, even for (1−є)-approximations, has remained elusive. … In this paper, we prove the first super-linear in n lower bound for this problem.” Find the paper and authors list in the Proceedings of the 55th Annual ACM Symposium on…
-
‘Persistent Memory Research in the Post-Optane Era’
“After over a decade of researcher anticipation for the arrival of persistent memory (PMem), the first shipments of 3D XPoint-based Intel Optane Memory in 2019 were quickly followed by its cancellation in 2022. Was this another case of an idea quickly fading from future to past tense, relegating work in this area to the graveyard of failed technologies? … Without persistent memory itself, is future PMem research doomed? We offer two arguments for why reports of the death of PMem research are greatly exaggerated.” Find the paper and authors list in the Proceedings of the 1st Workshop on Disruptive Memory…
-
‘The Digital-Safety Risks of Financial Technologies for Survivors of Intimate Partner Violence’
“Digital technologies play a growing role in exacerbating financial abuse for survivors of intimate partner violence (IPV). … Scant research has examined how consumer-facing financial technologies can facilitate or obstruct IPV-related attacks on a survivor’s financial well-being. … We simulated both close-range and remote attacks commonly used by IPV adversaries. We discover that mobile banking and peer-to-peer payment applications are generally ill-equipped to deal with user-interface bound (UI-bound) adversaries, permitting unauthorized access to logins, surreptitious surveillance and harassing messages and system prompts.” Find the paper and full list of authors in the 32nd USENIX Security Symposium proceedings.
-
‘Discovering Informative and Robust Positives for Video Domain Adaptation’
Unsupervised domain adaptation for video recognition is challenging where the domain shift includes both spatial variations and temporal dynamics. Previous works have focused on exploring contrastive learning for cross-domain alignment. However, limited variations in intra-domain positives, false cross-domain positives, and false negatives hinder contrastive learning from fulfilling intra-domain discrimination and cross-domain closeness. This paper presents a non-contrastive learning framework without relying on negative samples for unsupervised video domain adaptation.” Find the paper and full list of authors at ICLR 2023.
-
‘HammerDodger: A Lightweight Defense Framework Against RowHammer Attack on DNNs’
“RowHammer attacks have become a serious security problem on deep neural networks (DNNs). Some carefully induced bit-flips degrade the prediction accuracy of DNN models to random guesses. This work proposes a lightweight defense framework that detects and mitigates adversarial bit-flip attacks. We employ a dynamic channel-shuffling obfuscation scheme to present moving targets to the attack, and develop a logits-based model integrity monitor with negligible performance loss.” Find the paper and full list of authors in the 2023 60th ACM/IEEE Design Automation Conference.
-
‘ICML 2023 Topological Deep Learning Challenge : Design and Results’
“This paper presents the computational challenge on topological deep learning that was hosted within the ICML 2023 Workshop on Topology and Geometry in Machine Learning. The competition asked participants to provide open-source implementations of topological neural networks from the literature by contributing to the python packages TopoNetX (data processing) and TopoModelX (deep learning). The challenge attracted twenty-eight qualifying submissions in its two-month duration. This paper describes the design of the challenge and summarizes its main findings.” Find the paper and full list of authors at ArXiv.
-
Panel discussion for CSCW ’23: ‘Getting Data for CSCW Research’
“This panel will bring together a group of scholars from diverse methodological backgrounds to discuss critical aspects of data collection for CSCW research. This discussion will consider the rapidly evolving ethical, practical, and data access challenges, examine the solutions our community is currently deploying and envision how to ensure vibrant CSCW research going forward.” Find the full list of panelists in the Companion Publication of the 2023 Conference on Computer Supported Cooperative Work and Social Computing.
-
‘An Example of (Too Much) Hyper-Parameter Tuning in Suicide Ideation Detection’
“This work starts with the TWISCO baseline, a benchmark of suicide-related content from Twitter. We find that hyper-parameter tuning can improve this baseline by 9%. We examined 576 combinations of hyper-parameters: learning rate, batch size, epochs and date range of training data. Reasonable settings of learning rate and batch size produce better results than poor settings.” Find the paper and full list of authors in the Proceedings of the International AAAI Conference on Web and Social Media.
-
‘Predicting GPU Failures With High Precision Under Deep Learning Workloads’
“Graphics processing units (GPUs) are the de facto standard for processing deep learning (DL) tasks. In large-scale GPU clusters, GPU failures are inevitable and may cause severe consequences. For example, GPU failures disrupt distributed training, crash inference services, and result in service level agreement violations. In this paper, we study the problem of predicting GPU failures using machine learning (ML) models to mitigate their damages.” Find the paper and full list of authors in the Proceedings of the 16th ACM International Conference on Systems and Storage.
-
‘NNSmith: Generating Diverse and Valid Test Cases for Deep Learning Compilers’
“Deep-learning (DL) compilers such as TVM and TensorRT are increasingly being used to optimize deep neural network (DNN) models to meet performance, resource utilization and other requirements. Bugs in these compilers can result in models whose semantics differ from the original ones, producing incorrect results that corrupt the correctness of downstream applications. … In this work, we propose a new fuzz testing approach for finding bugs in deep-learning compilers.” Find the paper and full list of authors at in the Proceedings of the 28th ACM International Conference on Architectural Support for Programming Languages and Operating Systems.
-
‘Semantic Encapsulation Using Linking Types’
“Interoperability pervades nearly all mainstream language implementations, as most systems leverage subcomponents written in different languages. And yet, such linking can expose a language to foreign behaviors that are internally inexpressible, which poses a serious threat to safety invariants and programmer reasoning. … In this paper, we outline an approach that encapsulates foreign code in a sound way — i.e., without disturbing the invariants promised by types of the core language.” Find the paper and full list of authors in the Proceedings of the 8th ACM SIGPLAN International Workshop on Type-Driven Development.
-
‘A Hybrid Partitioning Strategy for Backward Reachability of Neural Feedback Loops’
“As neural networks become more integrated into the systems that we depend on for transportation, medicine and security, it becomes increasingly important that we develop methods to analyze their behavior to ensure that they are safe to use within these contexts. The methods used in this paper seek to certify safety for closed-loop systems with neural network controllers, i.e., neural feedback loops, using backward reachability analysis.” Find the paper and full list of authors in the American Control Conference proceedings.
-
‘RAMP: A Risk-Aware Mapping and Planning Pipeline for Fast Off-Road Ground Robot Navigation’
“A key challenge in fast ground robot navigation in 3D terrain is balancing robot speed and safety. Recent work has shown that 2.5D maps (2D representations with additional 3D information) are ideal for real-time safe and fast planning. However, the prevalent approach of generating 2D occupancy grids through raytracing makes the generated map unsafe to plan in. … The RAMP pipeline proposed here solves these issues using new mapping and planning methods.” Find the paper and full list of authors at the IEEE International Conference on Robotics and Automation.
-
‘Re-trainable Procedural Level Generation via Machine Learning (RT-PLGML) as Game Mechanic’
“We present re-trainable procedural level generation via machine learning (RT-PLGML), a game mechanic of providing in-game training examples for a PLGML system. We discuss opportunities and challenges, along with concept RT-PLGML games.” Find the paper and full list of authors at Proceedings of the 18th International Conference on the Foundations of Digital Games
-
‘Solder: Retrofitting Legacy Code with Cross-Language Patches’
“Internet-of-things devices are widely deployed, and suffer from easy-to-exploit security issues. … Because patch deployments tend to be focused on server-side vulnerabilities, client software in large codebases such as Apache may remain largely unpatched, and hence, vulnerable. … In this paper, we address this issue of leaving latent vulnerabilities in legacy codebases. We propose Solder, a framework to patch or retrofit legacy C/C++ code by replacing any target function with a newly-implemented one in a safe language such as Rust.” Find the paper and full list of authors in the International Conference on Software Analysis, Evolution and Reengineering proceedings.
-
‘On Regularity Lemma and Barriers in Streaming and Dynamic Matching’
“We present a new approach for finding matchings in dense graphs by building on Szemerédi’s celebrated Regularity Lemma. This allows us to obtain non-trivial albeit slight improvements over longstanding bounds for matchings in streaming and dynamic graphs.” Find the paper and full list of authors in the Proceedings of the 55th Annual ACM Symposium on Theory of Computing.
-
‘SEIL: Simulation-Augmented Equivariant Imitation Learning’
“In robotic manipulation … traditional image-level data augmentation has shown the potential to improve sample efficiency in various machine learning tasks. However, image-level data augmentation is insufficient for an imitation learning agent to learn good manipulation policies in a reasonable amount of demonstrations. We propose Simulation-augmented Equivariant Imitation Learning (SEIL), a method that combines a novel data augmentation strategy of supplementing expert trajectories with simulated transitions and an equivariant model that exploits the O(2) symmetry in robotic manipulation.” Find the paper and full list of authors at the IEEE International Conference on Robotics and Automation proceedings.
-
‘SNAP: Efficient Extraction of Private Properties with Poisoning’
“Property inference attacks allow an adversary to extract global properties of the training dataset from a machine learning model. … Several existing approaches for property inference attacks against deep neural networks have been proposed, but they all rely on the attacker training a large number of shadow models. … We consider the setting of property inference attacks in which the attacker can poison a subset of the training dataset and query the trained target model.” Find the paper and full list of authors at the IEEE Symposium on Security and Privacy proceedings.
-
‘Layout Representation Learning With Spatial and Structural Hierarchies’
“We present a novel hierarchical modeling method for layout representation learning, the core of design documents (e.g., user interface, poster, template). Existing works on layout representation often ignore element hierarchies, which is an important facet of layouts, and mainly rely on the spatial bounding boxes for feature extraction. This paper proposes a Spatial-Structural Hierarchical Auto-Encoder (SSH-AE) that learns hierarchical representation by treating a hierarchically annotated layout as a tree format.” Find the paper and full list of authors at the Proceedings of the AAAI Conference on Artificial Intelligence.
-
‘Improving Cross-Domain Detection with Self-Supervised Learning’
“Cross-Domain Detection (XDD) aims to train a domain-adaptive object detector using unlabeled images from a target domain and labeled images from a source domain. Existing approaches achieve this either by transferring the style of source images to that of target images, or by aligning the features of images from the two domains. In this paper, rather than proposing another method following the existing lines, we introduce a new framework complementary to existing methods.” Find the paper and full list of authors in the IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops.
-
‘Trainability Preserving Neural Pruning’
“Many recent works have shown trainability plays a central role in neural network pruning — unattended broken trainability can lead to severe under-performance and unintentionally amplify the effect of retraining learning rate, resulting in biased (or even misinterpreted) benchmark results. This paper introduces trainability preserving pruning (TPP), a scalable method to preserve network trainability against pruning, aiming for improved pruning performance and being more robust to retraining hyper-parameters (e.g., learning rate).” Find the paper and full list of authors at Open Review. Published at ICLR 2023.
-
‘Sharing Speaker Heart Rate With the Audience Elicits Empathy and Increases Persuasion’
“Persuasion is a primary goal of public speaking, and eliciting audience empathy increases persuasion. In this research, we explore sharing a speaker’s heart rate as a social cue, to elicit empathy and increase persuasion in the audience. In particular, we developed two interfaces embedding the speaker’s heart rate over a recorded presentation video. … We observed that heart rate sharing significantly increased persuasion for participants with normal baseline empathy levels and increased empathic accuracy for all participants.” Find the paper and full list of authors in the journal of the International Conference on Persuasive Technology.
-
‘Sturgeon-GRAPH: Constrained Graph Generation From Examples’
“Procedural level generation techniques that learn local neighborhoods from example levels (such as WaveFunctionCollapse) have risen in popularity. Usually the neighborhood structure (such as a regular grid) onto which a level is generated is fixed in advance and not generated. In this work, we present a constraint-based approach for graph generation that learns local neighborhood patterns (in the form of labeled nodes and edges) from example graphs. This allows the approach to generate graphs with varying structures that are still locally similar to the examples.”
-
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.”
-
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.
-
‘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.