Publications
Our teams aspire to make discoveries that impact everyone, and core to our approach is sharing our research and tools to fuel progress in the field.
Our teams aspire to make discoveries that impact everyone, and core to our approach is sharing our research and tools to fuel progress in the field.
Sort By
1 - 15 of 11377 publications
GUIDE: A Benchmark for User Context Understanding and Assistance in GUI Workflow Videos
Saelyne Yang
Jaesang Yu
Yi-Hao Peng
Kevin Qinghong Lin
Jae Won Cho
Juho Kim
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2026)
Preview abstract
Graphical User Interface (GUI) agents have the potential to assist users in interacting with complex software. While prior research has primarily focused on automating user actions through clicks and keystrokes, this paradigm overlooks human intention, where users value the ability to explore, iterate, and refine their ideas while maintaining agency.To move beyond automation and toward collaboration, GUI agents must understand what users are doing and why. We introduce GUIDE (GUI Understanding, Intent, and Help Decision Evaluation), a benchmark that evaluates AI models on their ability to perceive user behavior, infer intent, and provide assistance in open-ended GUI tasks. GUIDE consists of 67.5 hours of screen recordings from 120 novice user demonstrations with think-aloud narrations that surface user intent, across 10 complex software (e.g., PowerPoint, Photoshop). GUIDE defines three tasks—(i) Behavior State Detection, (ii) Intent Prediction, and (iii) Help Prediction that test a model’s ability to recognize behavior state, reason about goals, and decide when and how to help. Evaluations across eight state-of-the-art multimodal models reveal that all models struggled with the tasks, achieving only 44.6% and 55.0% accuracy on behavior state and help prediction. However, providing user context such as behavioral state and intent significantly improved the performance, raising help prediction by up to 50.2%. These results highlight the critical role of structured user understanding in effective assistance.Our benchmark provides a path toward GUI agents that go beyond automation to become truly user-aware collaborators.
View details
Preview abstract
We introduce AASE (Activation-based AI Safety Enforcement), a framework for post-perception safety monitoring in large language models. Unlike pre-perception approaches that analyze input or output text, AASE monitors the model's internal activation patterns—what the model "understands" rather than what text it processes or generates—enabling detection of safety-relevant states before harmful outputs are produced. The framework comprises three techniques: Activation Fingerprinting (AF) for harmful content detection, Agent Action Gating (AAG) for prompt injection defense, and Activation Policy Compliance (APC) for enterprise policy enforcement. We introduce paired contrastive training to isolate safety-relevant signals from confounding factors such as topic and style, addressing signal entanglement in polysemantic activations. Validation across 7 models from 3 architecture families shows strong class separation: Gemma-2-9B achieves AUC 1.00 with 7.2σ separation across all probes; AAG achieves AUC ≥0.88 across all models on the InjecAgent benchmark; APC achieves 0.97-1.00 AUC across three enterprise policies. Model size correlates with probe quality—Gemma-2-9B (7.2σ separation) outperforms Gemma-2-2B (4.3σ). All techniques survive INT4 quantization with minimal separation degradation. AASE is 9× faster than Llama Guard 3 (33ms vs 306ms) with higher TPR (88% vs 50%) at a tunable threshold that trades FPR for detection sensitivity, adding only 0.002ms probe overhead to existing inference.
View details
Agentic AI Infrastructure in Practice: Learn These Key Hurdles to Deploy Production AI Agents Efficiently
https://swisscognitive.ch/ (2026)
Preview abstract
The emergence of Agentic AI—autonomous systems capable of reasoning, decision-making, and multi-step execution—represents a paradigm shift in enterprise technology. Moving beyond simple generative tasks, these agents offer the potential to solve long-standing industry pain points, with over 90% of enterprises planning integration within the next three years. However, the transition from successful proof-of-concept (PoC) to a resilient, production-grade system presents significant hurdles.
This article categorizes these challenges into three primary domains:
Technical and Engineering Hurdles: Issues such as "entangled workflows" that complicate debugging, the struggle to maintain output quality and mitigate hallucinations, and the unpredictability caused by shifting underlying models or data sources.
People, Process, and Ecosystem Hurdles: The high operational costs and unclear ROI of large models, the necessity of a new "Agent Ops" skillset, the complexity of integrating agents with disparate enterprise systems, and a rapidly evolving regulatory landscape.
The Pace of Change and Security risks: The technical debt incurred by shifting software frameworks and the expanded attack surface created by autonomous agents.
The article concludes that successful deployment requires a shift from informal "vibe-testing" to rigorous engineering discipline. By adopting code-first frameworks, establishing robust evaluation metrics (KPIs), and prioritizing functional deployment over theoretical optimization, organizations can effectively manage the lifecycle of Agentic AI and realize its transformative business value.
View details
VeriGuard: Enhancing LLM Agent Safety via Verified Code Generation
Dj Dvijotham
Mirko Montanari
ACL 2026
Preview abstract
Artificial intelligence is rapidly evolving, marked by the emergence of Large Language Model (LLM) agents – systems capable of complex reasoning, planning, and interaction with digital and physical environments. These agents, powered by advancements in LLMs, demonstrate remarkable capabilities across diverse domains, including finance, healthcare, web navigation, software development, and daily task assistance. Unlike traditional AI systems, LLM agents can perceive their surroundings, formulate multi-step plans, utilize external tools and APIs, access memory or knowledge bases, and execute actions to achieve specified goals. This ability to act upon the world, however, introduces significant safety and security challenges.
The safety paradigms developed for traditional LLMs, primarily focused on mitigating harmful textual outputs (e.g., toxicity, bias), are insufficient for safeguarding LLM agents. Agents interacting with dynamic environments and executing actions present a broader attack surface and new categories of risk. These include performing unsafe operations, violating privacy constraints through improper data handling or access control failures, deviating from user objectives (task misalignment), and susceptibility to novel manipulation techniques like indirect prompt injection and memory poisoning. Ensuring the trustworthy operation of these powerful agents is paramount, especially as they are integrated into high-stakes applications. To address this critical challenge, we introduce VeriGuard, a novel framework designed to enhance the safety and reliability of LLM agents by interactively verifying their policies and the actions. VeriGuard integrates a verification module that intercepts code-based actions proposed by the agent. In the first step, VeriGuard will generates and verifies the policies. The policies are rigorously checked against a set of predefined safety and security specifications Then each action will be verified to make sure it will align with the agent specification. This interactive verification loop ensures that the agent's behavior remains within safe operational bounds, effectively preventing the execution of harmful or unintended operations. By verifying each step, VeriGuard provides a robust safeguard, substantially improving the trustworthiness of LLM agents in complex, real-world environments.
View details
Preview abstract
Existing image simplification techniques often rely on Non-Photorealistic Rendering (NPR), transforming photographs into stylized sketches, cartoons, or paintings. While effective at reducing visual complexity, such approaches typically sacrifice photographic realism. In this work, we explore a complementary direction: simplifying images while preserving their photorealistic appearance.
We introduce progressive semantic image simplification, a framework that iteratively reduces scene complexity by removing and inpainting elements in a controlled manner. At each step, the resulting image remains a plausible natural photograph. Our method combines semantic understanding with generative editing, leveraging Vision-Language Models (VLMs) to identify and prioritize elements for removal, and a learned verifier to ensure photorealism and coherence throughout the process. This is implemented via an iterative \emph{Select–Remove–Verify} pipeline that produces high-quality simplification trajectories.
To improve efficiency, we further distill this process into an image-to-video generation model that directly predicts coherent simplification sequences from a single input image. Beyond generating cleaner and more focused compositions, our approach enables applications such as content-aware decluttering, semantic layer decomposition, and interactive editing.
More broadly, our work suggests that simplification through structured content removal can serve as a practical mechanism for guiding visual interpretation within the photorealistic domain, complementing traditional abstraction methods.
View details
Mining Attribute Subspaces for Efficient Fine-tuning of 3D Foundation Models
Yu Jiang
Hanwen Jiang
Vincent Chu
Brandon Y. Feng
Zhangyang Wang
Qixing Huang
IEEE/CVF Conference on Computer Vision and Pattern Recognition (2026)
Preview abstract
With the emergence of 3D foundation models, there is growing interest in fine-tuning them for downstream tasks, where LoRA is the dominant fine-tuning paradigm. As 3D datasets exhibit distinct variations in texture, geometry, camera motion, and lighting, there are interesting fundamental questions: 1) Are there LoRA subspaces associated with each type of variation? 2) Are these subspaces disentangled (i.e., orthogonal to each other)? 3) How do we compute them effectively? This paper provides answers to all these questions. We introduce a robust approach that generates synthetic datasets with controlled variations, fine-tunes a LoRA adapter on each dataset, and extracts a LoRA sub-space associated with each type of variation. We show that these subspaces are approximately disentangled. Integrating them leads to a reduced LoRA subspace that enables efficient LoRA fine-tuning with improved prediction accuracy for downstream tasks. In particular, we show that such a reduced LoRA subspace, despite being derived entirely from synthetic data, generalizes to real datasets. An ablation study validates the effectiveness of the choices in our approach.
View details
Preview abstract
While non-verbal behaviors and expressive movements are essential for natural human-robot interaction, existing methods often overlook a crucial element: the human’s internal cognitive state. Consequently, proactive multi-agent systems frequently interrupt humans at inopportune moments, leading to cognitive overload and decreased task performance. This paper introduces a framework for generating “cognitively aligned” multi-agent interactions, enhancing the ability of robotic systems to contextually defer communications during moments of high human mental workload. We present the design and implementation of a closed-loop architecture that explores the interplay between autonomous task execution and real-time neurophysiological focus. Utilizing a consumer-grade Brain-Computer Interface (BCI), our approach continuously monitors Electroencephalography (EEG) spectral band powers while a human performs a cognitive-load-inducing task. We propose a workload-driven pipeline where an HTTP-based signaling mechanism places a primary agent’s sensory inputs and audio outputs into a holding state upon detecting high cognitive load. This allows secondary agents to seamlessly process complex, delegated tasks in the background. Once the human’s cognitive state returns to a baseline, the primary agent releases the queued agent message. Our preliminary results demonstrate the feasibility of leveraging real-time signal processing, Large Language Models (LLMs), and physical robotic embodiments to create interrupt-aware, non-intrusive multi-agent systems.
View details
MoXaRt: Audio-Visual Object-Guided Sound Interaction for XR
Sieun Kim
Qianhui Zheng
Ruoyu Xu
Ravi Tejasvi
Anuva Kulkarni
Junyi Zhu
2026
Preview abstract
In Extended Reality (XR), complex acoustic environments often overwhelm users, compromising both scene awareness and social engagement due to entangled sound sources. We introduce MoXaRt, a real-time XR system that uses audio-visual cues to separate these sources and enable fine-grained sound interaction. MoXaRt's core is a cascaded architecture that performs coarse, audio-only separation in parallel with visual detection of sources (e.g. faces, instruments). These visual anchors then guide refinement networks to isolate individual sources, separating complex mixes of up to five concurrent sources (e.g. two voices + three instruments) with ca. 2 second processing latency. We validate MoXaRt through a technical evaluation on a new, complex dataset we collected, and a 22-participant user study. Our results demonstrate that MoXaRt significantly improves communication clarity—boosting listening comprehension in noisy conditions by 33.2% (p=0.0058)—and significantly reduces cognitive load (M=7.50 vs. M=3.36, p<0.001), paving the way for more perceptive and socially adept XR experiences.
View details
Nudging Developers Toward Privacy: Evaluating the Impact of Personalized App Review Reports
Omer Akgul
Michelle L. Mazurek
USENIX Symposium on Usable Privacy and Security (SOUPS) (2026)
Preview abstract
Mobile application developers often struggle to create accurate privacy notices or implement robust privacy practices due to limited expertise or resources. While users share unsolicited privacy feedback in app reviews, and prior research has characterized this privacy feedback, uncovering developer reactions to this feedback remains unexplored. This study explores whether personalized privacy review reports---summarizing real user feedback for a developer's own app---can effectively nudge them toward planning privacy improvements. We surveyed 42 app developers, presenting them with reports containing privacy themes, temporal trends, peer benchmarks, and emotion distributions derived from their apps' reviews. Our findings indicate that these privacy report interventions proved highly effective, with 76% (32 of 42) of participants finding at least one section of the report useful. Furthermore, exposure to the report increased the participants' intent to pursue privacy-relevant actions -- such as reorganizing the UI, enhancing privacy communications, or adding/removing features -- with 69% (29 of 42) of participants indicating an increased intent to do so. Almost all developers expressed a desire to receive such privacy reports periodically or on demand. These results indicate that making this style of report broadly available across the industry could foster a more privacy-conscious mobile ecosystem.
View details
Preview abstract
Large language models (LLMs) are trained on web-scale corpora that exhibit steep power-law distributions, in which the distribution of knowledge is highly long-tailed, with most appearing infrequently. While scaling has improved average-case performance, persistent failures on low-frequency, domain-specific, cultural, and temporal knowledge remain poorly characterized. This paper develops a structured taxonomy and analysis of long-tail knowledge in large language models, synthesizing prior work across technical and sociotechnical perspectives.
We organize the literature along four complementary axes: how long-tail knowledge is defined, the mechanisms by which it is lost or distorted during training and inference, the technical interventions proposed to mitigate these failures, and the implications of these failures for fairness, accountability, transparency, and user trust. We further examine how existing evaluation practices obscure tail behavior and complicate accountability for rare but consequential failures. The paper concludes by identifying open challenges related to privacy, sustainability, and governance that constrain long-tail knowledge representation. Taken together, this paper provides a unifying conceptual framework for understanding how long-tail knowledge is defined, lost, evaluated, and manifested in deployed language model systems.
View details
Preview abstract
In a prior column, we wrote about how measuring productivity can be viewed as a form of modeling and that all models are wrong, but some are useful. That discussion centered on the idea of ensuring that a productivity model was inclusive of multiple metrics and that those metrics covered the various facets of productivity and covered each facet reasonably well. In that article, we set aside the question of what makes a good individual productivity metric that can be combined with others into a (hopefully) useful model of productivity. In this article, we’ll share some things we consider when building an individual metric, including an example of a novel metric we built in the aftermath of the COVID pandemic.
View details
Preview abstract
Systems for escalating interactions from automated agents to human agents can create inefficiencies, for example, by transferring unstructured transcripts. An intermediary system can employ a generative artificial intelligence synthesis engine to process the context of an automated interaction upon an escalation trigger. The engine may analyze the dialogue transcript, user metadata, and the automated agent's internal state to perform semantic abstraction, diagnose potential failure points, and infer a possible resolution. The system can then generate a structured briefing for the human agent, which could include a concise summary, a failure diagnosis, or a recommended next action presented as an interactive element. This process may facilitate a more efficient handoff and contribute to an improved escalation workflow by providing the human agent with synthesized, contextual information.
View details
Preview abstract
This study examines the psychological and ethical implications of generative-AI chatbot use among youth, introducing the CTRL framework (Cognitive Trust, Reliance, and Learning Diminution) to explain how repeated use fosters cognitive offloading and reduced verification behavior. Survey data from 420 participants analyzed through factor analysis and structural equation modeling reveal that higher trust predicts greater reliance and diminished critical evaluation, alongside elevated concerns around privacy and academic integrity. Findings highlight the need for AI literacy and responsible design to mitigate unintended cognitive impacts.
View details
Preview abstract
Coding agents are rapidly changing the landscape of software development, moving from inline com- pletion to autonomous systems that edit repositories, open pull requests, respond to issues, and run scheduled or webhook triggered routines across the development life cycle. The next generation is increasingly described as proactive and long-horizon: agents should notice relevant changes before the developer asks, connect signals across tools, decide when to interrupt, and carry preferences across sessions. Yet the field lacks a precise account of what proactivity means for software development, how it differs from autonomy, what acceptance criteria proactive long-horizon tasks should satisfy, and which metrics determine whether unsolicited agent behavior is useful rather than merely active. We argue that proactive coding agents should be evaluated by the quality and improvement of their insight policy: the policy that decides what matters next, what evidence supports it, whether to surface it, and how to adapt after feedback. We re-anchor this view in mixed initiative interaction, introduce a three level taxonomy (Reactive, Scheduled, and Situation Aware), compare contemporary coding agents against five operational criteria, and sketch an active user simulation protocol with three evaluation targets: Insight Decision Quality (IDQ), Context Grounding Score (CGS), and Learning Lift (LL).
View details
