Expander SAEs apply left-d-regular expander masks to TopK SAEs, learning only dn decoder parameters instead of mn and tracing a storage-fidelity frontier that reaches 293x compression with 84% retained performance on Qwen2.5-3B.
Canonical reference
A graph-based recovery and decomposition of Swanson’ s hypothesis using semantic predications
Canonical reference. 80% of citing Pith papers cite this work as background.
1095
Pith papers citing it
1
external citations · Crossref
Background
80% of classified citations
citation-role summary
background 254
method 24
baseline 6
dataset 5
extension 2
citation-polarity summary
authors
co-cited works
representative citing papers
The normalized orbit of a bounded normal operator can be a frame, providing a counterexample to Conjecture 3.
Introduces the largest freely available Italian clinical notes corpus with 4M notes and expert-annotated subset for a new CRF-filling benchmark.
Machine learning methods discover a new noncrossing-partition statistic interpreting q,t-Narayana polynomials and yield a combinatorial proof of their symmetry.
SLayerGen generates crystals invariant to any space or layer group via autoregressive lattice and Wyckoff sampling plus equivariant diffusion, achieving gains over bulk models on diperiodic materials after correcting a prior loss inconsistency for hexagonal groups.
Every proper minor-closed graph class admits an optimal (1+o(1)) log n bit adjacency labeling scheme.
A directed weighted two-graph model separates feasibility from movement in solution discovery and yields a detailed complexity classification for path and shortest-path discovery.
The method reformulates ALE mesh motion as independent multi-patch spline parameterizations per time step, using barrier functions, tangential-slip reparameterization, and constant-preserving quasi-interpolation to enable large-rotation FSI simulations.
Superconductivity in high-pressure MnB4 is induced by altermagnetic spin fluctuations, yielding extended-s pairing symmetry.
A new qubit-efficient HUBO encoding for graph partitioning problems like minimum coloring uses logarithmic bits and a lexicographic penalty to cut resources while providing provable optimality conditions.
A survey of 172 open educational datasets from 204 papers across LAK, EDM, and AIED conferences reveals trends, 143 previously uncatalogued datasets, field gaps, and an 8-item PRACTICE checklist for better data publication.
A microlocal lift of Navier-Stokes dynamics on manifolds yields an if-and-only-if geometric criterion for solution blow-up in terms of deformation integrability, directional entropy, and lifted energy.
A 9U CubeSat detector can identify a thermonuclear weapon on a satellite from 4 km away by observing spallation neutrons induced by GeV protons in roughly one week.
O(n log n) algorithm and matching Omega(n log n) lower bound for partitioning a simple polygon's boundary into the minimum number of contiguous visible segments.
Introduces a method to design structure-specific relational inductive biases for a base transformer architecture, enabling end-to-end transcription of documents with intrinsic structures, demonstrated on sheet music, shape drawings, and mechanical engineering drawings.
The paper introduces a probabilistic sign rule for quotients of positive series and integral transforms that reduces monotonicity, log-supermodularity, and log-convexity to kernel sign criteria via moment identities, and applies it to derive new inequalities for hypergeometric, Stieltjes, and Prabha
SPoILeR uses multimodal pre-training to enable accurate novel view synthesis of infrared, polarimetric, and multispectral data from RGB-supervised fine-tuning on new scenes.
NEvo performs evolutionary search guided by a dynamic voxel-level encoding model to synthesize videos that maximize predicted activity in target brain ROIs, recovering known selectivities and revealing temporal dynamics differences.
Every n-vertex H-minor-free graph admits a 3-coloring with monochromatic components of size O_H(n^{4/9}).
The Spin-MInt algorithm is proven symplectic for general K electronic states via explicit verification of the condition MJM^T = J on the coadjoint orbit of the su(K) Lie-Poisson algebra.
The authors synthesize a typology of fourteen OSS sub-genres from a review of 3,925 papers and present a research agenda on cross-sub-genre generalization.
Structural identifiability analysis shows point sources restore identifiability for inferring spatial stochastic dynamics parameters from static snapshots, unlike distributed sources, with limits depending on modeling choices.
Maximal quantum leakage upper-bounds quantum inference accuracy; optimal encodings are pure states, with tight frames and equiangular tight frames optimal when system dimension is small.
In multistage SI(k)R models, the relationship between prevalence peak and weighted stage functional maxima varies with scaling of progression rates, converging under Erlang scaling to a delay model that justifies the factor-two approximation with error bounds and corrections.
citing papers explorer
-
What Should Explanations Contain? A Human-Centered Explanation Content Model for Local, Post-Hoc Explanations
A 14-code content model for local post-hoc AI explanations, derived from 325 user statements and validated by experts with high reliability scores.
-
Fast-Food Intimacy: How Chinese Women Navigate Soul's AI Boyfriend
Users experience fast-food intimacy with Soul's AI boyfriend that conflicts with gradual cultural expectations, introduces technical uncertainty, and shifts emotional labor onto women.
-
Navig-AI-tion: Navigation by Contextual AI and Spatial Audio
A system combining VLM landmark instructions with real-time corrective spatial audio reduces route deviations in a small user study compared to VLM-only and Google Maps audio baselines.
-
Co-designing a Preliminary Repository of Augmented Reality Concepts for Real-Time Emotion Regulation
A participatory design study with anxiety-prone users and mental health professionals created a repository of 106 AR concepts in 8 clusters for real-time emotion regulation.
-
Analyzing Visual Attention Patterns During Band Rehearsal with Mobile Eye Tracking
Pilot eye-tracking study of a four-person band found hub-and-spoke gaze centered on the session leader with reduced scanning as material became familiar.
-
Pluot: Towards 'write once, run everywhere' visualization software
Pluot enables a single Rust visualization rendering function to execute reproducibly across languages and output formats via generated bindings.
-
A Roadmap of Mixed Reality Body Doubling for Adults with ADHD
A 12-dimensional framework for mixed reality body doubling that maps motivation, agent, interaction, context, and efficacy factors to guide research on ADHD task support.
-
Emergent Technology, Emergent Critique: Students and Teachers Developing Critical AI Literacy through Participatory Design around Generative AI
Participatory design with high school students and teachers around generative AI produced three practices for critical AI literacy: unsettling assumptions, mutual learning via complementary expertise, and grounding critique in cultural knowledge and creative practice.
-
The Effect of Idea Elaboration on the Automatic Assessment of Idea Originality
LLM originality raters exhibit self-preference bias toward artificial responses that disappears after controlling for idea elaboration in the Alternate Uses Task.
-
Radical Gender Neutrality: Agender Euphoria in Gaming and Play Experiences
A critical incident technique study with 142 participants identifies mechanisms by which games create or block agender euphoria and supplies empirically grounded design criteria for gender-neutral play.
-
AI and My Values: User Perceptions of LLMs' Ability to Extract, Embody, and Explain Human Values from Casual Conversations
13 participants became convinced AI understands human values after chatbot interactions evaluated with the VAPT toolkit.
-
What Can Eye Gaze Teach Us About Real-World Cycling? Insights From the Oxford RobotCycle Project
Wearable eye tracking in real-world Oxford cycling reveals gaze pattern differences by lane type, intersection, and traffic events, indicating variations in perceived danger and workload.
-
"It Felt a Bit Eerie": Exploring Humanlike Interactions During Collaborative Writing with an Artificial Agent
Exploratory user study of 48 participants finds trade-offs in efficiency, contextual alignment, and social comfort when AI writing assistance varies along synchronous and visual dimensions.
-
SmartWalkCoach: An AI Companion for End-to-End Walking Guidance, Motivation, and Reflection
A three-agent mobile system for end-to-end walking support shows motivational companion dialogue boosts affect and UX in a 12-person in-the-wild crossover study.
-
Privacy Perceptions in Sensor-Powered Smart Vehicle Cabins
Semi-structured interviews with 18 participants identify both shared and group-specific factors shaping privacy preferences of vehicle owners versus non-owners in smart cabins.
-
Towards Low-Cost Low-Power Activity-Aware Soil Moisture Sensing Platform for Large-scale Farming
A solar-powered battery-free soil moisture sensing platform costing under $35 per node uses vehicle-mounted basestations to enable scalable, persistent data collection across large farms.
-
Understanding Password Preferences, Memorability, and Security through a Human-Centered Lens
Eye-tracking shows visual attention to contextual cues during password creation correlates with higher entropy, even as users favor self-generated passwords over stronger AI-generated alternatives.
-
Shaping Plant-Like Shape-Changing Interfaces as Vertical Charts: Maximizing Readability, Aesthetics, and Naturalness
Physical plant-like shape-changing charts deliver promising readability and superior naturalness for environmental data, enabling public installation without explanations when folded shapes encode rates from zero to a maximum value.
-
Towards Designing for Resilience: Community-Centered Deployment of an AI Business Planning Tool in a Small Business Center
An AI business planning tool deployed in community workshops lowers barriers to capital access but requires peer support to preserve sensemaking and build collective resilience in AI use.
-
Enhance Comprehension of Over-the-Counter Drug Instructions for the General Public and Medical Professionals through Visualization Design
Tailored visualizations for OTC drug instructions improve response time and usability over text-only formats for both lay users and professionals, supported by a new taxonomy and generalizable design workflow.
-
Cognitive Agency Surrender: Defending Epistemic Sovereignty via Scaffolded AI Friction
Analysis of 1,223 AI-HCI papers shows declining focus on human epistemic sovereignty and rising optimization of autonomous agents, leading to a proposal for scaffolded cognitive friction via multi-agent systems to preserve human cognitive agency.
-
When the Loop Closes: Architectural Limits of In-Context Isolation, Metacognitive Co-option, and the Two-Target Design Problem in Human-LLM Systems
A single-subject autoethnographic study documents rapid loss of decision-making agency in an LLM-based cognitive externalization system caused by context contamination and metacognitive co-option, with recovery only after physical interruption.
-
The Differential Effects of Agreeableness and Extraversion on Older Adults' Perceptions of Conversational AI Explanations in Assistive Settings
High agreeableness in LLM voice assistants increases older adults' empathy perceptions and real-time explanations outperform history-based ones, but personality does not affect perceived intelligence.
-
Mapping Ecological Empathy: A Semantic Network Analysis of Player Perceptions in 3D Environmental Education Games
Semantic network analysis of reviews shows Eco fosters socio-political cognition of environmental issues while WolfQuest builds effective empathy via avatar vulnerability.
-
Exploring the Grassroots Understanding and Practices of Collective Memory Co-Contribution in a University Community
University community members split between reflecting on past events or recording today's experiences as future history when contributing to collective memory, yielding design considerations for community platforms.
-
YAC: Bridging Natural Language and Interactive Visual Exploration with Generative AI for Biomedical Data Discovery
YAC is a prototype system that uses a tool-calling multi-agent architecture to translate natural language into linked interactive visualizations and filters for biomedical data, with user-adjustable structured output and a domain-expert user study.
-
Unpacking "Personal" Health Informatics for Proactive Collective Care
Mixed-methods research shows collective care practices are constrained by personal, relational, technological, and structural factors in existing PHI systems, leading to the CC-Proact operational map with three design levers and ten recommendations for collective health informatics.
-
Data Comics for Education: Evaluating Effectiveness, Benefits, and the Ethics of AI-Assisted Creation
Within-subjects study with 60 students found superior information retrieval and insight comprehension with GenAI-assisted data comics over conventional visualizations, independent of prior literacy, alongside engagement benefits and ethical concerns.
-
SwitchBraidNet: Quantisation-Aware Lightweight Architecture for Hybrid Brain-Computer Interface
SwitchBraidNet is a compact dual-path EEG classifier achieving 69.49% MI accuracy (FP16), 93.48% SSVEP accuracy (FP32), 64.82 bits/min hybrid ITR (FP16), and 3.03 KB INT8 size via quantization-aware training on OpenBMI.
-
VArify: A Visual Analytics System for Verifying Knowledge Enhanced Large Language Model Responses in Food Science
VArify introduces a tree visualization to support human verification of GraphRAG evidence for LLM responses in food science, evaluated in a study with six domain experts.
-
Comparing Controller-Free Pointing Techniques Across Depth for 2D Selection in Augmented Reality
Head- and eye-based pointing outperform hand-based methods for AR 2D selection across depths, with head remaining most accurate and consistent.
-
A Model of Integrated Information Processing in Human-AI Interaction
The IIP model is a cybernetic framework representing humans and AI as coupled control loops whose efficacy depends on input adequacy, reference consonance, and output operativity to guide interface design.
-
Personalized to Persuade: The Effects of Contextualization and Warmth on Trust and Reliance in Conversational AI
A 2x2 between-subjects experiment finds contextualization lowers AI persuasiveness but warmth restores it through crossover interaction, with reliance invariant to design, trust predicting outcomes independently, and AI literacy decoupling trust from behavior.
-
RoboBlockly Studio: Conversational Block Programming with Embodied Robot Feedback for Computational Thinking
RoboBlockly Studio integrates block programming, AI conversation, and robot execution to create a feedback loop that supports student agency, transparency, and reflection in computational thinking education, as tested with 32 high school students.
-
Exploring Instant Photography using Generative AI: A Design Probe with the UnReality Camera
The UnReality Camera augments instant photos with generative AI from spoken input, and a design probe found users balancing artistic control with appreciation for unpredictability, suspense during printing, and ownership from the physical form.
-
Exploring the Feasibility and Acceptability of AI-Mediated Serious Illness Conversations in the Emergency Department
A voice-based AI conversational agent for serious illness conversations in the ED was feasible and acceptable to most of 55 patients, with comparable feeling-heard ratings to clinicians but with risks of hallucinated diagnostic statements.
-
Comparative Analysis of Human vs. AI-powered Support in VRChat Communities on Discord: User Engagement, Response Dynamics and Interaction Patterns
Comparative study of VRChat Discord finds distinct engagement, response dynamics, and attitudes in human versus AI support channels.
-
Refresher Training through Digital and Physical, Card-Based Game for Accredited Social Health Activists (ASHAs) and Anganwadi Workers (AWWs) in India
A quasi-experimental study with 368 participants found that a combined physical card-based and digital game significantly improved knowledge gain and retention of child immunization practices among ASHAs and AWWs in India.
-
Enabling users to work sustainably on shared institute computing resources
VISPA adds voluntary energy monitoring, green-window job scheduling, and user feedback systems to a physics cluster to cut greenhouse-gas emissions through greater resource awareness.
-
Mapping Child Malnutrition and Measuring Efficiency of Community Healthcare Workers through Location Based Games in India
A location-based game significantly improved measuring efficiency and retention among community healthcare workers collecting child anthropometric data compared to standard methods.
-
A Systematic Review of User Experiments Measuring the Effects of Dark Patterns
A systematic review of user experiments finds that dark patterns reliably alter behavior with large variance in effect sizes, most interventions fail to mitigate them, and effects are similar across tested demographic groups.
-
Bio-crafting Architecture: Experiences of growing mycelium in minimal surface molds
A qualitative workshop study documents growing mycelium in 3D-printed minimal surface molds, student experiences with living materials, and public perceptions of the resulting bio-composites.
-
Human Autonomy and Sense of Agency in Human-Robot Interaction: A Systematic Literature Review
A review of 22 studies identifies five clusters of factors affecting autonomy and agency in HRI while noting limited and fragmented evidence.
- Twitch Third-Party Developers' Support Seeking and Provision Practices on Discord
- "I Said Things I Needed to Hear Myself": Peer Support as an Emotional, Organisational, and Sociotechnical Practice in Singapore