SimPersona induces a discrete buyer-type space from clickstreams via VQ-VAE, maps types to LLM persona tokens, fine-tunes agents on traces, and samples from merchant distributions to achieve 78% conversion-rate alignment on 42 held-out storefronts.
Canonical reference
Like Having a Really Bad PA
Canonical reference. 80% of citing Pith papers cite this work as background.
8
Pith papers citing it
21
external citations · Crossref
Background
80% of classified citations
citation-role summary
background 4
other 1
citation-polarity summary
representative citing papers
StateScribe uses a dual-layer memory architecture for episodic scenes and object-centric changes to deliver live and historical descriptions, achieving 83.1% F1 accuracy across revisits in evaluations and user studies with BLV participants.
Intent Lenses infer capture-time user intent from photos via LLMs to create dynamic, reusable interactive objects that generate and organize structured visual notes for later sensemaking.
Physical keyboards can be remapped in VR for new input/output behaviors, with nine applications shown usable in a 20-participant study.
OOPrompt reifies user intents into structured manipulable artifacts to enable modular and iterative prompting in LLM-based interactive systems.
Blur increases movement time and errors in target pointing tasks, accurately modeled by an improved Fitts' law, with per-user target size adjustment mitigating the effect.
AI integration in newsrooms drives internal deferral of judgment to LLMs and external shifts of power to platforms, making fairness, accountability, and transparency harder to sustain unless participatory mechanisms redistribute authority.
Smart glasses expand independent visual access for BLV participants in mixed-vision groups, supporting inclusive collaboration while sighted participants express uncertainty about adapting their helping behaviors.
citing papers explorer
-
SimPersona: Learning Discrete Buyer Personas from Raw Clickstreams for Grounded E-Commerce Agents
SimPersona induces a discrete buyer-type space from clickstreams via VQ-VAE, maps types to LLM persona tokens, fine-tunes agents on traces, and samples from merchant distributions to achieve 78% conversion-rate alignment on 42 held-out storefronts.
-
StateScribe: Towards Accessible Change Awareness Across Real-World Revisits
StateScribe uses a dual-layer memory architecture for episodic scenes and object-centric changes to deliver live and historical descriptions, achieving 83.1% F1 accuracy across revisits in evaluations and user studies with BLV participants.
-
Intent Lenses: Inferring Capture-Time Intent to Transform Opportunistic Photo Captures into Structured Visual Notes
Intent Lenses infer capture-time user intent from photos via LLMs to create dynamic, reusable interactive objects that generate and organize structured visual notes for later sensemaking.
-
ReconViguRation: Reconfiguring Physical Keyboards in Virtual Reality
Physical keyboards can be remapped in VR for new input/output behaviors, with nine applications shown usable in a 20-participant study.
-
OOPrompt: Reifying Intents into Structured Artifacts for Modular and Iterative Prompting
OOPrompt reifies user intents into structured manipulable artifacts to enable modular and iterative prompting in LLM-based interactive systems.
-
Blur Effects on User Performance in Target-Pointing Tasks
Blur increases movement time and errors in target pointing tasks, accurately modeled by an improved Fitts' law, with per-user target size adjustment mitigating the effect.
-
FAccT-Checked: A Narrative Review of Authority Reconfigurations and Retention in AI-Mediated Journalism
AI integration in newsrooms drives internal deferral of judgment to LLMs and external shifts of power to platforms, making fairness, accountability, and transparency harder to sustain unless participatory mechanisms redistribute authority.
-
Reshaping Inclusive Interpersonal Dynamics through Smart Glasses in Mixed-Vision Social Activities
Smart glasses expand independent visual access for BLV participants in mixed-vision groups, supporting inclusive collaboration while sighted participants express uncertainty about adapting their helping behaviors.