arXiv AI
Parametric Multimodal User Memory: Storing What Captions Cannot Carry
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Jul 1
Surprise as a Signal for Plasticity and Metacognition
arXiv:2606. 31495v1 Announce Type: new Abstract: We study a single idea across two settings: that a prediction-error signal, computed by a small predictor over the latent space of a frozen encoder, can serve both as a gate on plasticity and as a substrate for metacognition.
arXiv Computation and Language
Sep 15
Where Should Language Sit in a Multimodal Model? Lessons from What Language Does to Human Perception and Cognition
arXiv:2609.07474v2 Announce Type: replace Abstract: Language models compute over tokens: language is their input, their output, and increasingly their internal representation. Whether language should...
arXiv AI
Jun 29
DMV-Bench: Diagnosing Long-Horizon Multimodal Agents' Visual Memory with Incidental Cue Injection
arXiv:2606. 27499v1 Announce Type: cross Abstract: Research on agent memory has matured rapidly, but almost entirely on the text side: few existing benchmarks ask, in an interactive environment, when an agent genuinely needs to remember what it saw rather than what it could write down.
arXiv Computer Vision
Sep 7
ICM-Bench: Person-Level Identity Reasoning in Multimodal Agents with Long-Term Memory
ICM-Bench is a new benchmark for evaluating identity-centric reasoning in multimodal agents with long-term memory. It consists of 839 synthetic video clips totaling 141 minutes and 1,217 open-ended questions about six recurring adults in a one-year life album. The benchmark isolates the ability to maintain recurring person identities and reason over their cross-time relations, and compares various baseline systems, showing that while Gemini 3.1 Pro performs well overall, its accuracy drops on questions requiring long-term identity profiles.
arXiv Computation and Language
1d ago
GAVAGAI: Referential Alignment for Infant-Scale Vision-Language Models via Balanced Optimal Transport
The paper introduces GAVAGAI, a method that adds a referential alignment variable to vision‑language models by solving a small assignment problem via entropic optimal transport. By allowing words to be assigned to a special NOTHING column and enforcing a capacity constraint on regions, the approach improves word‑to‑picture accuracy and localization on the SAYCam infant video corpus. Experiments show that the alignment loss boosts performance over a standard next‑token captioning baseline, especially under high non‑reference rates.
arXiv AI
Aug 21
Beyond Recall: Behavioral Specification as an Interpretive Layer for AI Personalization
arXiv:2605. 28969v2 Announce Type: replace-cross Abstract: If an AI agent makes decisions on a person's behalf, those decisions must align with its user.