VideoFDB is a new benchmark and LM-as-judge framework for evaluating full-duplex audio-visual-to-audio-visual conversational agents on nonverbal dynamics from real video calls.
Canonical reference
The stability-plasticity dilemma: investigating the continuum from catastrophic forgetting to age-limited learning effects.Fron- tiers in Psychology, V olume 4 - 2013, 2013
Canonical reference. 80% of citing Pith papers cite this work as background.
17
Pith papers citing it
Background
80% of classified citations
citation-role summary
background 5
citation-polarity summary
roles
background 5representative citing papers
DARE-EEG is a self-supervised EEG foundation model that enforces mask-invariance via contrastive mask alignment and momentum anchor alignment, plus conv-linear-probing for heterogeneous setups, achieving SOTA accuracy and cross-dataset portability.
Developers using AI showed the same core problem-solving behaviors as those without but differed in how they became stuck and recovered, with AI helping or hindering in specific cases.
AI-authored goals produce higher SMART quality scores but lower psychological ownership, commitment, importance, and goal-directed behavior than self-authored goals, with ownership as the mediating mechanism.
Eye contact norms create three recurring access barriers for visually impaired people in mixed-ability groups, reframing accessible design as support for explicit interaction contracts instead of gaze visibility.
Information defined as maximum-caliber deviation derives IIT 3.0 cause-effect repertoires from constrained entropy maximization and equates to prediction error under CLT and LDT.
People reject cookie + $2 offers from robots more than cookie alone due to inferred phantom costs, accepting more from robots than humans overall with no embodiment effect for robots.
Exploratory experience produces more spatially organized and transition-preserving predictive representations in maze navigation for both agents and mice.
Self-generated replay from language models nearly eliminates catastrophic forgetting during finetuning except when models are pretrained close to saturation.
Online posts by early childhood educators focus more on workplace demands than resources, with fear as the leading emotion and higher sadness and anger in demand-related posts.
Active inference model unifies human collision avoidance by reproducing meta-analysis aggregates and simulator-specific effects on response timing, maneuver selection, and execution.
A literature survey that categorizes high-level abstract concept image classification tasks in CV into semantic clusters and identifies persistent challenges and opportunities for hybrid AI approaches.
Response-time propensities estimated from tutoring logs are stable within students and predict learning efficiency conditionally on proficiency and practice stage.
LLMs accelerate research workflows from idea generation to writing but introduce challenges like hallucination, bias, opacity, and ten systemic risks requiring new governance frameworks.
Exploratory study reports measurable differences in emotion and immersion from systematic changes to frequency, dynamics, and directionality in film audio mixes.
The work introduces a visualization framework that turns imperceptible micro-expressions into perceptible cues and outlines a planned pilot study to test effects on empathic experience.
A review of 22 studies identifies five clusters of factors affecting autonomy and agency in HRI while noting limited and fragmented evidence.
citing papers explorer
-
VideoFDB: Evaluating Full-Duplex Vision-Speech Capabilities in Conversational Agents
VideoFDB is a new benchmark and LM-as-judge framework for evaluating full-duplex audio-visual-to-audio-visual conversational agents on nonverbal dynamics from real video calls.
-
DARE-EEG: A Foundation Model for Mining Dual-Aligned Representation of EEG
DARE-EEG is a self-supervised EEG foundation model that enforces mask-invariance via contrastive mask alignment and momentum anchor alignment, plus conv-linear-probing for heterogeneous setups, achieving SOTA accuracy and cross-dataset portability.
-
ChatGPT: Friend or Foe When Comprehending and Changing Unfamiliar Code
Developers using AI showed the same core problem-solving behaviors as those without but differed in how they became stuck and recovered, with AI helping or hindering in specific cases.
-
Optimized but Unowned: How AI-Authored Goals Undermine the Motivation They Are Meant to Drive
AI-authored goals produce higher SMART quality scores but lower psychological ownership, commitment, importance, and goal-directed behavior than self-authored goals, with ownership as the mediating mechanism.
-
The Ambivalent Experience of Eye Contact for People with Visual Impairments: Mechanisms and Design Challenges
Eye contact norms create three recurring access barriers for visually impaired people in mixed-ability groups, reframing accessible design as support for explicit interaction contracts instead of gaze visibility.
-
Information as Maximum-Caliber Deviation: A bridge between Integrated Information Theory and the Free Energy Principle
Information defined as maximum-caliber deviation derives IIT 3.0 cause-effect repertoires from constrained entropy maximization and equates to prediction error under CLT and LDT.
-
Too good to be true: People reject free gifts from robots because they infer bad intentions
People reject cookie + $2 offers from robots more than cookie alone due to inferred phantom costs, accepting more from robots than humans overall with no embodiment effect for robots.
-
Exploratory Experience Shapes the Geometry of Predictive Representations
Exploratory experience produces more spatially organized and transition-preserving predictive representations in maze navigation for both agents and mice.
-
Forgetting in Language Models: Capacity, Optimization, and Self-Generated Replay
Self-generated replay from language models nearly eliminates catastrophic forgetting during finetuning except when models are pretrained close to saturation.
-
Workplace Demands and Emotional Expression Among Early Childhood Educators: A Computational Analysis of Professional Online Discourse
Online posts by early childhood educators focus more on workplace demands than resources, with fear as the leading emotion and higher sadness and anger in demand-related posts.
-
Active inference as a unified model of collision avoidance behavior in human drivers
Active inference model unifies human collision avoidance by reproducing meta-analysis aggregates and simulator-specific effects on response timing, maneuver selection, and execution.
-
Seeing the Intangible: Survey of Image Classification into High-Level and Abstract Categories
A literature survey that categorizes high-level abstract concept image classification tasks in CV into semantic clusters and identifies persistent challenges and opportunities for hybrid AI approaches.
-
Understanding Student Effort Using Response-Time Propensities During Problem Solving
Response-time propensities estimated from tutoring logs are stable within students and predict learning efficiency conditionally on proficiency and practice stage.
-
From Text to Discovery: How Large Language Models Are Accelerating and Complicating Research Across Scientific and Humanistic Disciplines
LLMs accelerate research workflows from idea generation to writing but introduce challenges like hallucination, bias, opacity, and ten systemic risks requiring new governance frameworks.
-
EMORSION: Examining the Impact of Audio Parameters on Emotional Responses and Immersion in Film
Exploratory study reports measurable differences in emotion and immersion from systematic changes to frequency, dynamics, and directionality in film audio mixes.
-
Making the Invisible Visible: Toward Micro-Expression Visualization for Empathy in Social Interaction
The work introduces a visualization framework that turns imperceptible micro-expressions into perceptible cues and outlines a planned pilot study to test effects on empathic experience.
-
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.