Tag
YouTube Music is introducing AI-powered features like 'Ask Music' for conversational music discovery and 'Your Podcast Lineup' for personalized podcast recommendations, announced at the Made On YouTube event.
This exploratory pilot study evaluates personal information output from conversational interactions in generative AI systems, finding limited impact from model design differences and suggesting inferred profiles are constructed from contextual information.
WZRD is an AI-native platform that transforms documents, slides, forms, and sheets into interactive, conversational experiences, allowing users to engage with content through speaking or typing.
Reeno is an AI-powered product that randomly calls users for short speaking practice sessions to help integrate language learning into daily routines.
Describes a conversational AI system that uses Typesafe's Jev non-generative model to select from pre-written responses through parallel classification and scoring, providing a cost-effective and transparent alternative to generative LLMs.
Laya is an open-source non-autoregressive decision model that provides typed answers with calibrated probabilities, designed for tasks like email triage and conversational AI, showing significant performance improvements over existing models.
The paper proposes JustMem, a system that adapts memory access for long-term conversations by balancing discovery breadth and reading fidelity, achieving higher accuracy with fewer tokens.
The paper proposes a frontend-backend architecture for enabling tool calls in full-duplex speech models, where a speech frontend delegates to a text-based LLM backend for tool invocation, maintaining low-latency and natural interaction.
This paper proposes an Intent-Driven Query Suggestion Framework with dual-stage optimization to improve generative query suggestion by enhancing intent coverage and assigning credit at the query level, demonstrating improvements in click-through rate and intent coverage through experiments on production data.
Muse, an AI agent, now features an iPhone action button shortcut for automatic voice transcription, allowing users to engage in seamless multi-message conversations.
Gricea is an open-science platform for conversational AI research that enables configurable and deployable research artifacts to support replication, extension, and cumulative knowledge building.
The author discusses a common bias in AI agent development where conversational tone is prioritized over message efficiency, advocating for hybrid models that minimize turns per resolution.
This paper presents a confidence-gated hybrid system for emotion recognition in conversational AI that routes most traffic through a low-cost ensemble and escalates uncertain cases to an LLM, achieving high accuracy while reducing costs and latency for CCaaS platforms.
The paper introduces a bilingual, multi-turn framework to study AI assistants' responses to repeated verbal abuse, distinguishing between hard disengagement and soft withdrawal, and presents experimental results with various API configurations showing heterogeneous behaviors.
The article discusses benchmarking LLMs and inference clouds for YC's conversational AI, highlighting GLM-5.2 on Wafer as the top performer in head-to-head tests.
Critique of Qwen 3.8 model's conversational output, noting it produces nonsensical sentences while being optimized for coding and agentic usage.
ThinkFlow is a novel end-to-end latent memory framework for lifelong conversational agents that uses probabilistic vectors to overcome textual memory bottlenecks. It enables autonomous personalization through self-evolution and test-time learning, outperforming existing memory systems.
This paper analyzes user-AI mistreatment in conversational systems by auditing LMSYS-Chat-1M conversations, revealing distinct patterns in hostility detection and its implications for AI safety and alignment.
The tweet highlights VoiceArena's evaluation method for voice models, which separates Task Completion and Naturalness via blind pairwise voting, and announces Jarvis Bench v0.5 as a conversational agent benchmark.
Convo is an AI copilot designed for salespeople to assist during live conversations by handling objections, identifying buying signals, and providing instant answers from company knowledge. It also captures risks and follow-ups post-call to ensure deals move forward.