· ai
[Paper] Spoken Conversational Agents with Large Language Models
Spoken conversational agents are converging toward voice-native LLMs. This tutorial distills the path from cascaded ASR/NLU to end-to-end, retrieval-and vision-...
-
- · ai
[Paper] PaperDebugger: A Plugin-Based Multi-Agent System for In-Editor Academic Writing, Review, and Editing
Large language models are increasingly embedded into academic writing workflows, yet existing assistants remain external to the editor, preventing deep interact...
- · devops
[Paper] Solutions for Distributed Memory Access Mechanism on HPC Clusters
Paper presents and evaluates various mechanisms for remote access to memory in distributed systems based on two distinct HPC clusters. We are comparing solution...
- · ai
[Paper] Efficient Eye-based Emotion Recognition via Neural Architecture Search of Time-to-First-Spike-Coded Spiking Neural Networks
Eye-based emotion recognition enables eyewear devices to perceive users' emotional states and support emotion-aware interaction, yet deploying such functionalit...
- · ai
[Paper] The brain-AI convergence: Predictive and generative world models for general-purpose computation
Recent advances in general-purpose AI systems with attention-based transformers offer a potential window into how the neocortex and cerebellum, despite their re...
- · ai
[Paper] Associative Memory using Attribute-Specific Neuron Groups-1: Learning between Multiple Cue Balls
In this paper, we present a new neural network model based on attribute-specific representations (e.g., color, shape, size), a classic example of associative me...
- · devops
[Paper] DOLMA: A Data Object Level Memory Disaggregation Framework for HPC Applications
Memory disaggregation is promising to scale memory capacity and improves utilization in HPC systems. However, the performance overhead of accessing remote memor...
- · devops
[Paper] Fantasy: Efficient Large-scale Vector Search on GPU Clusters with GPUDirect Async
Vector similarity search has become a critical component in AI-driven applications such as large language models (LLMs). To achieve high recall and low latency,...
- · ai
[Paper] Sampling on Metric Graphs
Metric graphs are structures obtained by associating edges in a standard graph with segments of the real line and gluing these segments at the vertices of the g...
- · ai
[Paper] Feature Selection Empowered BERT for Detection of Hate Speech with Vocabulary Augmentation
Abusive speech on social media poses a persistent and evolving challenge, driven by the continuous emergence of novel slang and obfuscated terms designed to cir...
- · ai
[Paper] EfficientFlow: Efficient Equivariant Flow Policy Learning for Embodied AI
Generative modeling has recently shown remarkable promise for visuomotor policy learning, enabling flexible and expressive control across diverse embodied AI ta...
- · ai
[Paper] A Diffusion Model Framework for Maximum Entropy Reinforcement Learning
Diffusion models have achieved remarkable success in data-driven learning and in sampling from complex, unnormalized target distributions. Building on this prog...