Page 35 - Paper Library - AiPaper

Distributed LLM Serving on Consumer-Grade GPUs by Reconciling Computation and Communication

Published:1/1/2025

Distributed LLM Serving on Consumer-Grade GPUsMoLink Serving SystemPrefill Request Transmission Scheduling AlgorithmCommunication Efficiency Optimization for LLMsDistributed Inference Computing Architecture

This paper presents MoLink, an efficient distributed LLM serving system that reduces costs using consumergrade GPUs. It splits the prefill request data into smaller chunks and optimizes transmission scheduling, achieving up to 46% reductions in firsttoken generation time, pert

Order-agnostic Identifier for Large Language Model-based Generative Recommendation

Published:2/15/2025

LLM-based Generative Recommendation SystemsOrder-Agnostic Identifier DesignIntegration of Collaborative Filtering and Semantic InformationSETRec FrameworkSparse Attention Mechanism

This paper presents an orderagnostic identifier design for LLMbased generative recommendations, addressing efficiency and performance issues. By integrating CF and semantic information using the SETRec framework, it significantly enhances recommendation effectiveness and genera

Comprehensive characterization and expression analysis of enzymatic antioxidant gene families in passion fruit (Passiflora edulis)

Published:10/26/2023

Identification of Antioxidant Enzyme Gene Families in Passion FrExpression Analysis of Antioxidant GenesCharacteristics of Antioxidant Enzyme Gene FamiliesTemperature Stress Resistance in Passion FruitSecondary Metabolite Research

This study identifies and characterizes 90 antioxidant genes in passion fruit, revealing phylogenetic links among similarly localized genes and their role in oxidative protection in flowers/fruits, while suggesting candidates for enhancing temperature stress resistance.

DexFlyWheel: A Scalable and Self-improving Data Generation Framework for Dexterous Manipulation

Published:9/28/2025

Data Generation for Dexterous ManipulationSelf-Improving Data Generation FrameworkImitation Learning and Reinforcement LearningData Diversity EnhancementIterative Cycle Data Generation

DexFlyWheel introduces a scalable and selfimproving data generation framework for dexterous manipulation, addressing the lack of diverse, highquality training datasets. Utilizing a closedloop pipeline with imitation learning, residual RL, and data augmentation, it iteratively

MoMaGen: Generating Demonstrations under Soft and Hard Constraints for Multi-Step Bimanual Mobile Manipulation

Published:10/21/2025

Multi-Step Bimanual Mobile Manipulation Demonstration GenerationImitation Learning for Robot TrainingConstraint-Based Optimization for Data GenerationAugmentation of Human Demonstration DatasetsReachability and Visibility Issues in Mobile Manipulation

MoMaGen introduces a method for generating demonstrations in multistep bimanual mobile manipulation, addressing the high cost of human data collection by solving base placement and visibility issues. The evaluation shows it greatly enhances dataset diversity compared to existing

ThinkAct: Vision-Language-Action Reasoning via Reinforced Visual Latent Planning

Published:7/23/2025

Vision-Language-Action ReasoningReinforced Visual Latent PlanningMultimodal Large Language ModelLong-Horizon PlanningRobotic Action Execution

ThinkAct proposes a dualsystem framework that connects highlevel reasoning and lowlevel action execution through reinforced visual latent planning, enabling fewshot adaptation, longhorizon planning, and selfcorrection in complex environments.

Breaking the Bottleneck: User-Specific Optimization and Real-Time Inference Integration for Sequential Recommendation

Published:8/3/2025

Sequential Recommender SystemsUser-Specific OptimizationReal-Time Inference IntegrationKL Divergence OptimizationDeep Learning Sequence Methods

This paper addresses performance bottlenecks in sequential recommendation by proposing userspecific optimization, analyzing each user's behavior independently, and integrating realtime inference to enhance efficiency and model stability, using KL divergence for individual seque

Robust deep learning–based protein sequence design using ProteinMPNN

Published:9/15/2022

Deep Learning-Based Protein Sequence DesignProteinMPNNProtein Structure PredictionExperimental Protein Design MethodsMulti-Chain Amino Acid Coupling

The study introduces ProteinMPNN, a deep learningbased protein sequence design method, achieving 52.4% sequence recovery, outperforming Rosetta's 32.9%. It can handle amino acid coupling in single and multichains, successfully rescuing previously failed protein designs, showcas

014

Generative Sparse-View Gaussian Splatting

Published:6/10/2025

Generative Sparse-View Gaussian Splatting3D/4D Scene ReconstructionImage Diffusion ModelsView Consistency EnhancementGenerative Models for Limited Observations

The paper presents Generative Sparseview Gaussian Splatting (GSGS) to enhance 3D/4D scene reconstruction under limited observations, leveraging pretrained image diffusion models to improve view consistency and rendering quality, outperforming existing stateoftheart methods.

Personalized Safety in LLMs: A Benchmark and A Planning-Based Agent Approach

Published:5/25/2025

Personalized Safety in Large Language ModelsPENGUIN BenchmarkUser-Context-Based Safety EnhancementRAISE Agent FrameworkSafety Evaluation Methods

This paper introduces personalized safety and presents the PENGUIN benchmark, showing a 43.2% safety score improvement from personalized user information. It also develops the RAISE framework, enhancing safety scores by 31.6% without the need for model retraining, highlighting th

014

探究老年糖尿病夜间低血糖的预防及护理

Elderly Diabetes CareHypoglycemia Prevention MeasuresNighttime Hypoglycemia ManagementDiabetes Clinical Treatment

The paper explores the causes and nursing measures for nocturnal hypoglycemia in elderly diabetics, highlighting their diminished awareness. It presents six causes and five preventive strategies to guide clinical practitioners.

Aligning LLMs with Individual Preferences via Interaction

Published:10/4/2024

LLM Personalized AlignmentMulti-Turn Preference LearningPersonalized User Behavior ModelingPersonalized Preference DatasetInteraction-Based LLM Fine-Tuning

This study introduces a method for aligning large language models (LLMs) with individual preferences through multiturn dialogues, using a diverse persona pool and a multiturn conversation dataset. The approach enhances model adaptability via supervised finetuning and reinforce

老年糖尿病患者夜间低血糖的识别与护理防范措施

Management of Nocturnal Hypoglycemia in Elderly Diabetic PatientHypoglycemia Identification and Care StrategiesBlood Glucose Monitoring and Individualized TreatmentNursing Interventions for Elderly Patients

This paper explores the characteristics and identification methods of nocturnal hypoglycemia in elderly diabetics. It finds that comprehensive nursing strategies can significantly reduce risks, highlighting the importance of a systematic approach to enhance patient quality of lif

Dynamic Discounted Counterfactual Regret Minimization (CFR) is a family of iterative algorithms showing promising results in solving imperfect-information games. Recent novel CFR variants (e.g., CFR+, DCFR) have significantly improved the convergence rate of the vanilla CFR. The key to these CFR variants’ performance is weighting each iteration non-uniformly, i.e., discounting earlier iterations. However, these algorithms use a fixed, manually-specified scheme to weight each iteration, which eno

Dynamic Discounted Counterfactual Regret MinimizationPolicy Optimization in Markov Decision ProcessesSolving Imperfect-Information GamesImproving Convergence of Iterative AlgorithmsDynamic Weight Learning

This paper introduces Dynamic Discounted CFR (DDCFR), the first framework to dynamically learn discounting for iterations. By formalizing the CFR process as a Markov decision process, DDCFR achieves faster convergence and high performance, significantly improving efficiency in so

STUDY OF HYPOGLYCEMIA IN ELDERLY DIABETES MELLITUS PATIENTS

Published:2/5/2022

Study of Hypoglycemia in Elderly Diabetes Mellitus PatientsDiabetes ManagementClinical PharmacologyHypoglycemic SymptomsUse of Sulphonylureas

This study examines hypoglycemia in elderly diabetic patients at Raja Muthiah Medical College, finding Glimipride as the most common sulphonylurea used, with over 30% of patients asymptomatic during hypoglycemic episodes, highlighting monitoring challenges.

EchoMind: An Interrelated Multi-level Benchmark for Evaluating Empathetic Speech Language Models

Published:10/26/2025

Empathetic Dialogue Evaluation BenchmarkEvaluation of Speech Language Model CapabilitiesSpoken Content Understanding and Non-Lexical CuesMulti-Level Dialogue Capability AssessmentEmotionally Intelligent Dialogue Systems

The paper introduces EchoMind, a multilevel benchmark to evaluate empathetic Speech Language Models (SLMs), integrating spoken content understanding, vocalcue perception, reasoning, and response generation. Findings indicate significant weaknesses in advanced models' empathic r

CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models

Published:12/16/2024

Streaming Speech SynthesisApplication of Large Language ModelsMultilingual DatasetOptimization of Speech Generation ModelsProgressive Semantic Decoding

CosyVoice 2 is an enhanced streaming speech synthesis model that optimizes token utilization with finitescalar quantization, simplifies the LM architecture using pretrained large language models, and employs chunkaware causal flow matching for humanlevel naturalness and virtu

5G Vehicle-to-Everything Services: Gearing Up for Security and Privacy

Published:11/13/2019

5G V2X Security and PrivacyVehicle-to-Everything Communication5G Network Services and ApplicationsVehicle Sensor NetworksLow Latency Communication

The paper provides a comprehensive review of security and privacy issues in 5G V2X services, analyzing architecture, use cases, and potential trust threats, while exploring recent protection strategies and highlighting future research directions to advance this field.

A Component Architecture for the Internet of Things

Published:9/1/2018

Component Architecture for Internet of ThingsConcurrent Time-Stamped Discrete-Event SemanticsAsynchronous Atomic Callbacks (AAC)Secure Swarm Toolkit (SST)Proxies and Services Interaction

This paper presents a componentbased architecture for IoT, featuring proxies called "accessors" that interact under concurrent, timestamped discreteevent semantics, leveraging asynchronous atomic callbacks (AAC) and the actor model to enhance efficiency and security.

UniMMVSR: A Unified Multi-Modal Framework for Cascaded Video Super-Resolution

Published:10/9/2025

Cascaded Video Super-ResolutionMultimodal Video GenerationLatent Video Diffusion ModelCondition Injection StrategiesMultimodal Condition Utilization

The paper introduces UniMMVSR, a unified framework for video superresolution that handles multiple input modalities. It explores condition injection strategies and demonstrates superior performance in detail and conformity to multimodal conditions, enabling 4K video generation.

681 - 700 / 993

Papers