Page 33 - Paper Library - AiPaper

This paper surveys Computational Meme Understanding (CMU), introducing a comprehensive meme taxonomy and analyzing key tasks like classification and interpretation, while reviewing existing datasets and models, addressing limitations, key challenges, and suggesting future researc

UniWorld-V1: High-Resolution Semantic Encoders for Unified Visual Understanding and Generation

Published:6/3/2025

Unified Visual Understanding and Generation ModelHigh-Resolution Semantic EncodersContrastive Semantic Encoding-Based Generative FrameworkImage Understanding and GenerationMultimodal Large Language Model

UniWorldV1 is an innovative generative framework that integrates highresolution semantic encoders for visual understanding and generation, achieving impressive performance across tasks using only 2.7M training data.

ImgEdit: A Unified Image Editing Dataset and Benchmark

Published:5/27/2025

ImgEdit DatasetImage Editing BenchmarkVision-Language Model ApplicationComplex Image Editing TasksMulti-Turn Editing Evaluation

The paper introduces , a dataset of 1.2 million curated edit pairs for image editing, addressing the lack of quality data and benchmarks. It trains the model and presents , demonstrating superior performance across tasks.

AnyKey: A Key-Value SSD for All Workload Types

Published:2/6/2025

Universal Key-Value SSDKey-Value Store ApplicationsMetadata OptimizationSolid-State Drive Performance EvaluationDiverse Workload Types

AnyKey, a novel KVSSD design, addresses performance issues in existing systems under workloads with larger keys by optimizing metadata size. It outperforms stateoftheart KVSSD designs across various workload types.

Enhancing Embedding Representation Stability in Recommendation Systems with Semantic ID

Published:4/3/2025

Semantic ID Embedding in Recommendation SystemsEnhanced Stability of Embedding RepresentationsTail ID Modeling OptimizationContent-Based ID ClusteringIntegration of Attention Models

This paper introduces Semantic ID prefix ngram, a novel token parameterization technique that enhances embedding stability in recommendation systems by hierarchically clustering items based on their content, addressing key challenges like data pollution and performance degradatio

Enzyme specificity prediction using cross-attention graph neural networks

Published:10/8/2025

Cross-Attention Graph Neural NetworksEnzyme Specificity PredictionSE(3)-Equivariant Graph Neural NetworkEnzyme-Substrate Interaction DatabaseHigh-Precision Enzyme-Substrate Recognition

The paper presents , a crossattention graph neural network for predicting enzyme substrate specificity, achieving 91.7% accuracy in identifying reactive substrates, significantly outperforming existing models and enhancing applications in biocatalysis and drug dis

111

Analysis of effects to scientific impact indicators based on the coevolution of coauthorship and citation networks

Published:4/19/2024

Co-evolution of Coauthorship and Citation NetworksAnalysis of Scientific Impact IndicatorsJournal Impact Factor and H-indexPreferential Attachment ModelingScientometrics Simulation Method

This study establishes a model for coauthorship and citation networks to explore their effects on scientific impact indicators. It finds that increasing references or reducing paper lifespan boosts journal impact factor and hindex, highlighting the dynamic nature of these indica

Freezing-based Memory and Process Co-design for User Experience on Resource-limited Mobile Devices

Published:1/18/2025

User Experience Optimization on Resource-Limited Mobile DevicesMemory and Process Co-managementApplication Freezing MechanismLRU List OptimizationPerformance Enhancement for Mobile Devices

The framework proposed in this study enhances user experience on resourcelimited mobile devices by integrating memory and process management. It identifies and freezes background processes that cause frequent refaults, boosting performance and increasing frame rates by 1.5

SSEmb: A joint embedding of protein sequence and structure enables robust variant effect predictions

Published:11/7/2024

Sequence-Structure Embedding ModelVariant Effect PredictionGraph Representation of Protein StructureTransformer Model for Sequence AlignmentProtein-Protein Binding Site Prediction

The study introduces SSEmb, a method integrating protein sequence and structure for robust variant effect predictions, particularly effective with limited sequence data, and applicable in tasks like predicting proteinprotein binding sites.

InterPLM: Discovering Interpretable Features in Protein Language Models via Sparse Autoencoders

Published:11/13/2024

Feature Extraction in Protein Language ModelsApplication of Sparse AutoencodersInterpretable Protein BiologyHuman-Interpretable Latent FeaturesAnalysis of ESM-2 Model

This paper introduces a method using sparse autoencoders to extract interpretable features from protein language models, revealing up to 2,548 features correlated with 143 biological concepts, and demonstrating applications in database annotation and targeted protein generation.

010

SCALING LARGE LANGUAGE MODELS FOR NEXT-GENERATION SINGLE-CELL ANALYSIS

Published:4/17/2025

Large Language Model Fine-TuningSingle-Cell RNA SequencingCell Text ModelingBiological Information SynthesisMulticellular Context Reasoning

This study introduces a novel approach using the Cell2Sentence framework to convert singlecell RNA sequencing data into textual 'cell sentences,' training large language models on over a billion tokens. Scaling to 27 billion parameters resulted in enhanced performance in multice

RaC: Robot Learning for Long-Horizon Tasks by Scaling Recovery and Correction

Published:9/10/2025

Robot Learning for Long-Horizon TasksHuman-in-the-Loop Recovery and CorrectionRobotic Policy Fine-TuningBimanual Control TasksEfficiency and Robustness Enhancement

The paper introduces , a method that enhances robot learning for longhorizon tasks by scaling recovery and correction behaviors, finetuning robotic policies through human interventions, thus improving efficiency and robustness in complex tasks.

ShiDianNao: Shifting Vision Processing Closer to the Sensor

Image Application-Specific Neural Network AcceleratorOptimization of Convolutional Neural NetworksNear-Sensor Architecture DesignHigh-Efficiency Neural Network Accelerator65nm Layout Design

The ShiDianNao CNN accelerator is placed next to CMOS or CCD sensors to eliminate DRAM accesses, achieving 60x energy efficiency improvement and 30x faster performance than highend GPUs, with a compact design of 4.86mm² area and 320mW power consumption.

INT v.s. FP: A Comprehensive Study of Fine-Grained Low-bit Quantization Formats

Published:10/29/2025

Low-bit Quantization FormatsFine-grained Quantization ComparisonFloating-point and Integer QuantizationAI Hardware OptimizationFine-grained INT Training

This study offers a systematic comparison between floatingpoint (FP) and integer (INT) quantization formats, revealing that MXINT8 outperforms FP in 8bit finegrained formats. For 4bit formats, FP often excels, but NVINT4 can surpass it with outliermitigation techniques. A ne

A genome-to-proteome map reveals how natural variants drive proteome diversity and shape fitness

Published:10/9/2025

Genome-to-Proteome MappingNatural Variation and Proteome DiversityImpact of Natural Genetic VariantsYeast Strain Genetic StudyGenotype-Phenotype Relationship Study

This study presents a nucleotideresolution genometoproteome map, revealing how natural genetic variants drive proteome diversity and enhance fitness. Analyzing meiotic progeny from yeast strains highlights the interplay of small variations and selection mechanisms, underlining

DaDianNao: A Machine-Learning Supercomputer

Published:12/1/2014

Machine-Learning SupercomputerConvolutional Neural Network AcceleratorDeep Neural Network ArchitectureMulti-Chip System DesignHigh-Performance Computing Optimization

DaDianNao is a machinelearning supercomputer optimized for CNNs and DNNs, demonstrating a 450.65x speedup and 150.31x energy reduction compared to GPUs, effectively addressing the high computational and memory demands of machine learning.

Physics-Based Dexterous Manipulations with Estimated Hand Poses and Residual Reinforcement Learning

Published:8/7/2020

Residual Reinforcement Learning and Imitation Learning3D Hand Pose Estimation and Physics SimulationDexterous Manipulation in Virtual EnvironmentsGesture-Based Object InteractionPhysics-Guided Target Pose Remapping

This study presents a residual reinforcement learning approach that enables agents to perform dexterous manipulation in virtual environments by mapping estimated hand poses to target poses, effectively overcoming the challenges of absent physical feedback.

DreamControl: Human-Inspired Whole-Body Humanoid Control for Scene Interaction via Guided Diffusion

Published:9/18/2025

Diffusion Model-Based Robot ControlWhole-Body Humanoid Action LearningHuman Motion Data-Guided Reinforcement LearningSim-to-Real Motion TransferTask Execution on Unitree G1 Robot

DreamControl introduces a novel method for learning wholebody skills in humanoid robots by combining diffusion models and reinforcement learning, enabling complex tasks and facilitating simtoreal transfer.

Omnigrasp: Grasping Diverse Objects with Simulated Humanoids

Published:7/16/2024

Grasp Control with Simulated HumanoidsGrasping and Moving Diverse ObjectsHumanoid Motion Representation LearningTraining without Paired DatasetObject Trajectory Following Task

Omnigrasp is a method for controlling simulated humanoids to grasp and manipulate over 1200 diverse objects along predefined trajectories. It enhances control accuracy through humanoid motion representation, requiring no paired training data and demonstrating excellent scalabilit

Stable-Predictive Optimistic Counterfactual Regret Minimization

Published:2/14/2019

Counterfactual Regret MinimizationStable-Predictive Regret MinimizationLarge-Scale Game SolvingConvergence Rate OptimizationStability in Decision Trees

This paper introduces a new CFR variant achieving

O(T^{3/4})

convergence rate for largescale extensiveform games. By combining advances in predictive and stable regret minimization, the concept of 'stablepredictivity' enhances algorithm performance beyond traditional CFR.

641 - 660 / 980

Papers