Daily Arxiv

전 세계에서 발간되는 인공지능 관련 논문을 정리하는 페이지 입니다.
본 페이지는 Google Gemini를 활용해 요약 정리하며, 비영리로 운영 됩니다.
논문에 대한 저작권은 저자 및 해당 기관에 있으며, 공유 시 출처만 명기하면 됩니다.

M3DR: Towards Universal Multilingual Multimodal Document Retrieval

Physics-Driven Learning Framework for Tomographic Tactile Sensing

NAS-LoRA: Empowering Parameter-Efficient Fine-Tuning for Visual Foundation Models with Searchable Adaptation

Cell-cell communication inference and analysis: biological mechanisms, computational approaches, and future opportunities

ATHENA: Agentic Team for Hierarchical Evolutionary Numerical Algorithms

AsymPuzl: An Asymmetric Puzzle for multi-agent cooperation

Text-Printed Image: Bridging the Image-Text Modality Gap for Text-centric Training of Large Vision-Language Models

Learning From Limited Data and Feedback for Cell Culture Process Monitoring: A Comparative Study

Think Before You Drive: World Model-Inspired Multimodal Grounding for Autonomous Vehicles

GalaxyDiT: Efficient Video Generation with Guidance Alignment and Adaptive Proxy in Diffusion Transformers

Multi-Aspect Knowledge-Enhanced Medical Vision-Language Pretraining with Multi-Agent Data Generation

World Models for Autonomous Navigation of Terrestrial Robots from LIDAR Observations

BookRAG: A Hierarchical Structure-aware Index-based Approach for Retrieval-Augmented Generation on Complex Documents

Better World Models Can Lead to Better Post-Training Performance

VS-Graph: Scalable and Efficient Graph Classification Using Hyperdimensional Computing

UniQL: Unified Quantization and Low-rank Compression for Adaptive Edge LLMs

FireSentry: A Multi-Modal Spatio-temporal Benchmark Dataset for Fine-Grained Wildfire Spread Forecasting

HalluGen: Synthesizing Realistic and Controllable Hallucinations for Evaluating Image Restoration

Idea-Gated Transformers: Enforcing Semantic Coherence via Differentiable Vocabulary Pruning

ProtoEFNet: Dynamic Prototype Learning for Inherently Interpretable Ejection Fraction Estimation in Echocardiography

Single-Round Scalable Analytic Federated Learning

Cache What Lasts: Token Retention for Memory-Bounded KV Cache in LLMs

NavMapFusion: Diffusion-based Fusion of Navigation Maps for Online Vectorized HD Map Construction

Retrofitting Earth System Models with Cadence-Limited Neural Operator Updates

Robust Tabular Foundation Models

HydroDCM: Hydrological Domain-Conditioned Modulation for Cross-Reservoir Inflow Prediction

Adaptive Regime-Switching Forecasts with Distribution-Free Uncertainty: Deep Switching State-Space Models Meet Conformal Prediction

BlendedNet++: A Large-Scale Blended Wing Body Aerodynamics Dataset and Benchmark

Thucy: An LLM-based Multi-Agent System for Claim Verification across Relational Databases

PyroFocus: A Deep Learning Approach to Real-Time Wildfire Detection in Multispectral Remote Sensing Imagery

Learning Network Sheaves for AI-native Semantic Communication

SPARK: Stepwise Process-Aware Rewards for Reference-Free Reinforcement Learning

How to DP-fy Your Data: A Practical Guide to Generating Synthetic Data With Differential Privacy

InvertiTune: High-Quality Data Synthesis for Cost-Effective Single-Shot Text-to-Knowledge Graph Generation

Ultra-Strong Gradient Diffusion MRI with Self-Supervised Learning for Prostate Cancer Characterization

Plantain: Plan-Answer Interleaved Reasoning

Culture Affordance Atlas: Reconciling Object Diversity Through Functional Mapping

Atomic Diffusion Models for Small Molecule Structure Elucidation from NMR Spectra

Mitigating Intra- and Inter-modal Forgetting in Continual Learning of Unified Multimodal Models

Lost in Modality: Evaluating the Effectiveness of Text-Based Membership Inference Attacks on Large Multimodal Models

Beyond Additivity: Sparse Isotonic Shapley Regression toward Nonlinear Explainability

PanFoMa: A Lightweight Foundation Model and Benchmark for Pan-Cancer

The BEAT-CF Causal Model: A model for guiding the design of trials and observational analyses of cystic fibrosis exacerbations

E-valuator: Reliable Agent Verifiers with Sequential Hypothesis Testing

Public Sentiment Analysis of Traffic Management Policies in Knoxville: A Social Media Driven Study

Dynamic Correction of Erroneous State Estimates via Diffusion Bayesian Exploration

ALARM: Automated MLLM-Based Anomaly Detection in Complex-EnviRonment Monitoring with Uncertainty Quantification

Ensemble Privacy Defense for Knowledge-Intensive LLMs against Membership Inference Attacks

QGShap: Quantum Acceleration for Faithful GNN Explanations

Community Quality and Influence Maximization: An Empirical Study

Password-Activated Shutdown Protocols for Misaligned Frontier Agents

When Harmful Content Gets Camouflaged: Unveiling Perception Failure of LVLMs with CamHarmTI

Beyond Code Pairs: Dialogue-Based Data Generation for LLM Code Translation

Alleviating Choice Supportive Bias in LLM with Reasoning Dependency Generation

AtomDisc: An Atom-level Tokenizer that Boosts Molecular LLMs and Reveals Structure--Property Associations

Irresponsible AI: big tech's influence on AI research and associated impacts

Will Power Return to the Clouds? From Divine Authority to GenAI Authority

Economies of Open Intelligence: Tracing Power & Participation in the Model Ecosystem

PretopoMD: Pretopology-based Mixed Data Hierarchical Clustering

Mixed Data Clustering Survey and Challenges

Hierarchical clustering of complex energy systems using pretopology

Echoes of AI Harms: A Human-LLM Synergistic Framework for Bias-Driven Harm Anticipation

Quantifying the Potential to Escape Filter Bubbles: A Behavior-Aware Measure via Contrastive Simulation

Optimizing Life Sciences Agents in Real-Time using Reinforcement Learning

A note on the impossibility of conditional PAC-efficient reasoning in large language models

Delta Sampling: Data-Free Knowledge Transfer Across Diffusion Models

Physics-informed self-supervised learning for predictive modeling of coronary artery digital twins

Energy-Efficient Federated Learning via Adaptive Encoder Freezing for MRI-to-CT Conversion: A Green AI-Guided Research

Mitigating hallucinations and omissions in LLMs for invertible problems: An application to hardware logic design automation

Entropy-Based Measurement of Value Drift and Alignment Work in Large Language Models

AI-Driven Document Redaction in UK Public Authorities: Implementation Gaps, Regulatory Challenges, and the Human Oversight Imperative

Benchmark for Planning and Control with Large Language Model Agents: Blocksworld with Model Context Protocol

Autonomous Agents and Policy Compliance: A Framework for Reasoning About Penalties

A Hierarchical Tree-based approach for creating Configurable and Static Deep Research Agent (Static-DRA)

Omni-AutoThink: Adaptive Multimodal Reasoning via Reinforcement Learning

RoCo: Role-Based LLMs Collaboration for Automatic Heuristic Design

MemVerse: Multimodal Memory for Lifelong Learning Agents

DeepRule: An Integrated Framework for Automated Business Rule Generation via Deep Predictive Modeling and Hybrid Search Optimization

EnCompass: Enhancing Agent Programming with Search Over Program Execution Paths

Reason-Plan-ReAct: A Reasoner-Planner Supervising a ReAct Executor for Complex Enterprise Tasks

PARC: An Autonomous Self-Reflective Coding Agent for Robust Execution of Long-Horizon Tasks

Multi-Agent Reinforcement Learning with Communication-Constrained Priors

Multimodal Reinforcement Learning with Agentic Verifier for AI Agents

Evaluating Generalization Capabilities of LLM-Based Agents in Mixed-Motive Scenarios Using Concordia

Prior preferences in active inference agents: soft, hard, and goal shaping

When Do Symbolic Solvers Enhance Reasoning in Large Language Models?

Beyond the Black Box: A Cognitive Architecture for Explainable and Aligned AI

Exploring Syntropic Frameworks in AI Alignment: A Philosophical Investigation

Kardia-R1: Unleashing LLMs to Reason toward Understanding and Empathy for Emotional Support via Rubric-as-Judge Reinforcement Learning

Proactive Agentic Whiteboards: Enhancing Diagrammatic Learning

Beyond Greenfield: The D3 Framework for AI-Driven Productivity in Brownfield Engineering

Look, Recite, Then Answer: Enhancing VLM Performance via Self-Generated Knowledge Hints

HBLLM: A Haar-Based Approach for Accurate Structured 1-Bit Quantized LLMs

Limitations of Using Identical Distributions for Training and Testing When Learning Boolean Functions

BioArc: Discovering Optimal Neural Architectures for Biological Foundation Models

MIMIC-MJX: Neuromechanical Emulation of Animal Behavior

Multimodal Continual Learning with MLLMs from Multi-scenario Perspectives

PersonaAgent with GraphRAG: Community-Aware Knowledge Graphs for Personalized LLM

Generative AI in Sociological Research: State of the Discipline

MRI Super-Resolution with Deep Learning: A Comprehensive Survey

SWAN: Sparse Winnowed Attention for Reduced Inference Memory via Decompression-Free KV-Cache Compression

Created by

Haebom

Category

Empty

저자

Santhosh G S, Saurav Prakash, Balaraman Ravindran

개요

SWAN은 Key-Value (KV) 캐시의 메모리 footprint 문제를 해결하기 위해 제안된, fine-tuning이 필요 없는 프레임워크입니다. 오프라인 직교 행렬을 사용하여 KV 캐시를 회전 및 가지치기하여 정보를 손실 없이 압축하고, 압축 해제 단계 없이 어텐션 계산에 직접 사용합니다. SWAN은 소규모의 dense buffer를 추가하여 KV 캐시당 50-60%의 메모리 절약으로도 uncompressed baseline에 근접하는 성능을 유지하며, 런타임에 압축 수준을 조절할 수 있는 유연성을 제공합니다.

시사점, 한계점

•

시사점:

◦

fine-tuning 없이 KV 캐시 압축 가능

◦

압축 해제 단계 불필요

◦

높은 압축률에서도 성능 유지

◦

런타임에 압축 수준 조절 가능

•

한계점:

◦

논문 내에서 구체적인 한계점에 대한 언급은 없음.

Made with Slashpage