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.

Exploring Diffusion Transformer Designs via Grafting

Teaming in the AI Era: AI-Augmented Frameworks for Forming, Simulating, and Optimizing Human Teams

ECoRAG: Evidentiality-guided Compression for Long Context RAG

Dissecting Bias in LLMs: A Mechanistic Interpretability Perspective

Does It Make Sense to Speak of Introspection in Large Language Models?

Sparse Autoencoders, Again?

Feature-Based Lie Group Transformer for Real-World Applications

TracLLM: A Generic Framework for Attributing Long Context LLMs

SemiOccam: A Robust Semi-Supervised Image Recognition Network Using Sparse Labels

Labelling Data with Unknown References

Tug-of-war between idiom's figurative and literal meanings in LLMs

State-Covering Trajectory Stitching for Diffusion Planners

Deep Learning Weather Models for Subregional Ocean Forecasting: A Case Study on the Canary Current Upwelling System

DORAEMON: Decentralized Ontology-aware Reliable Agent with Enhanced Memory Oriented Navigation

Subspecialty-Specific Foundation Model for Intelligent Gastrointestinal Pathology

RepoMaster: Autonomous Exploration and Understanding of GitHub Repositories for Complex Task Solving

An Uncertainty-Aware ED-LSTM for Probabilistic Suffix Prediction

SageAttention2++: A More Efficient Implementation of SageAttention2

Autocomp: LLM-Driven Code Optimization for Tensor Accelerators

IDA-Bench: Evaluating LLMs on Interactive Guided Data Analysis

Decoupling Representation and Learning in Genetic Programming: the LaSER Approach

Common Data Format (CDF): A Standardized Format for Match-Data in Football (Soccer)

Web Intellectual Property at Risk: Preventing Unauthorized Real-Time Retrieval by Large Language Models

How can Diffusion Models Evolve into Continual Generators?

Open Your Eyes: Vision Enhances Message Passing Neural Networks in Link Prediction

m-KAILIN: Knowledge-Driven Agentic Scientific Corpus Distillation Framework for Biomedical Large Language Models Training

FinSage: A Multi-aspect RAG System for Financial Filings Question Answering

Not All Rollouts are Useful: Down-Sampling Rollouts in LLM Reinforcement Learning

LauraTSE: Target Speaker Extraction using Auto-Regressive Decoder-Only Language Models

Reasoning Towards Fairness: Mitigating Bias in Language Models through Reasoning-Guided Fine-Tuning

Sparse Autoencoders Learn Monosemantic Features in Vision-Language Models

Multivariate Temporal Regression at Scale: A Three-Pillar Framework Combining ML, XAI, and NLP

GENIUS: A Generative Framework for Universal Multimodal Search

TinySQL: A Progressive Text-to-SQL Dataset for Mechanistic Interpretability Research

ARMOR: Empowering Multimodal Understanding Model with Interleaved Multimodal Generation Capability

A Survey on Sparse Autoencoders: Interpreting the Internal Mechanisms of Large Language Models

Knowledge Retention for Continual Model-Based Reinforcement Learning

Adversarial Tokenization

UDora: A Unified Red Teaming Framework against LLM Agents by Dynamically Hijacking Their Own Reasoning

SAGE: A Framework of Precise Retrieval for RAG

Graph Attention Networks Unleashed: A Fast and Explainable Vulnerability Assessment Framework for Microgrids

SafeAuto: Knowledge-Enhanced Safe Autonomous Driving with Multimodal Foundation Models

Emergent Symbolic Mechanisms Support Abstract Reasoning in Large Language Models

Improving Customer Service with Automatic Topic Detection in User Emails

DualSpec: Text-to-spatial-audio Generation via Dual-Spectrogram Guided Diffusion Model

Jacobian Sparse Autoencoders: Sparsify Computations, Not Just Activations

SpargeAttention: Accurate and Training-free Sparse Attention Accelerating Any Model Inference

MimeQA: Towards Socially-Intelligent Nonverbal Foundation Models

A Comprehensive Survey on Concept Erasure in Text-to-Image Diffusion Models

LLMs on the Line: Data Determines Loss-to-Loss Scaling Laws

Maximum Entropy Reinforcement Learning with Diffusion Policy

TituLLMs: A Family of Bangla LLMs with Comprehensive Benchmarking

Relational Conformal Prediction for Correlated Time Series

RoSTE: An Efficient Quantization-Aware Supervised Fine-Tuning Approach for Large Language Models

UniDB: A Unified Diffusion Bridge Framework via Stochastic Optimal Control

The Complexity of Learning Sparse Superposed Features with Feedback

Peri-LN: Revisiting Normalization Layer in the Transformer Architecture

Rollout Roulette: A Probabilistic Inference Approach to Inference-Time Scaling of LLMs using Particle-Based Monte Carlo Methods

An Optimal Cascade Feature-Level Spatiotemporal Fusion Strategy for Anomaly Detection in CAN Bus

ProofAug: Efficient Neural Theorem Proving via Fine-grained Proof Structure Analysis

FDLLM: A Dedicated Detector for Black-Box LLMs Fingerprinting

The Bakers and Millers Game with Restricted Locations

Diving into Self-Evolving Training for Multimodal Reasoning

Reasoning Through Execution: Unifying Process and Outcome Rewards for Code Generation

A Riemannian Optimization Perspective of the Gauss-Newton Method for Feedforward Neural Networks

CoopetitiveV: Leveraging LLM-powered Coopetitive Multi-Agent Prompting for High-quality Verilog Generation

TraceVLA: Visual Trace Prompting Enhances Spatial-Temporal Awareness for Generalist Robotic Policies

The Synergy of LLMs & RL Unlocks Offline Learning of Generalizable Language-Conditioned Policies with Low-fidelity Data

Understanding Memorization in Generative Models via Sharpness in Probability Landscapes

A Cognac shot to forget bad memories: Corrective Unlearning in GNNs

Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and Efficiency

Who Can Withstand Chat-Audio Attacks? An Evaluation Benchmark for Large Audio-Language Models

CLIPErase: Efficient Unlearning of Visual-Textual Associations in CLIP

The Impact of Inference Acceleration on Bias of LLMs

pLDDT-Predictor: High-speed Protein Screening Using Transformer and ESM2

Simmering: Sufficient is better than optimal for training neural networks

PoisonBench: Assessing Large Language Model Vulnerability to Data Poisoning

Efficient Fine-Grained Guidance for Diffusion Model Based Symbolic Music Generation

AutoML-Agent: A Multi-Agent LLM Framework for Full-Pipeline AutoML

VisionTS: Visual Masked Autoencoders Are Free-Lunch Zero-Shot Time Series Forecasters

Deconfounding Multi-Cause Latent Confounders: A Factor-Model Approach to Climate Model Bias Correction

DyGMamba: Efficiently Modeling Long-Term Temporal Dependency on Continuous-Time Dynamic Graphs with State Space Models

Proximal Policy Distillation

BoA: Attention-aware Post-training Quantization without Backpropagation

Certification for Differentially Private Prediction in Gradient-Based Training

Multi-Agent Collaboration via Cross-Team Orchestration

LlavaGuard: An Open VLM-based Framework for Safeguarding Vision Datasets and Models

Computational Limits of Low-Rank Adaptation (LoRA) Fine-Tuning for Transformer Models

Boolean matrix logic programming for active learning of gene functions in genome-scale metabolic network models

Mirage: A Multi-Level Superoptimizer for Tensor Programs

Multidimensional Adaptive Coefficient for Inference Trajectory Optimization in Flow and Diffusion

Longitudinal Targeted Minimum Loss-based Estimation with Temporal-Difference Heterogeneous Transformer

TMT: Tri-Modal Translation between Speech, Image, and Text by Processing Different Modalities as Different Languages

Structure Guided Large Language Model for SQL Generation

GraphGPT: Generative Pre-trained Graph Eulerian Transformer

Graph Deep Learning for Time Series Forecasting

Diffusion Policies for Out-of-Distribution Generalization in Offline Reinforcement Learning

Just Enough Thinking: Efficient Reasoning with Adaptive Length Penalties Reinforcement Learning

Rethinking Machine Unlearning in Image Generation Models

The Coming Crisis of Multi-Agent Misalignment: AI Alignment Must Be a Dynamic and Social Process

SageAttention2++: A More Efficient Implementation of SageAttention2

Created by

Haebom

저자

Jintao Zhang, Xiaoming Xu, Jia Wei, Haofeng Huang, Pengle Zhang, Chendong Xiang, Jun Zhu, Jianfei Chen

개요

SageAttention2의 속도 향상을 위한 새로운 방법인 SageAttention2++를 제안합니다. SageAttention2는 양자화를 이용하여 어텐션 연산의 속도를 높였지만, SageAttention2++는 FP8 Matmul을 FP16으로 누적하는 더 빠른 명령어를 사용하여 추가적인 속도 향상을 달성합니다. 실험 결과, SageAttention2++는 FlashAttention보다 3.9배 빠르면서 SageAttention2와 동일한 정확도를 유지합니다. 이는 자연어, 이미지, 비디오 생성 모델 등 다양한 모델에 적용 가능하며, 종단 간 성능 저하 없이 효과적으로 속도를 향상시킴을 의미합니다. 코드는 https://github.com/thu-ml/SageAttention 에서 공개될 예정입니다.

GitHub - thu-ml/SageAttention: Quantized Attention achieves speedup of 2-5x and 3-11x compared to FlashAttention and xformers, without lossing end-to-end metrics across language, image, and video models.

Quantized Attention achieves speedup of 2-5x and 3-11x compared to FlashAttention and xformers, without lossing end-to-end metrics across language, image, and video models. - thu-ml/SageAttention

시사점, 한계점

•

시사점:

◦

FP8 Matmul을 FP16 누적 연산을 활용하여 어텐션 연산 속도를 획기적으로 향상시킬 수 있음을 보여줌.

◦

FlashAttention 대비 3.9배의 속도 향상을 달성하면서 정확도 손실은 거의 없음.

◦

다양한 모델(자연어, 이미지, 비디오 생성 모델)에 적용 가능성을 제시.

•

한계점:

◦

본 논문에서는 특정 하드웨어 환경에서의 성능 향상을 제시하므로, 다른 하드웨어 환경에서는 성능 차이가 발생할 수 있음.

◦

공개된 코드를 통해 실제 성능을 검증해야 함.

◦

FP16 누적 연산을 위한 하드웨어 지원이 필요하며, 모든 하드웨어에서 동일한 성능 향상을 기대할 수 없음.

Made with Slashpage