haebom
Sign In
Daily Arxiv
New
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, 요약본 공유 시 출처만 명기하면 됩니다.
This service is supported by Google Gemini.
Behavior Foundations for Quadruped Robots: ABot-C0 Technical Report
ResonatorLM: Causal Resonant Field Mixing for Efficient Long-Context Language Modeling
Search Beyond What Can Be Taught: Evolving the Knowledge Boundary in Agentic Visual Generation
KVpop -- Key-Value Cache Compression with Predictive Online Pruning
LLM for the development of FCM
Phase-Preserving Trimodal Transformer for Tropical Forest Biomass Estimation Using Optical and PolInSAR Data
MambaLIE: Scene Light Intensity-Boosted Low-Light Image Enhancement with State Space Model
Where do LLMs Fall Short in CBT-Guided Affective Reasoning?
TAG: A Lightweight Framework for Test-Driven Agentic Artifact Generation
GAP-GDRNet: Geometry-aware monocular 6D pose estimation for spacecraft using synthetic geometric supervision
Generalization in offline RL: The structure is more important than the amount of pessimism
Diffusion-GR2: Diffusion Generative Reasoning Re-ranker
A Stochastic--Geometric Theory of Scaling Laws in Grokking
How to Leverage Synthetic Speech for LLM-Based ASR Systems?
Play2Perfect: What Matters in Dexterous Play Pretraining for Precise Assembly?
video-SALMONN-R$^3$: Learning to ReWatch, ReAsk, and ReAnswer for Efficient Video Understanding
Improving Engine Sound Analysis in Hot-Test Environments via a RAB-U-Net (Residual Attention Block U-Net) Noise Removal Method
Does Mixture-of-Experts Actually Help Inference on Consumer and Edge Hardware? An Empirical Study
Hierarchical Control in Multi-Agent Games: LLM-based Planning and RL Execution
Training and Evaluating Diffusion Policies with Long Context Lengths
Bridging Modal Isolation in Interleaved Thinking: Supervising Modality Transitions via Stepwise Reinforcement
KG-SoftMAP: Soft Knowledge-Graph Priors for Bayesian Network Structure Learning from Sparse Discrete Data
MeCo: One-Step MeanFlow-based Corrector for Multi-Channel Speech Separation
EasyLens: A Training-Free Plug-and-Play Subtle-Lesion Representation Amplifier for Medical Vision-Language Models
Temporal Preference Concepts and their Functions in a Large Language Model
Autonomous heterogeneous catalyst discovery with a self-evolving multi-agent digital twin
When RLHF Fails: A Mechanistic Taxonomy of Reward Hacking, Collapse, and Evaluator Gaming
Correcting Visual Blur Induced by Attention Distraction to Reduce Hallucinations: Algorithm and Theory
MAVEN: A Multi-stage Agentic Annotation Pipeline for Video Reasoning Tasks
CriterAlign: Criterion-Centric Rationale Alignment for Code Preference Judging
MasFACT: Continual Multi-Agent Topology Learning via Geometry-Aware Posterior Transfer
Second-Order Actor-Critic Methods for Discounted MDPs via Policy Hessian Decomposition
LoKA: Low-precision Kernel Applications for Recommendation Models At Scale
DeepTutor: Towards Agentic Personalized Tutoring
Predicting Scale-Up of Metal-Organic Framework Syntheses with Large Language Models
Peer-Predictive Self-Training for Language Model Reasoning
Beyond Attention Scores: SVD-Based Vision Token Pruning for Efficient Vision-Language Models
Persona Matters: Effects of Activation Steering on Short Answer Generation and Scoring
LSRM: High-Fidelity Object-Centric Reconstruction via Scaled Context Windows
Neural Harmonic Textures for High-Quality Primitive Based Neural Reconstruction
Echoes: A semantically-aligned music deepfake detection dataset
StateLinFormer: Stateful Training Enhancing Long-term Memory in Navigation
The Phasor Transformer: Resolving Attention Bottlenecks on the Unit Circle
PhasorFlow: A Python Library for Unit Circle Based Computing
Safe Flow Q-Learning: Offline Safe Reinforcement Learning with Reachability-Based Flow Policies
Human-like Object Grouping in Self-supervised Vision Transformers
Robust Weighted Triangulation of Causal Effects Under Model Uncertainty
Curvature-Weighted Capacity Allocation: A Minimum Description Length Framework for Layer-Adaptive Large Language Model Optimization
Curriculum Learning for Efficient Chain-of-Thought Distillation via Structure-Aware Masking and GRPO
An Online Reference-Free Evaluation Framework for Flowchart Image-to-Code Generation
Self-EvolveRec: Self-Evolving Recommender Systems with LLM-based Directional Feedback
Towards Isolated Interventions via Almost Orthogonal Features in Language Models
Rethinking LLM-as-a-Judge: Representation-as-a-Judge with Small Language Models via Semantic Capacity Asymmetry
XFACTORS: Disentangled Information Bottleneck via Contrastive Supervision
GenDA: Generative Data Assimilation on Complex Urban Areas via Classifier-Free Diffusion Guidance
Bridging Cognitive Neuroscience and Graph Intelligence: Hippocampus-Inspired Multi-View Hypergraph Learning for Web Finance Fraud
SwinIFS: Landmark Guided Swin Transformer For Identity Preserving Face Super Resolution
V-VLAPS: Value-Guided Planning for Vision-Language-Action Models
CoCo-Fed: A Unified Framework for Memory- and Communication-Efficient Federated Learning at the Wireless Edge
Deep Neural Networks as Discrete Dynamical Systems: Implications for Physics-Informed Learning
MSRNet: A Multi-Scale Recursive Network for Camouflaged Object Detection
OREN: Octree Residual Network for Real-Time Euclidean Signed Distance Mapping
Adaptive Generation of Bias-Eliciting Questions for LLMs
MultiFair: Multimodal Balanced Fairness-Aware Medical Classification with Dual-Level Gradient Modulation
TOPO-Bench: An Open-Source Topological Mapping Evaluation Framework with Quantifiable Perceptual Aliasing
How Causal Abstraction Underpins Computational Explanation
Less Is More: Reducing Token Counts Without Compromising Performance
ToDMA: Large Model-Driven Massive Token Communications for Semantic Multiple Access
Concept-as-Tree: A Controllable Synthetic Data Framework Makes Stronger Personalized VLMs
Simulator Ensembles for Trustworthy Autonomous Driving Systems Testing
ParamMute: Suppressing Knowledge-Critical FFNs for Faithful Retrieval-Augmented Generation
The Contribution of XAI for the Safe Development and Certification of AI: An Expert-Based Analysis
Retrieval of Scientific and Technological Resources for Experts and Scholars
Knowledge Graph and Accurate Portrait Construction of Scientific and Technological Academic Conferences
Accurate Portraits of Scientific Resources and Knowledge Service Components
From Application-Layer Simulation to Native Meta-Architecture: Structural Tension as an Endogenous Driver for Heterogeneous AI Evolution
PolyWorkBench: Benchmarking Multilingual Long-Horizon LLM Agents
Distributed Attacks in Persistent-State AI Control
ContextSniper: AntTrail's Token-Efficient Code Memory for Repository-Level Program Repair
Theoria: Rewrite-Acceptability Verification over Informal Reasoning States
Narration-of-Thought: Inference-Time Scaffolding for Defeasible Ethical Reasoning in Large Language Models
InvestPhilBench: A Multi-Layer Benchmark for Evaluating Large Language Model Procedural Reasoning in Expert Investment Philosophy
TNODEV: Toolbox for Neural ODE Verification
LiteOdyssey: A Lightweight Reasoning AI Agent for Interpretable Rare-Disease Diagnosis
Deployment-Time Memorization in Foundation-Model Agents
SHARP: Sleep-based Hierarchical Accelerated Replay for Long Range Non-Stationary Temporal Pattern Recognition
The Power of Power Law: Asymmetry Enables Compositional Reasoning
Retrieval-Augmented Generation Must Move Beyond Factual Grounding to Represent Diverse Opinions
RetailBench: Evaluating Long-Horizon Autonomous Decision-Making and Strategy Stability of LLM Agents in Realistic Retail Environments
Conversational AI for Rapid Scientific Prototyping: A Case Study on ESA's ELOPE Competition
SimRPD: Optimizing Recruitment Proactive Dialogue Agents through Simulator-Based Data Evaluation and Selection
MetaHGNIE: Meta-Path Induced Hypergraph Contrastive Learning in Heterogeneous Knowledge Graphs
A Vision Toward Energy-Efficient Domain-Specific Artificial Intelligence Models and Agents
Dual-Difficulty Curriculum Learning for Direct Preference Optimization
Goal-Driven Reasoning in DatalogMTL with Magic Sets
IFAR: Multi-Perspective and Multi-Level Causal Discovery with LLMs
OpenCoF: Learning to Reason Through Video Generation
SLORR: Simple and Efficient In-Training Low-Rank Regularization
Dimensionality Reduction Meets Network Science: Sensemaking on UMAP's kNN Graph
Validity of LLMs as data annotators: AMALIA on authority
Load more
New
Made with Slashpage
