haebom
Sign In
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.
SIM1: Physics-Aligned Simulator as Zero-Shot Data Scaler in Deformable Worlds
CrashSight: A Phase-Aware, Infrastructure-Centric Video Benchmark for Traffic Crash Scene Understanding and Reasoning
QARIMA: A Quantum Approach To Classical Time Series Analysis
HyperMem: Hypergraph Memory for Long-Term Conversations
OV-Stitcher: A Global Context-Aware Framework for Training-Free Open-Vocabulary Semantic Segmentation
Governed Capability Evolution for Embodied Agents: Safe Upgrade, Compatibility Checking, and Runtime Rollback for Embodied Capability Modules
WisdomInterrogatory (LuWen): An Open-Source Legal Large Language Model Technical Report
DiffHDR: Re-Exposing LDR Videos with Video Diffusion Models
ALTO: Adaptive LoRA Tuning and Orchestration for Heterogeneous LoRA Training Workloads
Boosted Distributional Reinforcement Learning: Analysis and Healthcare Applications
Many Preferences, Few Policies: Towards Scalable Language Model Personalization
From Paper to Program: Accelerating Quantum Many-Body Algorithm Development via a Multi-Stage LLM-Assisted Workflow
Verbalizing LLMs' assumptions to explain and control sycophancy
Explorable Theorems: Making Written Theorems Explorable by Grounding Them in Formal Representations
Kill-Chain Canaries: Stage-Level Tracking of Prompt Injection Across Attack Surfaces and Model Safety Tiers
Towards Context-Aware Image Anonymization with Multi-Agent Reasoning
Chronological Contrastive Learning: Few-Shot Progression Assessment in Irreversible Diseases
RAM: Recover Any 3D Human Motion in-the-Wild
Improving Automatic Summarization of Radiology Reports through Mid-Training of Large Language Models
You've Got a Golden Ticket: Improving Generative Robot Policies With A Single Noise Vector
Fine-tuning is Not Enough: A Parallel Framework for Collaborative Imitation and Reinforcement Learning in End-to-end Autonomous Driving
Memory-efficient Continual Learning with Prototypical Exemplar Condensation
Better Eyes, Better Thoughts: Why Vision Chain-of-Thought Fails in Medicine
Why Adam Can Beat SGD: Second-Moment Normalization Yields Sharper Tails
Reinforcement-aware Knowledge Distillation for LLM Reasoning
Descriptor: Parasitoid Wasps and Associated Hymenoptera Dataset (DAPWH)
SubQuad: Near-Quadratic-Free Structure Inference with Distribution-Balanced Objectives in Adaptive Receptor framework
An Adaptive Model Selection Framework for Demand Forecasting under Horizon-Induced Degradation to Support Business Strategy and Operations
Exploring Teachers' Perspectives on Using Conversational AI Agents for Group Collaboration
Overstating Attitudes, Ignoring Networks: LLM Biases in Simulating Misinformation Susceptibility
SPEAR: An Engineering Case Study of Multi-Agent Coordination for Smart Contract Auditing
Tiled Prompts: Overcoming Prompt Misguidance in Image and Video Super-Resolution
On the Limits of Layer Pruning for Generative Reasoning in Large Language Models
Self-Supervised Slice-to-Volume Reconstruction with Gaussian Representations for Fetal MRI
Screen, Cache, and Match: A Training-Free Causality-Consistent Reference Frame Framework for Human Animation
Adversarial Evasion Attacks on Computer Vision using SHAP Values
The Two-Stage Decision-Sampling Hypothesis: Understanding the Emergence of Self-Reflection in RL-Trained LLMs
Multi-agent Adaptive Mechanism Design
Relational Visual Similarity
SkillFactory: Self-Distillation For Learning Cognitive Behaviors
Out-of-the-box: Black-box Causal Attacks on Object Detectors
From Navigation to Refinement: Revealing the Two-Stage Nature of Flow-based Diffusion Models through Oracle Velocity
See, Hear, and Understand: Benchmarking Audiovisual Human Speech Understanding in Multimodal Large Language Models
Bharat Scene Text: A Novel Comprehensive Dataset and Benchmark for Indian Language Scene Text Understanding
Commanding Humanoid by Free-form Language: A Large Language Action Model with Unified Motion Vocabulary
Structured Uncertainty guided Clarification for LLM Agents
Evolutionary Optimization Trumps Adam Optimization on Embedding Space Exploration
EGMOF: Efficient Generation of Metal-Organic Frameworks Using a Hybrid Diffusion-Transformer Architecture
How Similar Are Grokipedia and Wikipedia? A Multi-Dimensional Textual and Structural Comparison
LLM4Delay: Flight Delay Prediction via Cross-Modality Adaptation of Large Language Models and Aircraft Trajectory Representation
RESample: A Robust Data Augmentation Framework via Exploratory Sampling for Robotic Manipulation
Dejavu: Towards Experience Feedback Learning for Embodied Intelligence
Webscale-RL: Automated Data Pipeline for Scaling RL Data to Pretraining Levels
Unmasking Puppeteers: Leveraging Biometric Leakage to Disarm Impersonation in AI-based Videoconferencing
Traj2Action: A Co-Denoising Framework for Trajectory-Guided Human-to-Robot Skill Transfer
Adaptive Planning for Multi-Attribute Controllable Summarization with Monte Carlo Tree Search
On-the-Fly Adaptation to Quantization: Configuration-Aware LoRA for Efficient Fine-Tuning of Quantized LLMs
STCast: Adaptive Boundary Alignment for Global and Regional Weather Forecasting
AR-KAN: Autoregressive-Weight-Enhanced Kolmogorov-Arnold Network for Time Series Forecasting
Investigating Multimodal Large Language Models to Support Usability Evaluation
Mitigating Domain Drift in Multi Species Segmentation with DINOv2: A Cross-Domain Evaluation in Herbicide Research Trials
VSI: Visual Subtitle Integration for Keyframe Selection to enhance Long Video Understanding
Provable Post-Training Quantization: Theoretical Analysis of OPTQ and Qronos
Listener-Rewarded Thinking in VLMs for Image Preferences
Enhancing the Safety of Medical Vision-Language Models by Synthetic Demonstrations
Gen-n-Val: Agentic Image Data Generation and Validation
Chain-of-Zoom: Extreme Super-Resolution via Scale Autoregression and Preference Alignment
Revitalizing Black-Box Interpretability: Actionable Interpretability for LLMs via Proxy Models
Constraining Sequential Model Editing with Editing Anchor Compression
AgentSociety: Large-Scale Simulation of LLM-Driven Generative Agents Advances Understanding of Human Behaviors and Society
Neurons Speak in Ranges: Breaking Free from Discrete Neuronal Attribution
OmniPrism: Learning Disentangled Visual Concept for Image Generation
Mitigating Extrinsic Gender Bias for Bangla Classification Tasks
Learning General Representation of 12-Lead Electrocardiogram with a Joint-Embedding Predictive Architecture
Detection and Characterization of Coordinated Online Behavior: A Survey
Group-Aware Coordination Graph for Multi-Agent Reinforcement Learning
Temporal Transfer Learning for Traffic Optimization with Coarse-grained Advisory Autonomy
Task-Distributionally Robust Data-Free Meta-Learning
ASPECT:Analogical Semantic Policy Execution via Language Conditioned Transfer
MONETA: Multimodal Industry Classification through Geographic Information with Multi Agent Systems
EigentSearch-Q+: Enhancing Deep Research Agents with Structured Reasoning Tools
Squeeze Evolve: Unified Multi-Model Orchestration for Verifier-Free Evolution
Towards Knowledgeable Deep Research: Framework and Benchmark
AgentCE-Bench: Agent Configurable Evaluation with Scalable Horizons and Controllable Difficulty under Lightweight Environments
ActivityEditor: Learning to Synthesize Physically Valid Human Mobility
Memory Intelligence Agent
Domain-Contextualized Inference: A Computable Graph Architecture for Explicit-Domain Reasoning
ActionNex: A Virtual Outage Manager for Cloud Computing
TRU: Targeted Reverse Update for Efficient Multimodal Recommendation Unlearning
Reasoning Provenance for Autonomous AI Agents: Structured Behavioral Analytics Beyond State Checkpoints and Execution Traces
PACED: Distillation and On-Policy Self-Distillation at the Frontier of Student Competence
ReplicatorBench: Benchmarking LLM Agents for Replicability in Social and Behavioral Sciences
H-AdminSim: A Multi-Agent Simulator for Realistic Hospital Administrative Workflows with FHIR Integration
Reasoning in a Combinatorial and Constrained World: Benchmarking LLMs on Natural-Language Combinatorial Optimization
The Hot Mess of AI: How Does Misalignment Scale With Model Intelligence and Task Complexity?
ConvoLearn: A Learning Sciences Grounded Dataset for Fine-Tuning Dialogic AI Tutors
Reasoning Models Will Sometimes Lie About Their Reasoning
Precomputing Multi-Agent Path Replanning using Temporal Flexibility
Sample-Efficient Neurosymbolic Deep Reinforcement Learning
EchoTrail-GUI: Building Actionable Memory for GUI Agents via Critic-Guided Self-Exploration
Load more
Made with Slashpage
