haebom
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, 요약본 공유 시 출처만 명기하면 됩니다.
This service is supported by Google Gemini.
Think as Needed: Geometry-Driven Adaptive Perception for Autonomous Driving
CFSPMNet: Cross-subject Fourier-guided Spatial-Patch Mamba Network for EEG Motor Imagery Decoding in Stroke Patients
ViSRA: A Video-based Spatial Reasoning Agent for Multi-modal Large Language Models
HYPERPOSE: Hyperbolic Kinematic Phase-Space Attention for 3D Human Pose Estimation
Retrieve-then-Steer: Online Success Memory for Test-Time Adaptation of Generative VLAs
PoDAR: Power-Disentangled Audio Representation for Generative Modeling
Metis: Learning to Jailbreak LLMs via Self-Evolving Metacognitive Policy Optimization
NCO: A Versatile Plug-in for Handling Negative Constraints in Decoding
Not-So-Strange Love: Language Models and Generative Linguistic Theories are More Compatible than They Appear
Swarm Skills: A Portable, Self-Evolving Multi-Agent System Specification for Coordination Engineering
Guided Streaming Stochastic Interpolant Policy
Rethinking Loss Reweighting for Imbalance Learning as an Inverse Problem: A Neural Collapse Point of View
Adaptive Action Chunking via Multi-Chunk Q Value Estimation
Personalizing LLMs with Binary Feedback: A Preference-Corrected Optimization Framework
Bridging the Cognitive Gap: A Unified Memory Paradigm for 6G Agentic AI-RAN
Speech-based Psychological Crisis Assessment using LLMs
Medical Incident Causal Factors and Preventive Measures Generation Using Tag-based Example Selection in Few-shot Learning
The two clocks and the innovation window: When and how generative models learn rules
Combining Mechanical and Agentic Specification Inference for Move
Continual Harness: Online Adaptation for Self-Improving Foundation Agents
Attention Drift: What Autoregressive Speculative Decoding Models Learn
Geometric 4D Stitching for Grounded 4D Generation
Yeti: A compact protein structure tokenizer for reconstruction and multi-modal generation
GLiNER2-PII: A Multilingual Model for Personally Identifiable Information Extraction
HapticLDM: A Diffusion Model for Text-to-Vibrotactile Generation
G-Zero: Self-Play for Open-Ended Generation from Zero Data
SDTalk: Structured Facial Priors and Dual-Branch Motion Fields for Generalizable Gaussian Talking Head Synthesis
Novel GPU Boruta algorithms for feature selection from high-dimensional data
PruneTIR: Inference-Time Tool Call Pruning for Effective yet Efficient Tool-Integrated Reasoning
Team-Based Self-Play With Dual Adaptive Weighting for Fine-Tuning LLMs
Verifier-Free RL for LLMs via Intrinsic Gradient-Norm Reward
NaiAD: Initiate Data-Driven Research for LLM Advertising
Position: Academic Conferences are Potentially Facing Denominator Gaming Caused by Fully Automated Scientific Agents
Voice Biomarkers for Depression and Anxiety
Rethinking Random Transformers as Adaptive Sequence Smoothers for Sleep Staging
Hyperbolic Distillation: Geometry-Guided Cross-Modal Transfer for Robust 3D Object Detection
Pseudo-Deliberation in Language Models: When Reasoning Fails to Align Values and Actions
The Geometric Wall: Manifold Structure Predicts Layerwise Sparse Autoencoder Scaling Laws
The Cartesian Shortcut: Re-evaluate Vision Reasoning in Polar Coordinate Space
Key-Value Means
EgoMemReason: A Memory-Driven Reasoning Benchmark for Long-Horizon Egocentric Video Understanding
Intervention-Based Time Series Causal Discovery via Simulator-Generated Interventional Distributions
Continuous Latent Contexts Enable Efficient Online Learning in Transformers
Nautilus Compass: Black-box Persona Drift Detection for Production LLM Agents
UFO: A Unified Flow-Oriented Framework for Robust Continual Graph Learning
Flag Varieties: A Geometric Framework for Deep Network Alignment
MoPO: Incorporating Motion Prior for Occluded Human Mesh Recovery
Probing Routing-Conditional Calibration in Attention-Residual Transformers
ChladniSonify: A Visual-Acoustic Mapping Method for Chladni Patterns in New Media Art Creation
Free Energy Manifold: Score-Based Inference for Hybrid Bayesian Networks
Fashion Florence: Fine-Tuning Florence-2 for Structured Fashion Attribute Extraction
Pretraining large language models with MXFP4
CalBench: Evaluating Coordination-Privacy Trade-offs in Multi-Agent LLMs
Oracle Poisoning: Corrupting Knowledge Graphs to Weaponise AI Agent Reasoning
LEAD: Length-Efficient Adaptive and Dynamic Reasoning for Large Language Models
Insight: Enhancing Mobile Accessibility for Blind and Visually Impaired Users with LLMs
CrossVL: Complexity-Aware Feature Routing and Paired Curriculum for Cross-View Vision-Language Detection
Multi-Tier Labeling and Physics-Informed Learning for Orbital Anomaly Detection at Scale
Parameter-Efficient Neuroevolution for Diverse LLM Generation: Quality-Diversity Optimization via Prompt Embedding Evolution
EvoPref: Multi-Objective Evolutionary Optimization Discovers Diverse LLM Alignments Beyond Gradient Descent
Exploitation Without Deception: Dark Triad Feature Steering Reveals Separable Antisocial Circuits in Language Models
WISTERIA: Learning Clinical Representations from Noisy Supervision via Multi-View Consistency in Electronic Health Records
LEVI: Stronger Search Architectures Can Substitute for Larger LLMs in Evolutionary Search
Sequential Feature Selection for Efficient Landslide Segmentation from Multi-Spectral Data
Entropy-informed Decoding: Adaptive Information-Driven Branching
TIDES: Implicit Time-Awareness in Selective State Space Models
The Silent Vote: Improving Zero-Shot LLM Reliability by Aggregating Semantic Neighborhoods
KV-RM: Regularizing KV-Cache Movement for Static-Graph LLM Serving
Trajectory Supervision for Continual Tool-Use Learning in LLMs
One for All: A Non-Linear Transformer can Enable Cross-Domain Generalization for In-Context Reinforcement Learning
Security Risks in Tool-Enabled AI Agents: A Systematic Analysis of Privileged Execution Environments
Distilling 3D Spatial Reasoning into a Lightweight Vision-Language Model with CoT
Metal-Sci: A Scientific Compute Benchmark for Evolutionary LLM Kernel Search on Apple Silicon
Adaptive Data Harvesting for Efficient Neural Network Learning with Universal Constraints
Do multimodal models imagine electric sheep?
Learning Unified Representations of Normalcy for Time Series Anomaly Detection
MonitoringBench: Semi-Automated Red-Teaming for Agent Monitoring
DeepTumorVQA: A Hierarchical 3D CT Benchmark for Stage-Wise Evaluation of Medical VLMs and Tool-Augmented Agents
ChaosNetBench: Benchmarking Spatio-Temporal Graph Neural Networks on Chaotic Lattice Dynamics
S2P-Net: A Spectral-Spatial Polar Network for Rotation-Invariant Object Recognition in Low-Data Regimes
Rethinking Evaluation of Multiple Sclerosis (MS) Lesion Segmentation Models
Learning Multi-Indicator Weights for Data Selection: A Joint Task-Model Adaptation Framework with Efficient Proxies
Causal Parametric Drift Simulation: A Digital Twin Framework for Classifier Robustness Evaluation
MedMeta: A Benchmark for LLMs in Synthesizing Meta-Analysis Conclusion from Medical Studies
RDEx-CASK: Cauchy Mutation, Archive, and Stagnation Kick for RDEx-CSOP
Adaptive DNN Partitioning and Offloading in Heterogeneous Edge-Cloud Continuum
Any2Any 3D Diffusion Models with Knowledge Transfer: A Radiotherapy Planning Study
SmartEval: A Benchmark for Evaluating LLM-Generated Smart Contracts from Natural Language Specifications
Efficient Ensemble Selection from Binary and Pairwise Feedback
CLR-voyance: Reinforcing Open-Ended Reasoning for Inpatient Clinical Decision Support with Outcome-Aware Rubrics
Biosignal Fingerprinting: A Cross-Modal PPG-ECG Foundation Model
KAN Text to Vision? The Exploration of Kolmogorov-Arnold Networks for Multi-Scale Sequence-Based Pose Animation from Sign Language Notation
PhysHanDI: Physics-Based Reconstruction of Hand-Deformable Object Interactions
TAD: Temporal-Aware Trajectory Self-Distillation for Fast and Accurate Diffusion LLM
Governing AI-Assisted Security Operations: A Design Science Framework for Operational Decision Support
Assessment of RAG and Fine-Tuning for Industrial Question-Answering-Applications
Mixture of Layers with Hybrid Attention
Position: AI Security Policy Should Target Systems, Not Models
Hidden Error Awareness in Chain-of-Thought Reasoning: The Signal Is Diagnostic, Not Causal
Spectral Transformer Neural Processes
Load more
Share
Emergent Semantics Beyond Token Embeddings: Transformer LMs with Frozen Visual Unicode Representations
Created by
Haebom
Category
Empty
저자
A. Bochkov
PDF 보기
Made with Slashpage
