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, 요약본 공유 시 출처만 명기하면 됩니다.
This service is supported by Google Gemini.
Learning Discrete Autoregressive Priors with Wasserstein Gradient Flow
Unifying Goal-Conditioned RL and Unsupervised Skill Learning via Control-Maximization
AI-Generated Images: What Humans and Machines See When They Look at the Same Image
IRC-Bench: Recognizing Entities from Contextual Cues in First-Person Reminiscences
SymDrift: One-Shot Generative Modeling under Symmetries
Listwise Policy Optimization: Group-based RLVR as Target-Projection on the LLM Response Simplex
Autoregressive Visual Generation Needs a Prologue
BUILD-AND-FIND: An Effort-Aware Protocol for Evaluating Agent-Managed Codebases
Continuous Expert Assembly: Instance-Conditioned Low-Rank Residuals for All-in-One Image Restoration
Dynamic Pondering Sparsity-aware Mixture-of-Experts Transformer for Event Stream based Visual Object Tracking
Schedule-and-Calibrate: Utility-Guided Multi-Task Reinforcement Learning for Code LLMs
Beyond Autoregressive RTG: Conditioning via Injection Outside Sequential Modeling in Decision Transformer
CredibleDFGO: Differentiable Factor Graph Optimization with Credibility Supervision
VISD: Enhancing Video Reasoning via Structured Self-Distillation
Milestone-Guided Policy Learning for Long-Horizon Language Agents
Normalized Architectures are Natively 4-Bit
Causal Reinforcement Learning for Complex Card Games: A Magic The Gathering Benchmark
TFM-Retouche: A Lightweight Input-Space Adapter for Tabular Foundation Models
Optimal Transport for LLM Reward Modeling from Noisy Preference
Quantum Kernels for Audio Deepfake Detection Using Spectrogram Patch Features
When AI Meets Science: Research Diversity, Interdisciplinarity, Visibility, and Retractions across Disciplines in a Global Surge
Does Synthetic Data Help? Empirical Evidence from Deep Learning Time Series Forecasters
Quantizing With Randomized Hadamard Transforms: Efficient Heuristic Now Proven
Adding Thermal Awareness to Visual Systems in Real-Time via Distilled Diffusion Models
PersonaKit (PK): A Plug-and-Play Platform for User Testing Diverse Roles in Full-Duplex Dialogue
A Fine-Grained Understanding of Uniform Convergence for Halfspaces
Safety Anchor: Defending Harmful Fine-tuning via Geometric Bottlenecks
iPhoneBlur: A Difficulty-Stratified Benchmark for Consumer Device Motion Deblurring
PragLocker: Protecting Agent Intellectual Property in Untrusted Deployments via Non-Portable Prompts
Towards Reliable LLM Evaluation: Correcting the Winner's Curse in Adaptive Benchmarking
Beyond Uniform Credit Assignment: Selective Eligibility Traces for RLVR
Hallucination as an Anomaly: Dynamic Intervention via Probabilistic Circuits
LLM-Driven Design Space Exploration of FPGA-based Accelerators
Quantum-enhanced Large Language Models on Quantum Hardware via Cayley Unitary Adapters
Architecture-agnostic Lipschitz-constant Bayesian header and its application to resolve semantically proximal classification errors with vision transformers
VARS-FL: Validation-Aligned Client Selection for Non-IID Federated Learning in IoT Systems
Detecting AI-Generated Videos with Spiking Neural Networks
Logic-Regularized Verifier Elicits Reasoning from LLMs
MTL-MAD: Multi-Task Learners are Effective Medical Anomaly Detectors
DBMSolver: A Training-free Diffusion Bridge Sampler for High-Quality Image-to-Image Translation
Tuning Derivatives for Causal Fairness in Machine Learning
CITE: Anytime-Valid Statistical Inference in LLM Self-Consistency
SOPE: Stabilizing Off-Policy Evaluation for Online RL with Prior Data
VideoRouter: Query-Adaptive Dual Routing for Efficient Long-Video Understanding
LoopTrap: Termination Poisoning Attacks on LLM Agents
LeakDojo: Decoding the Leakage Threats of RAG Systems
A Testable Certificate for Constant Collapse in Teacher-Guided VAEs
LCC-LLM: Leveraging Code-Centric Large Language Models for Malware Attribution
Revealing Modular Gradient Noise Imbalance in LLMs: Calibrating Adam via Signal-to-Noise Ratio
Steering Visual Generation in Unified Multimodal Models with Understanding Supervision
The autoPET3 Challenge -- Automated Lesion Segmentation in Whole-Body PET/CT - Multitracer Multicenter Generalization
Adaptive Selection of LoRA Components in Privacy-Preserving Federated Learning
Transformers Provably Implement In-Context Reinforcement Learning with Policy Improvement
Fourier Feature Methods for Nonlinear Causal Discovery: FFML Scoring and FFCI Testing in Mixed Data
Multi-Dimensional Behavioral Evaluation of Agentic Stock Prediction Systems Using LLM Judges with Closed-Loop Reinforcement Learning Feedback
CoMemNet: Contrastive Sampling with Memory Replay Network for Continual Traffic Prediction
CRAFT: Forgetting-Aware Intervention-Based Adaptation for Continual Learning
WARP: A Benchmark for Primal-Dual Warm-Starting of Interior-Point Solvers
Auto Research with Specialist Agents Develops Effective and Non-Trivial Training Recipes
SafeHarbor: Hierarchical Memory-Augmented Guardrail for LLM Agent Safety
Active Learning for Communication Structure Optimization in LLM-Based Multi-Agent Systems
An Empirical Study of Proactive Coding Assistants in Real-World Software Development
When Quantization Is Free: An int4 KV Cache That Outruns fp16 on Apple Silicon
Budgeted Attention Allocation: Cost-Conditioned Compute Control for Efficient Transformers
Irminsul: MLA-Native Position-Independent Caching for Agentic LLM Serving
CFE-PPAR: Compression-friendly encryption for privacy-preserving action recognition leveraging video transformers
Temporal Functional Circuits: From Spline Plots to Faithful Explanations in KAN Forecasting
PersonaTeaming: Supporting Persona-Driven Red-Teaming for Generative AI
Decomposing the Basic Abilities of Large Language Models: Mitigating Cross-Task Interference in Multi-Task Instruct-Tuning
EGA: Adapting Frozen Encoders for Vector Search with Bounded Out-of-Distribution Degradation
XL-SafetyBench: A Country-Grounded Cross-Cultural Benchmark for LLM Safety and Cultural Sensitivity
The Missing Evaluation Axis: What 10,000 Student Submissions Reveal About AI Tutor Effectiveness
One Turn Too Late: Response-Aware Defense Against Hidden Malicious Intent in Multi-Turn Dialogue
Leveraging Image Generators to Address Training Data Scarcity: The Gen4Regen Dataset for Forest Regeneration Mapping
When2Speak: A Dataset for Temporal Participation and Turn-Taking in Multi-Party Conversations for Large Language Models
X-Voice: Enabling Everyone to Speak 30 Languages via Zero-Shot Cross-Lingual Voice Cloning
Nearly Optimal Attention Coresets
Accelerating LMO-Based Optimization via Implicit Gradient Transport
AstroAlertBench: Evaluating the Accuracy, Reasoning, and Honesty of Multimodal LLMs in Astronomical Classification
MOSAIC: Module Discovery via Sparse Additive Identifiable Causal Learning for Scientific Time Series
When Semantic Communication Meets Queueing: Cross-Layer Latency and Task Fidelity Optimization
ReaComp: Compiling LLM Reasoning into Symbolic Solvers for Efficient Program Synthesis
GRALIS: A Unified Canonical Framework for Linear Attribution Methods via Riesz Representation
A Unified Benchmark for Evaluating Knowledge Graph Construction Methods and Graph Neural Networks
The Pedagogy of AI Mistakes: Fostering Higher-Order Thinking
Robustness of Graph Self-Supervised Learning to Real-World Noise: A Case Study on Text-Driven Biomedical Graphs
SLAM: Structural Linguistic Activation Marking for Language Models
On Semantic Loss Fine-Tuning Approach for Preventing Model Collapse in Causal Reasoning
Information Theoretic Adversarial Training of Large Language Models
Creative Robot Tool Use by Counterfactual Reasoning
Mise en Place for Agentic Coding: Deliberate Preparation as Context Engineering Methodology
Generating Query-Focused Summarization Datasets from Query-Free Summarization Datasets
Two-Stage Learned Decomposition for Scalable Routing on Multigraphs
Two Steps Are All You Need: Efficient 3D Point Cloud Anomaly Detection with Consistency Models
SPADE: Faster Drug Discovery by Learning from Sparse Data
Towards an Inferentialist Account of Information Through Proof-theoretic Semantics
Tamaththul3D: High-Fidelity 3D Saudi Sign Language Avatars from Monocular Video
COPYCOP: Ownership Verification for Graph Neural Networks
Counterargument for Critical Thinking as Judged by AI and Humans
Making AI Drafts Count: A Quality Threshold in Audio Description Workflows
Load more
Made with Slashpage
