haebom
Sign In
Daily Arxiv
全世界で発刊される人工知能関連論文をまとめるページです。
このページはGoogle Geminiを活用して要約整理し、非営利で運営されています。
論文の著作権は著者とその機関にあります。
This service is supported by Google Gemini.
The Surprising Effectiveness of Canonical Knowledge Distillation for Semantic Segmentation
AHASD: Asynchronous Heterogeneous Architecture for LLM Adaptive Drafting Specialtive Decoding on Mobile Devices
Faithfulness-QA: A Counterfactual Entity Substitution Dataset for Training Context-Faithful RAG Models
DiRe-RAPIDS: Topology-faithful dimensionality reduction at scale
The Role of Symmetry in Optimizing Overparameterized Networks
Towards Unified Multi-task EEG Analysis with Low-Rank Adaptation
Frontier Coding Agents Can Now Implement an AlphaZero Self-Play Machine Learning Pipeline For Connect Four That Performs Comparably to an External Solver
ViPO: Visual Preference Optimization at Scale
ADE：Adaptive Dictionary Embeddings - Scaling Multi-Anchor Representations to Large Language Models
A Comparative Analysis on the Performance of Upper Confidence Bound Algorithms in Adaptive Deep Neural Networks
TCOD: Exploring Temporal Curriculum in On-Policy Distillation for Multi-turn Autonomous Agents
Inverting Foundation Models of Brain Function with Simulation-Based Inference
How Do AI Agents Spend Your Money? Analyzing and Predicting Token Consumption in Agentic Coding Tasks
Semantic Error Correction and Decoding for Short Block Codes
A Co-Evolutionary Theory of Human-AI Coexistence: Mutualism, Governance, and Dynamics in Complex Societies
Reliability Auditing for Downstream LLM tasks in Psychiatry: LLM-Generated Hospitalization Risk Scores
Causal Disentanglement for Full-Reference Image Quality Assessment
Open-H-Embodiment: A Large-Scale Dataset for Enabling Foundation Models in Medical Robotics
Curiosity-Critic: Cumulative Prediction Error Improvement as a Tractable Intrinsic Reward for World Model Training
IDOBE: Infectious Disease Outbreak forecasting Benchmark Ecosystem
Provable Coordination for LLM Agents via Message Sequence Charts
Co-generation of Layout and Shape from Text via Autoregressive 3D Diffusion
Don't Retrieve, Navigate: Distilling Enterprise Knowledge into Navigable Agent Skills for QA and RAG
Awakening Dormant Experts:Counterfactual Routing to Mitigate MoE Hallucinations
Diffusion Language Models for Speech Recognition
Graph Propagated Projection Unlearning: A Unified Framework for Vision and Audio Discriminative Models
Rethinking Satellite Image Restoration for Onboard AI: A Lightweight Learning-Based Approach
SkillForge: Forging Domain-Specific, Self-Evolving Agent Skills in Cloud Technical Support
A Self-Calibrating Framework for Analog Circuit Sizing Using LLM-Derived Analytical Equations
Retrieval-Augmented LLMs for Evidence Localization in Clinical Trial Recruitment from Longitudinal EHR Narratives
DC-Ada: Reward-Only Decentralized Sensor Adaptation for Heterogeneous Multi-Robot Teams
Why Attend to Everything? Focus is the Key
Generative models on phase space
Woosh: A Sound Effects Foundation Model
Unilateral Relationship Revision Power in Human-AI Companion Interaction
Adaptive Layerwise Perturbation: Unifying Off-Policy Corrections for LLM RL
Integrating Weather Foundation Model and Satellite to Enable Fine-Grained Solar Irradiance Forecasting
Assessing the Utility of Volumetric Motion Fields for Radar-based Precipitation Nowcasting with Physics-informed Deep Learning
SciMDR: Advancing Scientific Multimodal Document Reasoning
Rethinking the Harmonic Loss via Non-Euclidean Distance Layers
Causally Sufficient and Necessary Feature Expansion for Class-Incremental Learning
TildeOpen LLM: Leveraging Curriculum Learning to Achieve Equitable Language Representation
CoFL: Continuous Flow Fields for Language-Conditioned Navigation
Evaluating the relationship between regularity and learnability in recursive numeral systems using Reinforcement Learning
ReLoop: Structured Modeling and Behavioral Verification for Reliable LLM-Based Optimization
Affective Flow Language Model for Emotional Support Conversation
ELIQ: A Label-Free Framework for Quality Assessment of Evolving AI-Generated Images
HER: Human-like Reasoning and Reinforcement Learning for LLM Role-playing
Bridging Visual and Wireless Sensing via a Unified Radiation Field for 3D Radio Map Construction
Glance-or-Gaze: Incentivizing LMMs to Adaptively Focus Search via Reinforcement Learning
AdaFRUGAL: Adaptive Memory-Efficient Training with Dynamic Control
Safety Is Not Universal: The Selective Safety Trap in LLM Alignment
Training-Free Adaptation of New-Generation LLMs using Legacy Clinical Models
Q3-MuPa: Quick, Quiet, Quantitative Multi-Parametric MRI using Physics-Informed Diffusion Models
PRAXIS: Integrating Program Analysis with Observability for Root-Cause Analysis
Consist-Retinex: One-Step Noise-Emphasized Consistency Training Accelerates High-Quality Retinex Enhancement
Value-Guided Iterative Refinement and the DIQ-H Benchmark for Evaluating VLM Robustness
Inferix: A Block-Diffusion based Next-Generation Inference Engine for World Simulation
Stress Testing Factual Consistency Metrics for Long-Document Summarization
EvoDev: An Iterative Feature-Driven Framework for End-to-End Software Development with LLM-based Agents
FedPF: Accurate Target Privacy Preserving Federated Learning Balancing Fairness and Utility
Rethinking Entropy Interventions in RLVR: An Entropy Change Perspective
A Survey of Process Reward Models: From Outcome Signals to Process Supervisions for Large Language Models
Emergent Coordination in Multi-Agent Language Models
Auto-ARGUE: LLM-Based Report Generation Evaluation
PATCH: Learnable Tile-level Hybrid Sparsity for LLMs
Hybrid Diffusion for Simultaneous Symbolic and Continuous Planning
Vibe Check: Understanding the Effects of LLM-Based Conversational Agents' Personality and Alignment on User Perceptions in Goal-Oriented Tasks
The Fools are Certain; the Wise are Doubtful: Exploring LLM Confidence in Code Completion
Robust Federated Learning under Adversarial Attacks via Loss-Based Client Clustering
GoViG: Goal-Conditioned Visual Navigation Instruction Generation via Multimodal Reasoning
Vertex Features for Neural Global Illumination
Neural Bridge Processes
Beyond the Leaderboard: Rethinking Medical Benchmarks for Large Language Models
PBiLoss: Popularity-Aware Regularization to Improve Fairness in Graph-Based Recommender Systems
Treatment, evidence, imitation, and chat
Efficient Traffic Forecasting on Large-Scale Road Network by Regularized Adaptive Graph Convolution
MINOS: A Multimodal Evaluation Model for Bidirectional Generation Between Image and Text
Time Blindness: Why Video-Language Models Can't See What Humans Can?
Lunguage: A Benchmark for Structured and Sequential Chest X-ray Interpretation
RetroMotion: Retrocausal Motion Forecasting Models are Instructable
Data Balancing Strategies: A Systematic Survey of Resampling and Augmentation Methods
OT Score: An OT based Confidence Score for Prototype-Assisted Source Free Unsupervised Domain Adaptation
A Survey on the Safety and Security Threats of Computer-Using Agents: JARVIS or Ultron?
Open Challenges in Multi-Agent Security: Towards Secure Systems of Interacting AI Agents
M2R2: MultiModal Robotic Representation for Temporal Action Segmentation
TinyR1-32B-Preview: Boosting Accuracy with Branch-Merge Distillation
Is Human-Like Text Liked by Humans? Multilingual Human Detection and Preference Against AI
A Practice of Post-Training on Llama-3 70B with Optimal Selection of Additional Language Mixture Ratio
Learning to Ask: When LLM Agents Meet Unclear Instruction
ComboStoc: Combinatorial Stochasticity for Diffusion Generative Models
Data-Centric Foundation Models in Computational Healthcare: A Survey
Identifying the Achilles' Heel: An Iterative Method for Dynamically Uncovering Factual Errors in Large Language Models
OxyGent: Making Multi-Agent Systems Modular, Observable, and Evolvable via Oxy Abstraction
The Price of Agreement: Measuring LLM Sycophancy in Agentic Financial Applications
A Dual Perspective on Synthetic Trajectory Generators: Utility Framework and Privacy Vulnerabilities
ClawEnvKit: Automatic Environment Generation for Claw-Like Agents
Beyond Text-Dominance: Understanding Modality Preference of Omni-modal Large Language Models
Benchmarks for Trajectory Safety Evaluation and Diagnosis in OpenClaw and Codex: ATBench-Claw and ATBench-Codex
A Framework for Longitudinal Health AI Agents
Load more
Made with Slashpage
