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.
LUT-LLM: Efficient Large Language Model Inference with Memory-based Computations on FPGAs
COFAP: A Universal Framework for COFs Adsorption Prediction through Designed Multi-Modal Extraction and Cross-Modal Synergy
DialectalArabicMMLU: Benchmarking Dialectal Capabilities in Arabic and Multilingual Language Models
Advantage Shaping as Surrogate Reward Maximization: Unifying Pass@K Policy Gradients
Towards a Practical Understanding of Lagrangian Methods in Safe Reinforcement Learning
What "Not" to Detect: Negation-Aware VLMs via Structured Reasoning and Token Merging
Your VAR Model is Secretly an Efficient and Explainable Generative Classifier
Understanding Temporal Logic Consistency in Video-Language Models through Cross-Modal Attention Discriminability
StaR-KVQA: Structured Reasoning Traces for Implicit-Knowledge Visual Question Answering
Auditing Pay-Per-Token in Large Language Models
Learning to Interpret Weight Differences in Language Models
Pretraining with hierarchical memories: separating long-tail and common knowledge
Learning to Generate Rigid Body Interactions with Video Diffusion Models
Explore Briefly, Then Decide: Mitigating LLM Overthinking via Cumulative Entropy Regulation
CurES: From Gradient Analysis to Efficient Curriculum Learning for Reasoning LLMs
Towards A Transferable Acceleration Method for Density Functional Theory
A Kernel Space-based Multidimensional Sparse Model for Dynamic PET Image Denoising
Randomness and signal propagation in physics-informed neural networks (PINNs): A neural PDE perspective
Taming Video Models for 3D and 4D Generation via Zero-Shot Camera Control
Masked Diffusion Models as Energy Minimization
Risk-Bounded Multi-Agent Visual Navigation via Iterative Risk Allocation
Can synthetic data reproduce real-world findings in epidemiology? A replication study using adversarial random forests
Long Chain-of-Thought Reasoning Across Languages
From Knowledge to Conjectures: A Modal Framework for Reasoning about Hypotheses
DMFI: A Dual-Modality Log Analysis Framework for Insider Threat Detection with LoRA-Tuned Language Models
Packet-Level DDoS Data Augmentation Using Dual-Stream Temporal-Field Diffusion
On Arbitrary Predictions from Equally Valid Models
Graph Structure Learning with Privacy Guarantees for Open Graph Data
Latent Policy Steering with Embodiment-Agnostic Pretrained World Models
Characterizing State Space Model and Hybrid Language Model Performance with Long Context
Chain of Retrieval: Multi-Aspect Iterative Search Expansion and Post-Order Search Aggregation for Full Paper Retrieval
Knowledge Fusion via Bidirectional Information Aggregation
The Impact of LLM-Assistants on Software Developer Productivity: A Systematic Review and Mapping Study
Segmenting Visuals With Querying Words: Language Anchors For Semi-Supervised Image Segmentation
Theory-Grounded Evaluation of Human-Like Fallacy Patterns in LLM Reasoning
Generalized Incremental Learning under Concept Drift across Evolving Data Streams
Stochastically Dominant Peer Prediction
Do LLMs Understand Collaborative Signals? Diagnosis and Repair
Architectural Backdoors for Within-Batch Data Stealing and Model Inference Manipulation
FRIREN: Beyond Trajectories -- A Spectral Lens on Time
MolLangBench: A Comprehensive Benchmark for Language-Prompted Molecular Structure Recognition, Editing, and Generation
MobileIPL: Enhancing Mobile Agents Thinking Process via Iterative Preference Learning
RoboFAC: A Comprehensive Framework for Robotic Failure Analysis and Correction
Uniform Loss vs. Specialized Optimization: A Comparative Analysis in Multi-Task Learning
An evolutionary perspective on modes of learning in Transformers
Must Read: A Comprehensive Survey of Computational Persuasion
AlphaZero-Edu: Democratizing Access to AlphaZero
DIP: Efficient Large Multimodal Model Training with Dynamic Interleaved Pipeline
Scalable Multi-Task Learning through Spiking Neural Networks with Adaptive Task-Switching Policy for Intelligent Autonomous Agents
Adaptive Insurance Reserving with CVaR-Constrained Reinforcement Learning under Macroeconomic Regimes
Breaking the Silence: A Dataset and Benchmark for Bangla Text-to-Gloss Translation
Levels of Analysis for Large Language Models
Interpretable Deep Learning Framework for Improved Disease Classification in Medical Imaging
UASTrack: A Unified Adaptive Selection Framework with Modality-Customization in Single Object Tracking
RLHF in an SFT Way: From Optimal Solution to Reward-Weighted Alignment
Enhanced Structured Lasso Pruning with Class-wise Information
DesCLIP: Robust Continual Learning via General Attribute Descriptions for VLM-Based Visual Recognition
A Hybrid Framework for Reinsurance Optimization: Integrating Generative Models and Reinforcement Learning
A Training-free Method for LLM Text Attribution
Meta-Transfer Learning Powered Temporal Graph Networks for Cross-City Real Estate Appraisal
Imaging foundation model for universal enhancement of non-ideal measurement CT
Strongly-polynomial time and validation analysis of policy gradient methods
Cognitive Spillover in Human-AI Teams
Batch Entanglement Detection in Parameterized Qubit States using Classical Bandit Algorithms
HPE-CogVLM: Advancing Vision Language Models with a Head Pose Grounding Task
Towards Urban General Intelligence: A Review and Outlook of Urban Foundation Models
Better Generative Replay for Continual Federated Learning
Policy Optimization over General State and Action Spaces
Multi-Step First: A Lightweight Deep Reinforcement Learning Strategy for Robust Continuous Control with Partial Observability
Human strategic decision making in parametrized games
FormalEvolve: Neuro-Symbolic Evolutionary Search for Diverse and Prover-Effective Autoformalization
Secure Linear Alignment of Large Language Models
Algorithmic Trading Strategy Development and Optimisation
Computational Concept of the Psyche
Benchmarking Zero-Shot Reasoning Approaches for Error Detection in Solidity Smart Contracts
When OpenClaw Meets Hospital: Toward an Agentic Operating System for Dynamic Clinical Workflows
LLMs can construct powerful representations and streamline sample-efficient supervised learning
Detecting Intrinsic and Instrumental Self-Preservation in Autonomous Agents: The Unified Continuation-Interest Protocol
Curveball Steering: The Right Direction To Steer Isn't Always Linear
The FABRIC Strategy for Verifying Neural Feedback Systems
A Hierarchical Error-Corrective Graph Framework for Autonomous Agents with LLM-Based Action Generation
Deconstructing Multimodal Mathematical Reasoning: Towards a Unified Perception-Alignment-Reasoning Paradigm
S5-SHB Agent: Society 5.0 enabled Multi-model Agentic Blockchain Framework for Smart Home
Architecting Trust in Artificial Epistemic Agents
RE-MCDF: Closed-Loop Multi-Expert LLM Reasoning for Knowledge-Grounded Clinical Diagnosis
EvoOpt-LLM: Evolving industrial optimization models with large language models
Explore with Long-term Memory: A Benchmark and Multimodal LLM-based Reinforcement Learning Framework for Embodied Exploration
Are Your Reasoning Models Reasoning or Guessing? A Mechanistic Analysis of Hierarchical Reasoning Models
The Illusion of AI Expertise Under Uncertainty: Navigating Elusive Ground Truth via a Probabilistic Paradigm
Social Comparison without Explicit Inference of Others' Reward Values: A Constructive Approach Using a Probabilistic Generative Model
Massive Editing for Large Language Models Based on Dynamic Weight Generation
Conflict-Aware Fusion: Mitigating Logic Inertia in Large Language Models via Structured Cognitive Priors
Stable diffusion models reveal a persisting human and AI gap in visual creativity
Think, Speak, Decide: Language-Augmented Multi-Agent Reinforcement Learning for Economic Decision-Making
RadHiera: Semantic Hierarchical Reinforcement Learning for Medical Report Generation
Spilling the Beans: Teaching LLMs to Self-Report Their Hidden Objectives
From Five Dimensions to Many: Large Language Models as Precise and Interpretable Psychological Profilers
DeepCompress: A Dual Reward Strategy for Dynamically Exploring and Compressing Reasoning Chains
TRI-DEP: A Trimodal Comparative Study for Depression Detection Using Speech, Text, and EEG
Towards Unified World Models for Visual Navigation via Memory-Augmented Planning and Foresight
Load more
Made with Slashpage
