Daily Arxiv

New

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.

Preference-Shaped Expected Hypervolume and R2 Improvement: Exact Computation and Monotonicity

ProRL: Effective Reinforcement Learning for Proactive Recommendation via Rectified Policy Gradient Estimation

QuITE: Query-Based Irregular Time Series Embedding

ROVER: Routing Object-Centric Visual Evidence for Grounded Multi-Image Reasoning

BIRDS: Characterizing and Understanding Biodiversity Impact of Large Language Model Serving

EvoSpec: Evolving Speculative Decoding via Real-Time Vocabulary and Parameter Adaptation

From AR to Diffusion: Efficiently Adapting Large Language Models with Strictly Causal and Elastic Horizons

The Alignment Floor: How Persona Customization Breaks Safety in Weakly-Aligned LLMs

Enhancing LLM Medical Coding with Structured External Knowledge

Two Speeds of Learning: A Representation-Readout Decomposition of Grokking and Double Descent

Prospective evaluation of multimodal respiratory failure prediction: Do chest X-rays improve performance beyond EHR signals?

Bridging Classification and Reconstruction: Cooperative Time Series Anomaly Detection

Turning Bias into Bugs: Bandit-Guided Style Manipulation Attacks on LLM Judges

GoQuant: Geometric Orthogonal Residual Projection for Multiplier-Free Power-of-Two Transformer Quantization

Keep the Proof State Live: Snapshotting for Efficient Tactic Search in Lean 4

Autoregression-Free Neural Operators for Time-Dependent PDEs

KYA: A Framework-Agnostic Trust Layer for Autonomous Systems with Verifiable Provenance and Hierarchical Policy Composition

Eureka: Intelligent Feature Engineering for Enterprise AI Cloud Resource Demand Prediction

Theoretical Analysis of Sparse Optimization with Reparameterization, Weight Decay, and Adaptive Learning Rate

HumanEgo: Zero-Shot Robot Learning from Minutes of Human Egocentric Videos

Tiny Brains, Giant Impact: Uncovering the Keystone Neurons of LLM with Just a Few Prompts

Coarse-to-Fine Domain Incremental Learning with Attentive Distillation for Mining Footprint Segmentation in Multispectral Imagery

Nano World Models: A Minimalist Implementation of Future Video Prediction

SSDAU: Structured Semantic Data Augmentation for Joint Entity and Relation Extraction

Reducing Political Manipulation with Consistency Training

The Distillation Game: Adaptive Attacks & Efficient Defenses

JMed48k: A Multi-Profession Japanese Medical Licensing Benchmark for Vision-Language Model Evaluation

Echoes in Filter Bubble: Diagnosing and Curing Popularity Bias in Generative Recommenders

Hilbert-Geo: Solving Solid Geometric Problems by Neural-Symbolic Reasoning

Turning Stale Gradients into Stable Gradients: Coherent Coordinate Descent with Implicit Landscape Smoothing for Lightweight Zeroth-Order Optimization

ProtoMedAgent: Multimodal Clinical Interpretability via Privacy-Aware Agentic Workflows

EVA-Bench: A New End-to-end Framework for Evaluating Voice Agents

AttenA+: Rectifying Action Inequality in Robotic Foundation Models

Many-Shot CoT-ICL: Making In-Context Learning Truly Learn

Teacher-Guided Policy Optimization for On-Policy Reasoning Distillation under Large Policy Divergence

AgentLens: Revealing The Lucky Pass Problem in SWE-Agent Evaluation

Self-Supervised Laplace Approximation for Bayesian Uncertainty Quantification

CaC: Advancing Video Reward Models via Hierarchical Spatiotemporal Concentrating

CalBench: Evaluating Coordination-Privacy Trade-offs in Multi-Agent LLMs

Prune-OPD: Efficient and Reliable On-Policy Distillation for Long-Horizon Reasoning

Aes3D: Aesthetic Assessment in 3D Gaussian Splatting

MedMosaic: A Challenging Large Scale Benchmark of Diverse Medical Audio

When 2D Tasks Meet 1D Serialization: On Serialization Friction in Structured Tasks

Graph Memory Transformer (GMT)

Explainable AI in Speaker Recognition -- Making Latent Representations Understandable

Architecture-Induced Recoverability Bias in Differentiable Symbolic Regression

Causal Disentanglement-Inspired Degradation Representation Learning for Full-Reference Image Quality Assessment

DialToM: A Theory of Mind Benchmark for Forecasting State-Driven Dialogue Trajectories

BEAT: Tokenizing and Generating Symbolic Music by Uniform Temporal Steps

Intent-aligned Autonomous Spacecraft Guidance via Reasoning Models

ReSpinQuant: Efficient Layer-Wise LLM Quantization via Subspace Residual Rotation Approximation

SPEED-Bench: A Unified and Diverse Benchmark for Speculative Decoding

SkillTrojan: Backdoor Attacks on Skill-Based Agent Systems

The Planetary Cost of AI Acceleration, Part II: The 10th Planetary Boundary and the 6.5-Year Countdown

Combating Data Laundering in LLM Training

SelfGrader: LLM Jailbreak Detection via Anchored Token-Level Logits

EvA: An Evidence-First Audio Understanding Paradigm for LALMs

Multi-Level Barriers to Generative AI Adoption Across Disciplines and Professional Roles in Higher Education

Bridge-RAG: An Abstract Bridge Tree Based Retrieval Augmented Generation Algorithm

The Price Reversal Phenomenon: When Cheaper Reasoning Models Cost More

AuthorMix: Modular Authorship Style Transfer via Layer-wise Adapter Mixing

Maximizing Mutual Information Between Prompt and Response Improves LLM Performance With No Additional Data

When Should a Robot Think? Resource-Aware Reasoning via Reinforcement Learning for Embodied Robotic Decision-Making

P$^2$RAG: Efficient Privacy-Preserving RAG Service Supporting Arbitrary Top-$k$ Retrieval

Steering at the Source: Style Modulation Heads for Robust Persona Control

Jailbreak Scaling Laws for Large Language Models: Polynomial-Exponential Crossover

Reasoning Theater: Disentangling Model Beliefs from Chain-of-Thought

Post-Training Language Models for Crosslingual Consistency

MOO: A Multi-view Oriented Observations Dataset for Viewpoint Analysis in Cattle Re-Identification

Relational In-Context Learning via Synthetic Pre-training with Structural Prior

AG-REPA: Causal Layer Selection for Representation Alignment in Audio Flow Matching

Rooted Absorbed Prefix Trajectory Balance with Submodular Replay for GFlowNet Training

JAEGER: Joint 3D Audio-Visual Grounding and Reasoning in Simulated Physical Environments

Who can we trust? LLM-as-a-jury for Comparative Assessment

GICDM: Mitigating Hubness for Reliable Distance-Based Generative Model Evaluation

Beyond Normalization: Rethinking the Partition Function as a Difficulty Scheduler for RLVR

OmniCustom: Sync Audio-Video Customization Via Joint Audio-Video Generation Model

A Language-Guided Bayesian Optimization for Efficient LoRA Hyperparameter Search

S-MARC: Causal Streaming Reasoning for Full-Duplex Conversational Behavior Modeling

Less is Enough: Synthesizing Diverse Data in LLM Feature Space with Sparse Autoencoders

PipeMFL-240K: A Large-scale Dataset and Benchmark for Object Detection in Pipeline Magnetic Flux Leakage Imaging

Scaling Small Agents Through Strategy Auctions

Good SFT Optimizes for SFT, Better SFT Prepares for Reinforcement Learning

Learn from A Rationalist: Distilling Intermediate Interpretable Rationales

Pushing the Limits of Block Rotations in Post-Training Quantization

Reasoning While Asking: Transforming Reasoning Large Language Models from Passive Solvers to Proactive Inquirers

NCSAM Noise-Compensated Sharpness-Aware Minimization for Noisy Label Learning

Grammar-Aware Literate Generative Mathematical Programming with Compiler-in-the-Loop

Mechanism Shift During Post-training from Autoregressive to Masked Diffusion Language Models

CORE-T: COherent REtrieval of Tables for Text-to-SQL

Steering Language Models Before They Speak: Logit-Level Interventions

From Rubrics to Reliable Scores: Evidence-Grounded Text Evaluation with LLM Judges

Thinking Before Constraining: A Unified Decoding Framework for Large Language Models

Differential syntactic and semantic encoding in LLMs

Bridging the Semantic Gap for Categorical Data Clustering via Large Language Models

HD-Prot: A Protein Language Model for Joint Sequence-Structure Modeling with Continuous Structure Tokens

Revisiting the Reliability of Language Models in Instruction-Following

A Review of Learning-Based Motion Planning: Toward a Data-Driven Optimal Control Approach

The Best of the Two Worlds: Harmonizing Semantic and Hash IDs for Sequential Recommendation

E3AD: An Emotion-Aware Vision-Language-Action Model for Human-Centric End-to-End Autonomous Driving

Made with Slashpage