Daily Arxiv

New

This is a page that organizes artificial intelligence-related papers published around the world.
This page is summarized using Google Gemini and is operated on a non-profit basis.
The copyright for the paper belongs to the author and the relevant institution, and you only need to cite the source when sharing the abstract.
This service is supported by Google Gemini.

Chatterbox-Flash: Prior-Calibrated Block Diffusion for Streaming Zero-Shot TTS

Prior Availability in Industrial Visual Sim-to-Real: A Review of CAD-Guided and CAD-Unavailable Regimes

Updating the standard neuron model in artificial neural networks

Self-Trained Verification for Training- and Test-Time Self-Improvement

Qwen-VLA: Unifying Vision-Language-Action Modeling across Tasks, Environments, and Robot Embodiments

CalArena: A Large-Scale Post-Hoc Calibration Benchmark

Dissociative Identity: Language Model Agents Lack Grounding for Reputation Mechanisms

Beyond MSE: Improving Precipitation Nowcasting with Multi-Quantile Regression

HoliTok:A Coutinuous Holistic Tokenization with Robust Dual Capabilities of Speech Generation and Understanding

GiPL: Generative augmented iterative Pseudo-Labeling for Cross-Domain Few-Shot Object Detection

AnyMo: Scaling Any-Modality Conditional Motion Generation with Masked Modeling

Honest Lying: Understanding Memory Confabulation in Reflexive Agents

BlockBatch: Multi-Scale Consensus Decoding for Efficient Diffusion Language Model Inference

TIMEGATE: Sustainable Time-Boxed Promotion Gates for Continual ML Adaptation Under Resource Constraints

GEO-Bench: Benchmarking Ranking Manipulation in Generative Engine Optimization

Hallucination Detection-Guided Preference Optimization for Clinical Summary

BenGER: Benchmarking LLM Systems on Subsumption-Based Legal Reasoning in German Law

Generic Interpretation Approach for Transformer Models Incorporating Heterogenous Attention Structures

Cast a Wider Net: Coordinated Pass@K Policy Optimization for Code Reasoning

Knowledge Graphs as the Missing Data Layer for LLM-Based Industrial Asset Operations

Beyond Trajectory-Level Attribution: Graph-Based Credit Assignment for Agentic Reinforcement Learning

Targeted Remasking: Replacing Token Editing with Token-to-Mask Refinement in Discrete Diffusion Language Models

Algorithmic Fragility and Persona Bias in LLM - Generated Autistic Communication

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

Channel-wise Vector Quantization

Rethinking Weak Supervision in Anomaly Detection: A Comprehensive Benchmark

Treatment Effect Estimation with Differentiated Networked Effect on Graph Data

CRISP -- Clustering-Based Redundancy-Reduced Instance Sampling for Pathology Case Representation and Retrieval

Attested Tool-Server Admission: A Security Extension to the Model Context Protocol

Task-Aligned Self-Supervised Learning for Medical Image Analysis: A Systematic Review and Practical Design Guidelines

Co-Fusion4D: Spatio-temporal Collaborative Fusion for Robust 3D Object Detection

Can Vision Models Truly Forget? Mirage: Representation-Level Certification of Visual Unlearning

Lying Is Just a Phase: The Hidden Alignment Transition in Language Model Scaling

Balancing Knowledge Distillation for Imbalance Learning with Bilevel Optimization

DynMuon: A Dynamic Spectral Shaping View of Muon

Privacy Policy Enforcement Guardrails for Data-Sensitive Retrieval-Augmented Generation

Physics-Guided Geometric Diffusion for Macro Placement Generation

Avoiding Structural Failure Modes in Tabular Fair SSL: Online Primal-Dual Allocation under Confidence Gating

PBT-Bench: Benchmarking AI Agents on Property-Based Testing

Beyond AI as Assistants: Toward Autonomous Discovery in Cosmology

Topology-Preserving Neural Operator Learning via Hodge Decomposition

AttenA+: Rectifying Action Inequality in Robotic Foundation Models

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

Towards a holistic understanding of Selection Bias for Causal Effect Identification

CLIP Tricks You: Training-free Token Pruning for Efficient Pixel Grounding in Large VIsion-Language Models

Revisiting Reinforcement Learning with Verifiable Rewards from a Contrastive Perspective

RISED: A Pre-Deployment Evaluation Framework for High-Stakes AI Decision-Support Systems, with Application to Healthcare

REALISTA: Realistic Latent Adversarial Attacks that Elicit LLM Hallucinations

Multi-Rollout On-Policy Distillation via Peer Successes and Failures

OGLS-SD: On-Policy Self-Distillation with Outcome-Guided Logit Steering for LLM Reasoning

The Cartesian Shortcut: Re-evaluate Vision Reasoning in Polar Coordinate Space

Cornerstones or Stumbling Blocks? Deciphering the Rock Tokens in On-Policy Distillation

Normalization Equivariance for Arbitrary Backbones, with Application to Image Denoising

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

Why Self-Inconsistency Arises in GNN Explanations and How to Exploit It

Do Joint Audio-Video Generation Models Understand Physics?

MidSteer: Optimal Affine Framework for Steering Generative Models

Gradients with Respect to Semantics Preserving Embeddings Tell the Uncertainty of Large Language Models

STABLEVAL: Disagreement-Aware and Stable Evaluation of AI Systems

Possibilistic Predictive Uncertainty for Deep Learning

Beyond Visual Fidelity: Benchmarking Super-Resolution Models for Large-Scale Remote Sensing Imagery via Downstream Task Integration

Defeasible Conditional Obligation in a Two-tiered Preference-based Semantics (Extended Version)

MedSynapse-V: Bridging Visual Perception and Clinical Intuition via Latent Memory Evolution

How Can Reinforcement Learning Achieve Expert-level Placement?

FlowPlace: Flow Matching for Chip Placement

Deep Interest Mining for Intent-Enriched Semantic IDs in Multimodal Generative Recommendation

BEAT: Tokenizing and Generating Symbolic Music by Uniform Temporal Steps

Dual-Anchoring: Addressing State Drift in Vision-Language Navigation

Reward Score Matching: Unifying Reward-based Fine-tuning for Flow and Diffusion Models

Just Type It in Isabelle! AI Agents Drafting, Mechanizing, and Generalizing from Human Hints

Representation over Routing: Diagnosing Temporal Routing Pathologies in Multi-Timescale PPO

TInR: Exploring Tool-Internalized Reasoning in Large Language Models

SCOPE: Signal-Calibrated On-Policy Distillation Enhancement with Dual-Path Adaptive Weighting

Vibe-driven model-based engineering

AffordGen: Generating Diverse Demonstrations for Generalizable Object Manipulation with Afford Correspondence

Genie 4D: Semantic-Prior-Guided 4D Dynamic Scene Reconstruction

Beyond Offline A/B Testing: Context-Aware Agent Simulation for Recommender System Evaluation

Frequency-Enhanced Diffusion Models: Curriculum-Guided Semantic Alignment for Zero-Shot Skeleton Action Recognition

U-Cast: A Surprisingly Simple and Efficient Frontier Probabilistic AI Weather Forecaster

Multi-Modal Learning meets Genetic Programming: Analyzing Alignment in Latent Space Optimization

AtomEval: Validity-Aware Atomic Evaluation of Adversarial Claim Rewriting in Fact Verification

Distributional Open-Ended Evaluation of LLM Cultural Value Alignment Based on Value Codebook

CalM: A Self-Supervised Foundation Model for Population Dynamics in Calcium Imaging Data

Automated Conjecture Resolution with Formal Verification

Acoustic and perceptual differences between standard and accented speech and their voice clones

Understand and Accelerate Memory Processing Pipeline for Large Language Model Inference

Incentives, Equilibria, and the Limits of Healthcare AI: A Game-Theoretic Perspective

EuraGovExam: A Multilingual Multimodal Benchmark from Real-World Civil Service Exams

Limits of Spatial Imagery Reasoning in Frontier LLM Models

Claudini: Autoresearch Discovers State-of-the-Art Adversarial Attack Algorithms for LLMs

Large Language Model Guided Incentive Aware Reward Design for Cooperative Multi-Agent Reinforcement Learning

{\Lambda}Split: Self-Supervised Content-Aware Spectral Unmixing for Fluorescence Microscopy

Failure of contextual invariance in large language models

Graph Energy Matching: Transport-Aligned Energy-Based Modeling for Graph Generation

AgentDS Technical Report: Benchmarking the Future of Human-AI Collaboration in Domain-Specific Data Science

Beyond String Matching: Semantic Evaluation of PDF Table Extraction

To See or To Please: Uncovering Visual Sycophancy and Split Beliefs in VLMs

MineDraft: A Framework for Batch Parallel Speculative Decoding

Scicode-lint: Detecting Methodology Bugs in Scientific Python Code with LLM-Generated Patterns

Context Matters: Repository-Aware Security Analysis of the Agent Skill Ecosystem

Share

Advanced Prediction of Hypersonic Missile Trajectories with CNN-LSTM-GRU Architectures

Author

Haebom

Category

Empty

저자

Amir Hossein Baradaran

개요

본 논문은 극초음속 미사일의 궤적 예측을 위한 새로운 하이브리드 심층 학습 접근 방식을 제시합니다. 합성곱 신경망(CNN), 장단기 메모리(LSTM) 네트워크, 그리고 게이트 순환 단위(GRU)를 통합하여 극초음속 미사일의 복잡한 궤적을 고정확도로 예측하는 방법을 제안합니다. 이 연구는 방위 시스템의 예측 능력 향상에 있어서 고급 기계 학습 기술의 잠재력을 보여줍니다. 이는 국가 안보 및 안전을 위한 방위 산업 발전에 중요한 기여를 할 수 있습니다.

시사점, 한계점

•

시사점:

◦

극초음속 미사일 궤적 예측의 정확도 향상에 기여

◦

방위 시스템의 예측 능력 향상 및 미사일 요격 기술 발전에 기여

◦

CNN, LSTM, GRU의 하이브리드 모델을 통한 심층 학습의 효용성을 증명

◦

국가 안보 및 안전 강화에 기여

•

한계점:

◦

실제 데이터를 사용한 검증 부족 (논문에 명시되지 않음)

◦

모델의 일반화 성능 및 다양한 환경에 대한 적용성에 대한 추가 연구 필요 (논문에 명시되지 않음)

◦

하이퍼파라미터 최적화 및 모델 복잡도에 대한 추가적인 분석 필요 (논문에 명시되지 않음)

◦

다른 궤적 예측 모델과의 비교 분석 부족 (논문에 명시되지 않음)

Made with Slashpage