AI Research Papers
Explore the latest research papers from arXiv in artificial intelligence, machine learning, and related fields. Discover cutting-edge research from top institutions and researchers worldwide. Total: 27248 papers — Page 121 of 545
SpecForge: Recursive Self-Improvement for Coding Agents via Behavioral Specifications
Oct 11, 2026
4 authors
cs.AIcs.SE
Suggested Is Not Superseded: A Pre-Registered Evaluation of a System-One Model as a Memory-Retirement Gate
Oct 11, 2026
2 authors
cs.AI
TL;QR: Querying Temporal Discursive Patterns in Textual Corpora
Oct 11, 2026
5 authors
cs.CLcs.CYcs.DB+1
History Replays Itself: Unleashing Long-Context Capability in Linear Attention
Oct 11, 2026
13 authors
cs.AIcs.LG
To Cache or Not to Cache: Understanding and Mitigating Safety Incompatibility in Cross-Model KV Cache Reuse
Oct 11, 2026
4 authors
cs.LGcs.CRcs.SE
PhySimCode: A Benchmark and Evaluation Method for Physics Video to Code Generation
Oct 11, 2026
6 authors
cs.CV
Uncovering the Generative Landscape of Diffusion Models: A Spectral-Guided Quality-Diversity Diffusion Framework
Oct 11, 2026
4 authors
cs.LGcs.AI
SkillMarker: A KGW-Based Watermarking Method for Agent Skill Ownership Verification
Oct 11, 2026
6 authors
cs.CRcs.AI
Visually Legible but Adversarial: Watermark-Constrained Attacks on End-to-End VLMs for Document Understanding
Oct 11, 2026
7 authors
cs.CV
A Dependency-Aware Multi-GPU Training Framework for Temporal Graph Neural Networks
Oct 11, 2026
11 authors
cs.LGcs.DC
NepPlural: A Human-Anchored Benchmark for Persona Annotation in Nepali Migration Discourse
Oct 11, 2026
3 authors
cs.CL
ScenePlacer: Reformulating Scene-Level Object Pose Estimation as Visibility Field Learning
Oct 11, 2026
10 authors
cs.CV
Visible but Not Avoided: State-Dependent Re-Proposal of Rejected Candidates in Catalog-Based LLM Optimization Loops
Oct 11, 2026
3 authors
cs.AI
RSAJEV: Training-Free Abstaining Prototype Memory for Eliminating Silent Hallucination in JEV-Based Remote Sensing Classification
Oct 11, 2026
8 authors
cs.CV
SpikeOcc: Towards Resilient Multimodal 3D Occupancy Perception via Spiking Experts
Oct 11, 2026
10 authors
cs.CV
Google Earth AI Geospatial Reasoning Agent: Capabilities and a Systematic Evaluation
Oct 11, 2026
37 authors
cs.AI
Frozen History: When Temporal Losses Stop Accumulation in Learned Real-Time Supersampling
Oct 11, 2026
2 authors
cs.CV
Enhancing Zero-Shot Domain Transfer in Low-Resource Sentiment Analysis: A Case Study in Marathi
Oct 11, 2026
4 authors
cs.CLcs.LG
Hyperbolic Time Series Forecasting with Learnable Decomposition and Manifold Dynamics
Oct 11, 2026
3 authors
cs.LGcs.AI
Robust Marathi Sentiment Analysis using Domain-Adaptive Pre-training and Data Augmentation Approaches
Oct 11, 2026
5 authors
cs.CLcs.LG
SlotAVS: Object-Centric Audio-Visual Segmentation via Bi-Modal Slot Attention
Oct 11, 2026
3 authors
cs.CV
A Decade in a Day: Synthesizing Agent-Native Interfaces from Human-Oriented Software Evolution
Oct 11, 2026
3 authors
cs.SEcs.AI
SurgiCLAW: An Interpretable Atomic-Skill Agent for Precision Robotic Micromanipulation
Oct 11, 2026
5 authors
cs.ROcs.AI
Hand2Robot: Object-Centric 4D Hand Reconstruction from Human Demonstrations for Robotics
Oct 11, 2026
7 authors
cs.ROcs.CV
RSIPO: Recursive Self-Improving Policy Optimization for Agentic Reinforcement Learning via Skill-Policy Co-Evolution
Oct 11, 2026
10 authors
cs.CL
Who Sets the Pace of Judge Hacking? Judge Capability versus the Policy-Judge Gap
Oct 11, 2026
1 authors
cs.LGcs.CL
Heterogeneous Structured Pruning Under Resource Constraints for Hardware-Efficient Large Language Models
Oct 11, 2026
5 authors
cs.LGcs.ARcs.CL
Data-Centric Recursive Self-Improvement for Navigation via Policy-Synchronized Language-Action Dual Bootstrapping
Oct 11, 2026
14 authors
cs.CV
Agent Sociodrama: Social-Dynamics-Guided Persona Recasting for LLM Agent Teams
Oct 11, 2026
3 authors
cs.AIcs.CLcs.MA
Inference on the Value of Policy Improvement in Adaptive Experiments
Oct 11, 2026
3 authors
stat.MLcs.LGecon.EM+1
An Explainable System for Offensive Content Detection in Nastaliq Urdu: Corpus Curation, Transformer Benchmarking, and Word-Level Attribution
Oct 11, 2026
1 authors
cs.CLcs.AI
Passing Tests, Missing Semantics: Evidence of Interpretive Lock-In in Plan-Based DataFrame Code Generation
Oct 11, 2026
5 authors
cs.AIcs.SE
Reference-Efficient Multimodal Bitstream-Corrupted Video Recovery via Depth-Conditioned Adaptation
Oct 11, 2026
7 authors
cs.CV
Adaptive Look, Flexible Thought: Learning How and How Long to Think in Multimodal Reasoning
Oct 11, 2026
8 authors
cs.CVcs.AIcs.CL
ChangeT$^3$: Evaluating Vision Test-Time Training for Remote Sensing Change Detection
Oct 11, 2026
6 authors
cs.CV
ML-CLAPPS: A Probabilistic Framework for Imbalanced Multilabel Learning under Class Prioritization
Oct 11, 2026
5 authors
cs.LGcs.CVstat.ML
Benchmarking Deep Learning Models for Anomaly Detection in Real-World Cloud Telemetry
Oct 11, 2026
2 authors
cs.LGcs.DC
Guarded Block Transfers for Polytope Distance: Linear Convergence with Explicit Constants and Gap-Certified Screening for SVM Training
Oct 11, 2026
1 authors
cs.LG
How Shared Representations Become Specialized: Formation, Maintenance, and Latent Susceptibility
Oct 11, 2026
1 authors
cs.LGcs.NE
Latent Taxonomies: How Property Induction Develops in Language Model Pre-training
Oct 11, 2026
5 authors
cs.CLcs.LG