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: 27748 papers — Page 72 of 555
ManiFusion: Unlocking the High-Throughput Generation via Superposition in Manifold Space
Oct 15, 2026
5 authors
cs.CVcs.LG
Policy-Aligned Predictive Verification for Adaptive VLA Action-Chunk Execution
Oct 15, 2026
7 authors
cs.ROcs.LG
HyCo: Hybrid Drafting for Cost-Efficient Mobile-Cloud Speculative Decoding
Oct 15, 2026
6 authors
cs.CLcs.DCcs.LG
RLDF: A Region-Level Deepfake Dataset and Benchmark for Partial-Face Manipulation Detection
Oct 15, 2026
2 authors
cs.CV
Each Reward to Its Relevant Tokens: Reward-Specific Token-Level Credit Assignment for Multi-Reward RL
Oct 15, 2026
7 authors
cs.LG
SITAR: A Situational Distortion Metric for Automatic Speech Recognition Evaluation
Oct 15, 2026
6 authors
cs.CL
V-SHARE: Provable Convergence Guarantees for Advantage-based Algorithms
Oct 15, 2026
6 authors
cs.LGcs.AI
Incentivizing Tool-Use Reinforcement Learning for Post-Arrival Emergency Care Prediction
Oct 15, 2026
7 authors
cs.AI
X-Fly: Learning to Reach and Stop in Full-Chunk Aerial Vision-Language Navigation
Oct 15, 2026
4 authors
cs.ROcs.AIcs.CV
PET Quantification-Preserving Registration for Longitudinal Whole-Body PSMA PET/CT
Oct 15, 2026
6 authors
cs.CV
Full-Duplex Interaction with Speech, Expressions and Gestures
Oct 15, 2026
8 authors
eess.AScs.AIcs.CV+1
CarryOn: A Dual-Loop Harness for Personalized and Reliable Robot Assistance
Oct 15, 2026
10 authors
cs.ROcs.CV
Translation Circuit Discovery and Targeted Optimization for Low-Resource Multilingual Translation
Oct 15, 2026
4 authors
cs.CL
Trajectory-Level Speculation with Semantic Verification for Tool-Using Agents
Oct 15, 2026
5 authors
cs.CLcs.AIcs.LG
DuET: Note-Frame Dual Encoding for Piano Performance-to-Score Transcription
Oct 15, 2026
2 authors
cs.SDcs.LGeess.AS
Can LLMs Tell Stories Out of Order? A Corpus and Benchmark for Nonlinear Narrative Generation
Oct 15, 2026
4 authors
cs.CLcs.AI
Cross-Prompt Inference Mitigates Rare-Class Suppression in Imbalanced VLM Finetuning
Oct 15, 2026
5 authors
cs.CV
Tool-Augmented Large Language Models for Reliable Medical Calculation from Patient Notes
Oct 15, 2026
7 authors
cs.AI
FlashAttention with Statistics: Low-Overhead Attention Features for Compact Hallucination Detectors
Oct 15, 2026
6 authors
cs.AI
MetaExp: Learning to Self-Improve through Experience via Verifiable Cross-Task Environment Scaling
Oct 15, 2026
7 authors
cs.AI
When the KV Cache Is Slower Than the GPU: Scaling Remote KV Tiers for Context-Parallel Prefill
Oct 15, 2026
1 authors
cs.DCcs.LG
ISW-Agent: Integrating LLM-Driven Dialogue with n8n Workflow for Internal Solitary Wave Remote Sensing Image Processing
Oct 15, 2026
4 authors
cs.AI
FilterFusion: Prior-Guided Adaptive Filter Fusion for Efficient Video Denoising
Oct 15, 2026
6 authors
cs.CV
Decomposing Brain-LLM Alignment with Interpretable Semantic Representations
Oct 15, 2026
2 authors
cs.AIcs.CL
QREF: Improving DeepSearch Agents by Aligning Search with Reasoning via Query Refinement and Evidence Filtering
Oct 15, 2026
18 authors
cs.AI
SCRIBE: Scalable Contextual Representations of Interpretable Brain-Grounded Semantics
Oct 15, 2026
4 authors
cs.AIcs.CL
Hierarchical Interpretable Multitask Audio Representation Learning: An Analysis of Event-Scene Relationships through the Information Bottleneck
Oct 15, 2026
3 authors
eess.AScs.AI
CriticaLLM: Using LLMs as Autonomous Game Master for Tabletop Role-Playing Games
Oct 15, 2026
4 authors
cs.AI
Functional Subnetwork Localization for Efficient Continual Learning in Large Language Models
Oct 15, 2026
11 authors
cs.AI
Agent Status Protocol (ASP): A Lightweight Specification for State Reporting in Multi-Agent Systems
Oct 15, 2026
5 authors
cs.AIcs.MA
Reinforcement Learning-driven Diffusion Models: Language, Vision, and Beyond
Oct 15, 2026
24 authors
cs.AI
Federated Art Chase: Privacy Leakage and Data Poisoning in Federated Fine-Tuning
Oct 15, 2026
2 authors
cs.LGcs.CR
Finite-Time Guarantees for Constrained Reinforcement Learning under Partial Observability
Oct 15, 2026
5 authors
cs.LG
Writability and the Pathway: A Controlled Study of Knowledge Injection into Addressed Memory
Oct 15, 2026
4 authors
cs.CL
Uncertainty Quantification in Pairwise Difference Learning for Classification
Oct 15, 2026
3 authors
cs.LGcs.AI
When Does Muon Actually Win? A Paired Data-, Time-, and Tuning-Budget Benchmark
Oct 15, 2026
4 authors
cs.LGcs.AI
Reducing the Cost of Qudit State Preparation by Learning a Sparse Structure for SNAP Gates
Oct 15, 2026
5 authors
quant-phcs.LG