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 73 of 555
BiShield-TEE: On the (In-)Security of Unilateral Weight Obfuscation in On-Device TEE-Shielded LLM Partition
Oct 15, 2026
6 authors
cs.CRcs.AI
Sharp and Stable Label-Free Calibration Certificates from Logical Coherence
Oct 15, 2026
1 authors
cs.LGstat.ML
From Perception to Prediction and Intervention: Benchmarking Proactive Video Assistants in Real-Life Scenarios
Oct 15, 2026
8 authors
cs.LG
Decoupled Safety Control: A Safety-Control Algorithm for Training-Free Safety Guidance
Oct 15, 2026
7 authors
cs.CV
Independent Data-Integrity Verification for LLM-Driven Functional Coverage Closure in Hardware Design
Oct 15, 2026
1 authors
cs.ARcs.AIcs.SE
MYOPIA: Understanding the Limits of Tree-Based Reasoning in Vision-Language Models
Oct 15, 2026
5 authors
cs.CV
Learning to Search for Executable Patternmaking from Certified Programs
Oct 15, 2026
5 authors
cs.LGcs.AIcs.GR
ClaimScope: Label-Blind Witness Verification for Mathematical Claim Auditing
Oct 15, 2026
1 authors
cs.AIcs.LG
Transfer Learning in Bandits from Unknown Adaptive Policies: Problem-Dependent Lower and Upper Bounds
Oct 15, 2026
4 authors
cs.LG
AVALON: Zero-Shot Indoor Navigation with Human-Seeded Topological Memory
Oct 15, 2026
8 authors
cs.ROcs.AI
Hear, Localize, and Reason: Spatially Aware Scene Understanding for Audio-Visual LLMs
Oct 15, 2026
7 authors
cs.CVcs.SD
LOADBench: A Large Open Analog Dataset and Benchmark for Machine Learning in IC Design
Oct 15, 2026
10 authors
cs.AI
LoopAhead: Speculating Ahead for Faster Decoding in Looped Language Models
Oct 15, 2026
7 authors
cs.AIcs.LG
Decoding What iOS Location Services Send to Apple: An LLM Is an Unreliable Analyst but a Useful Toolmaker
Oct 15, 2026
1 authors
cs.NIcs.AI
Waypoint-OPD: Transferring RL-Induced Policy Shifts via Gated On-Policy Distillation
Oct 15, 2026
7 authors
cs.LGcs.CL
Evaluating Inquiry Learning in LLM-Based Agents: Hypothesizing, Reasoning, and Exploration
Oct 15, 2026
5 authors
cs.AI
A Decision-Aware Evaluation Protocol for Uncertainty in Medical Image Segmentation
Oct 15, 2026
2 authors
cs.CV
AgentPerturb: Evaluating LLM Agent Robustness under Controlled Interaction Perturbations
Oct 15, 2026
8 authors
cs.AI
ContextLift: Breaking the Spurious Correlation Behind Conditional Emergent Misalignment
Oct 15, 2026
2 authors
cs.CLcs.LG
Anchor3DGS: Feed-Forward 3D Gaussian Splatting with Compact Anchor-Based Representation
Oct 15, 2026
6 authors
cs.CV
Spurious Attention Heads in Vision Transformers: Mechanistic Identification of Annotation-Driven Bias in Medical Chest X-Ray Analysis
Oct 15, 2026
2 authors
cs.CVcs.CL
DIAL: Dynamic and Informed Adjustment of the Native Stochastic Law for Reliable Weather Ensembles
Oct 15, 2026
7 authors
cs.CV
SCMerge: Spatial-Consistency-Aware Token Pair Merging for Efficient Semantic Segmentation
Oct 15, 2026
3 authors
cs.CV
Efficient Pairwise Difference Learning: A Comparative Study of Encoding Strategies and Training Pair Selection
Oct 15, 2026
3 authors
cs.LGcs.AI
Digital Typhoon Dataset V3: Benchmarking for Multi-spectral Extension and Analyzing Systematic Bias in Intensity Regression
Oct 15, 2026
5 authors
cs.CV
Conditional Mean Flows: Few-Step Densities for Simulation-Based Inference
Oct 15, 2026
3 authors
stat.MLcs.LG
When Does "Post-Call" Begin? An Availability Contract for Earnings-Call NLP Benchmarks
Oct 15, 2026
4 authors
q-fin.CPcs.CLcs.LG
Approaching Backpropagation Accuracy with Weight Perturbation on MNIST
Oct 15, 2026
1 authors
cs.LGcs.NE
FusionAudit: Pathway-Conditioned Robustness Auditing for Native Multimodal Models
Oct 15, 2026
6 authors
cs.CV
Enhancing Multimodal RLVR with Pairwise Token Contrast and Adaptive Trajectory Confidence
Oct 15, 2026
6 authors
cs.CL
Classical methods for modern applications: synthetic tabular data generation using lightweight discrete response continuous latent variable model
Oct 15, 2026
2 authors
cs.LGstat.ML
No Single Tokenizer Feature Reliably Predicts Downstream Language Model Performance
Oct 15, 2026
6 authors
cs.CL
Data Strategies for Large Language Models: A Unified Perspective on the Training Lifecycle
Oct 15, 2026
10 authors
cs.CL
Router Drift Control: Mitigating Off-Policy Degradation in Mixture-of-Experts Reinforcement Learning
Oct 15, 2026
11 authors
cs.LGcs.AI
MARS: A Momentum-Aware Adaptive Rating System for Personalized Assessment
Oct 15, 2026
3 authors
cs.CYcs.LG
Abstracts or full text? Evaluating input scope and computational efficiency in biomedical lay summarization
Oct 15, 2026
3 authors
cs.CL
ShiftQAT: Quantization-Aware Training for the Numerical Contract of a Fixed-Function Edge CNN Accelerator
Oct 15, 2026
3 authors
cs.LG