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 161 of 545
Think Before You Paint: Recursive Latent Reasoning for Diffusion Models
Oct 7, 2026
5 authors
cs.AIcs.LG
Layerwise Error Attribution for Fast and Robust Mixed-Precision Post-Training Quantization
Oct 7, 2026
3 authors
cs.LG
Sparsifying Stochasticity, Not Capacity: Partial Stochasticity via Deep Weight Factorization of Prior Scales
Oct 7, 2026
2 authors
stat.MLcs.LG
Identifiability of a dissipative knowledge-dynamics model: exact recovery under designed excitation, degeneration on observational data
Oct 7, 2026
2 authors
cs.LGmath.OCstat.ML
Outperformance Inverse Optimization: Learning Objective Functions that Outperform Agent Decisions
Oct 7, 2026
1 authors
cs.AImath.OCmath.ST+1
A Scoping Review and Experimental Study on Reinforcement Learning from Human Feedback for Human-Robot Collaboration
Oct 7, 2026
6 authors
cs.HCcs.AIcs.RO
QCATS: Query Context-Aware Transformer Slicing for Efficient Predictive Query Processing
Oct 7, 2026
4 authors
cs.DBcs.AI
Love for Believable AI: Artificial Partiality and Relationship Persistence as an Engineerable Stance
Oct 7, 2026
1 authors
cs.HCcs.CL
NL2Hull: A Natural Language-Driven Constrained Ship Design Decision Framework
Oct 7, 2026
5 authors
cs.AI
Learning joint probabilistic weather forecasts from station observations alone
Oct 7, 2026
2 authors
stat.APcs.LGphysics.ao-ph
Constrained-Action AI Remediation for SIEM/XDR via a NeMo-Guardrails Proxy
Oct 7, 2026
4 authors
cs.CRcs.AIcs.CL
FedSSMCoOp: SSM Encoders for light-weight Federated Prompt Learning for Few-shot Classification
Oct 7, 2026
4 authors
cs.CV
RollVerify: Bridging Efficiency and Accuracy in Long-Tail Rollout Reinforcement Learning
Oct 7, 2026
8 authors
cs.LGcs.AI
Eigenvalues of the Hessian in Deep Learning: The Origin of Symmetry and Its Breaking
Oct 7, 2026
1 authors
cs.LGmath.OCstat.ML
Itgan at NADI 2026 shared task: Parameter-Efficient Whisper Adaptation for Robust, Mixed-Dialect and Code-Switched Arabic ASR
Oct 7, 2026
1 authors
cs.CLcs.AIcs.SD
Where Can a Decision Model Diagnose HVAC Faults? Reasoning Demand, Physical Representation, and Robustness Under Shift
Oct 7, 2026
1 authors
cs.AI
Purifying Backdoored Large Vision-Language Models by Removing Hijacked Directions
Oct 7, 2026
6 authors
cs.CV
Many Ways to Succeed: Diversity-Driven RL Fine-Tuning for VLA Generalization
Oct 7, 2026
8 authors
cs.ROcs.LG
Learning Traffic Flow Dynamics with Stochastic Physics-Informed Neural Cellular Automata
Oct 7, 2026
2 authors
cs.LG
MSU Team at the Explainable Deepfake Detection Challenge 2026: Grounded Artifact Evidence for Deepfake Detection
Oct 7, 2026
5 authors
cs.CV
Force without transmission: a depth-induced rank collapse that no loss on the representation reopens
Oct 7, 2026
2 authors
cs.LG
The Harness as the Only Mutable Surface: Compliance-Bounded Self-Evolution of LLM Agents in Credit Pipelines, with a Measured Admission Gate
Oct 7, 2026
1 authors
cs.AI
Successive Training Stages and Large Language Model Persuasion: Effects of Misalignment, Supervised Fine-Tuning, and Preference Optimization
Oct 7, 2026
4 authors
cs.AIcs.CY
TR-PTQ: High-Accuracy Integer-Only Transformer Post Training Quantization via Taylor Region Reformulation
Oct 7, 2026
3 authors
cs.LG
From Expected Harmfulness to Likelihood: A Probabilistic Reformulation of Jailbreaking LLM Agents
Oct 7, 2026
5 authors
cs.AI
EASE: Entropy-Adaptive Distribution Shaping for Evading AI-generated Text Detectors
Oct 7, 2026
4 authors
cs.CL
Sensitive-Topic Leakage Through LLM Routing Metadata: Measurement and Mitigation
Oct 7, 2026
1 authors
cs.CRcs.CL
Extreme Binary Classification: Extreme Value Theory for Extreme Constraint on False Negative
Oct 7, 2026
3 authors
stat.MLcs.LGstat.AP+1
Efficient Patch-Based Anomaly Detection Fused with Diffusion Driven Generative Modeling for Semiconductor Wafer Bin Map Open Set Anomaly Detection
Oct 7, 2026
2 authors
cs.LGcs.AI
Temporal Predictive Multiplicity: Equally Accurate Time Series Models Yield Different Forecast Trajectories
Oct 7, 2026
4 authors
cs.LGcs.AI
Beyond Reward Suppression: Near-Optimal Offline Attacks on Warm-Start Bandits with Bounded Rewards
Oct 7, 2026
5 authors
cs.LGcs.AI
A Drosophila Whole-Connectome Network Can Learn Human-Designed Cognitive Tasks
Oct 7, 2026
3 authors
cs.LG
What the Sleeve Feels: Explainable Machine Learning for Textile Pressure-Based Postural Screening
Oct 7, 2026
2 authors
cs.AI