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 196 of 545
Residual Visual Credit Optimization: Conserved Evidence Routing for Multimodal Reinforcement Learning
Oct 4, 2026
9 authors
cs.LGcs.CL
Complex Agents, Shallow Tests: Demystifying and Enhancing Test Adequacy of Agent Harness in the Wild
Oct 4, 2026
4 authors
cs.SEcs.AI
TRACE: Time-Adaptive Residual Attention Control with Content-Style Decomposition for Training-Free Diffusion Style Transfer
Oct 4, 2026
8 authors
cs.CV
TSAE: Structured Sparse Autoencoders for Interpreting Time-Series Forecasting Models
Oct 4, 2026
2 authors
cs.LGcs.AI
Assembling Insights for Agentic Machine Learning Engineering Systems
Oct 4, 2026
4 authors
cs.SEcs.AIcs.LG
Prompt Dominance and Asymmetric Verifier Costs: Empirical Ablations of GRPO at 1B Scale on GSM8K
Oct 4, 2026
1 authors
cs.LG
Billion-Scale Thumbnail Optimization for Uncurated Short-Form Videos via Multi-Armed Bandits
Oct 4, 2026
10 authors
cs.LG
DiVeR: Decision-Critical Verifier Learning for VLA Test-Time Scaling
Oct 4, 2026
8 authors
cs.ROcs.AIcs.LG
D-DOIT: Training-free Adaptation of Discrete Diffusion via Doob's h-Transform
Oct 4, 2026
6 authors
cs.LGcs.AI
A Graph-Based Inspection and Intervention Tool for Assessing Mechanistic Learning in PINNs
Oct 4, 2026
4 authors
cs.LGcs.AI
Software World Models: From Consequence Prediction to Decision Value
Oct 4, 2026
6 authors
cs.LGcs.AIcs.SE
Zero-Shot Time-Series Question Answering via Decoupled Perception and Reasoning
Oct 4, 2026
3 authors
cs.AI
Near-Optimal Complexity of Finite-Sum Nonconvex-Strongly-Concave Minimax Optimization
Oct 4, 2026
1 authors
math.OCcs.LG
TempoBridge: Source-Conditioned Flow Matching with Optimal Transport Couplings for Single-Cell Population Transitions
Oct 4, 2026
10 authors
cs.LGcs.AIq-bio.GN
Bridging the EHR Divide: Asymmetric Contrastive Learning for Cross-National Medical Representation Transfer
Oct 4, 2026
1 authors
cs.LG
A Unified Dynamics Framework for Reinforcement Learning and Classical Control of a Six-DOF Pipeline-Tracking ROV in NVIDIA Isaac Sim
Oct 4, 2026
3 authors
cs.ROcs.AIeess.SY
How Should Teachers Be Prepared? RL on Student-Induced States for On-Policy Distillation
Oct 4, 2026
5 authors
cs.LG
EDISCO: Equivariant DIScrete Diffusion for Euclidean Combinatorial Optimization
Oct 4, 2026
2 authors
cs.LGcs.AI
Kapture: Capturing Cardiac Dynamics with Koopman-Governed Learning for Efficient Radar-Based Electrocardiogram Recovery
Oct 4, 2026
4 authors
eess.SPcs.AI
From Overloaded to Guaranteed: High-Throughput Multi-SLO Enforcement for LoRA-Assisted On-Premise LLM Deployment
Oct 4, 2026
12 authors
cs.CLcs.DC
Trinity: One Differentiable Physics for Training, Refining and Scoring Generative Floorplanners
Oct 4, 2026
10 authors
cs.LGcs.AR
Building LLM Agent Systems the Deep Learning Way: From Modular Design to Architecture Search
Oct 4, 2026
4 authors
cs.CL
One Token Can Be Enough: Bridging Prompting and Activation Steering with Prefix Steering
Oct 4, 2026
2 authors
cs.LGcs.CL
Hamiltonian Metric Learning and Energy-Based Training: A Dissipative Geometric Framework for Optimization
Oct 4, 2026
6 authors
cs.LGmath.OCquant-ph
TrajLong: Co-Designing Agentic and Long-Context Supervision for Mid-Training
Oct 4, 2026
11 authors
cs.CL
IREA: Intermediate Representation-based Embedding Alignment for Normative RAG
Oct 4, 2026
3 authors
cs.CL
Runtime Authorization of Self-Generated Subgoals in Long-Horizon Tool-Using AI Agents
Oct 4, 2026
2 authors
cs.AIcs.CR
Do LLMs Understand Sequential Structure? A Controlled Study of Inference and Generation
Oct 4, 2026
6 authors
cs.AI
What Will Post-Training Fix? Per-Problem Gains Are Shared Across Independent RL Runs, and Existing Checkpoints Predict Them Better Than A Priori Signals
Oct 4, 2026
1 authors
cs.LG
Robust Tensor Completion via Reflective Convolution Nuclear Norm Minimization
Oct 4, 2026
4 authors
cs.CV
TeleGen: Improving LLM-Based Web Application Generation via Runtime Telemetry
Oct 4, 2026
5 authors
cs.SEcs.AI
Hidden Risks of Jev: An Empirical Study of Security, Privacy, and Dual Use
Oct 4, 2026
6 authors
cs.CRcs.AI
How Long, Not How Close: A Learned Temporal Metric for Planning in Latent World Models
Oct 4, 2026
3 authors
cs.LG
When Is a Graph a Covariance? Bayesian Residual Propagation under Covariance Uncertainty
Oct 4, 2026
1 authors
math.STstat.ML
CrystalJev: calibrated foundation-model probabilities decide what to compute next in materials discovery
Oct 4, 2026
6 authors
cond-mat.mtrl-scics.AIphysics.comp-ph
CIPO: Counterfactual Imagination Policy Optimization for Adaptive Tool Granularity Selection
Oct 4, 2026
7 authors
cs.AI
Pessimistic Minimax Learning for Public-Private Information Games under Unilateral Coverage
Oct 4, 2026
4 authors
cs.LG
Beyond Overparameterization: Provable Learning of Input-Convex Multi-Layer Polynomial Networks with Active Queries
Oct 4, 2026
4 authors
cs.LGstat.ML
VisualErase: Dual-Branch Visual Trajectory Redirection for Robust Concept Erasure in Text-to-Image Diffusion Models
Oct 4, 2026
6 authors
cs.CV
How corner is a corner case? Percentile control for highway scenario generation
Oct 4, 2026
8 authors
cs.AI