Browse all

arXiv research papers — all

All arXiv papers (AI/ML focus) — filter and search by category and year.

Clear

674 results

PaperCategoryAuthorsDate
Query-Efficient Rejection Sampling for Parallel Masked Diffusion ↗ cs.LG 4 Oct 15, 2026
Training-Free On-Policy Distillation ↗ cs.LG 5 Oct 15, 2026
OS-Helix: Unifying GUI Interaction and Code Execution in Native... ↗ cs.LG 11 Oct 15, 2026
Generalization Guarantees of Randomized Block Coordinate Descent... ↗ cs.LG 2 Oct 15, 2026
LCT: Losslessly Compressed Tensors with GPU friendly execution f... ↗ cs.LG 4 Oct 15, 2026
Bi-FORK: Generative Modeling of High-Dimensional Bifurcating Sys... ↗ cs.LG 7 Oct 8, 2026
Caught in the Act: Probes Effectively Detect Sabotage and Catch... ↗ cs.LG 5 Oct 8, 2026
Rounding in Preconditioner Space: Redesigning 4-bit AdamW Optimi... ↗ cs.LG 10 Oct 8, 2026
A Unified Bellman Operator for Safety-Critical Reinforcement Lea... ↗ cs.LG 4 Oct 8, 2026
Learning Kilometer-Scale Weather Prediction with Global-Regional... ↗ cs.LG 8 Oct 8, 2026
Prospective Prediction of OOD Degradation from Source-Side Train... ↗ cs.LG 2 Oct 8, 2026
Long Text to Predictive Features: LLM-Guided Blockwise Feature E... ↗ cs.LG 5 Oct 8, 2026
Marformer: A Transformer for Predicting Missing Data Distributio... ↗ cs.LG 4 Oct 8, 2026
TACO: Ternary Absolute-max Column-wise One-sparse Optimizer for... ↗ cs.LG 5 Oct 1, 2026
FERPO: Forward Entropy-Regularized Policy Optimization ↗ cs.LG 3 Oct 1, 2026
Cost-augmented Schrödinger bridges on graphs are exactly solvabl... ↗ cs.LG 1 Oct 1, 2026
The Missing Primitive: Diagnosing and Repairing Mathematical Rea... ↗ cs.LG 10 Oct 1, 2026
Trust the Direction, Search the Step: Zero-and-First-Order Metho... ↗ cs.LG 3 Oct 1, 2026
Generative modeling of intrinsically disordered protein regions... ↗ cs.LG 10 Oct 1, 2026
Higher-Order Molecular Grammars for Generative and Foundation Mo... ↗ cs.LG 7 Oct 1, 2026
Decoding Looped Transformers Better for (Almost) Free ↗ cs.LG 8 Oct 1, 2026
SoftServe: A Scalable Quasi-Newton Method for Deep Learning ↗ cs.LG 4 Oct 1, 2026
From Gradients to Capabilities: Understanding Multi-Teacher On-P... ↗ cs.LG 7 Oct 1, 2026
Effective Resistance and Graph Neural Network Reliability in Tis... ↗ cs.LG 1 Oct 1, 2026
Every Ablation Is a Dose: Counterweights and the Semblance of Se... ↗ cs.LG 3 Oct 1, 2026
When Do Intrinsic Rewards Lead to Exploration? ↗ cs.LG 3 Oct 1, 2026
Muon meets Tamed Langevin: Momentum Preconditioning beyond Conve... ↗ cs.LG 2 Oct 1, 2026
Faynt: Scaling and Optimizing Policies for Competitive Melee ↗ cs.LG 4 Oct 1, 2026
Finetuning with Sampling: SFT Learns Better Than You Think ↗ cs.LG 3 Oct 1, 2026
Linear Programming Representations and Strongly Polynomial Algor... ↗ cs.LG 2 Oct 1, 2026
Local Support Learning ↗ cs.LG 4 Oct 1, 2026
Are We Recovering Mechanisms? Objective-Level Recovery Gaps in M... ↗ cs.LG 6 Oct 1, 2026
Learn the Directions, Normalize the Gains: Post-Training Normali... ↗ cs.LG 5 Oct 1, 2026
Foundations without Fundamentals: Zero-Shot Blind Spots in Time... ↗ cs.LG 5 Oct 1, 2026
Distributionally Robust Schrödinger Bridge ↗ cs.LG 5 Oct 1, 2026
CARM: Cancellation-Aware Response Masking for LLM Reinforcement... ↗ cs.LG 5 Oct 1, 2026
Relative Transitions, Not Absolute Destinations: A Transfer-and-... ↗ cs.LG 5 Oct 1, 2026
On Language Drift during RLVR Post-Training ↗ cs.LG 2 Oct 1, 2026
BranchIP: Learning Adaptive Equivariant Computation for Interato... ↗ cs.LG 9 Oct 1, 2026
Bellman Meets Lyapunov: Unsupervised Reinforcement Learning via... ↗ cs.LG 5 Oct 1, 2026
Universal interpolation for deep residual self-attention network... ↗ cs.LG 2 Oct 1, 2026
The Curvature of Regret in Contextual Linear Optimization ↗ cs.LG 3 Oct 1, 2026
Sim+Real: Joint Simulation - Experiment Training Improves Balanc... ↗ cs.LG 6 Oct 1, 2026
FastCI: Efficient GPU-Intensive CI for LLM Training Frameworks ↗ cs.LG 7 Oct 1, 2026
Temporal Gradient Inversion for Private Trajectory Reconstructio... ↗ cs.LG 5 Sep 24, 2026
To Trust or Not to Trust: Retrieval-Augmented Fact Checking in S... ↗ cs.LG 3 Sep 24, 2026
PoEM: Predicting RL Outcomes from Existing Policies ↗ cs.LG 3 Sep 24, 2026
Minimally Invasive Steering of Language Models ↗ cs.LG 4 Sep 24, 2026
Beyond Compression: Training Latent Representations for Stable L... ↗ cs.LG 8 Sep 24, 2026
Intrinsic-Extrinsic Coupling in Learning Dynamics ↗ cs.LG 1 Sep 24, 2026

Source: official U.S. government open data. This is an organized index, not an official U.S. government site. "Explained" links to our summary page; otherwise links go to the official primary source.

Disclaimer: This site independently summarizes and classifies information based on official data sources. Always verify the latest and accurate information with the official sources. Content on finance, health, legal, and security is information, not advice. This site is not an official website of the U.S. government.