9963 papers
This paper proposes a regularized online RLHF framework using Generalized Bilinear Preference Models to identify Nash Equilibria, establishing the first statistically efficient, dimension-free regret bounds for high-dimensional settings through two simple algorithms that leverage strong convexity and low-rank structures.
This paper introduces Lap2, a novel framework that enables L2-norm clipping for Laplace DP-SGD in high-dimensional models by leveraging majorization theory and Schur-convexity to overcome dimensionality barriers, thereby achieving privacy-utility performance comparable to or exceeding Gaussian DP-SGD.
This paper introduces a general inference-time optimization framework that generates experiment-grounded protein ensembles by optimizing latent representations and employing novel sampling schemes, thereby overcoming the limitations of current diffusion-based methods to produce thermodynamically plausible structures with improved agreement to experimental data while exposing vulnerabilities in existing confidence metrics.
The paper introduces Jailbreak Foundry (JBF), a multi-agent system that automatically translates jailbreak research papers into executable modules within a unified harness, enabling rapid, reproducible, and standardized benchmarking of large language model security against rapidly evolving attack techniques.
DiffusionHarmonizer is an online, single-step generative framework that leverages a custom data curation pipeline to transform imperfect neural reconstruction renderings into temporally consistent, photorealistic simulations, effectively resolving artifacts and harmonizing inserted dynamic objects for autonomous robot development.
This paper introduces Aurchestra, a novel system for resource-constrained hearables that enables real-time, fine-grained control over up to five overlapping sound sources by combining a dynamic interface with an optimized on-device multi-output extraction network, effectively transforming the acoustic environment into a programmable mix.
This paper demonstrates that interpreter persistence is a critical training-time semantic that significantly impacts agent efficiency and stability, revealing that misalignment between training data and deployment runtime causes substantial token waste or error rates despite achieving comparable solution quality.
This paper introduces Reference-Guided Fine-Tuning (ReGFT), a method that synthesizes model-aligned positive trajectories using partial human reference solutions to overcome reward sparsity and significantly enhance the performance and training efficiency of reinforcement learning for mathematical reasoning.
This paper introduces VoxKnesset, a large-scale open-access dataset of 2,300 hours of longitudinal Hebrew parliamentary speech spanning 2009–2025, which is used to benchmark and demonstrate the challenges of speaker verification and age prediction over time, revealing significant performance degradation in standard models as speakers age.
MatRIS is a novel, computationally efficient invariant machine learning interatomic potential that utilizes a linear-complexity separable attention mechanism for three-body interactions to achieve accuracy comparable to state-of-the-art equivariant models at a significantly lower training cost.
This paper proposes a conformal prediction framework for graph-valued outputs that ensures distribution-free coverage guarantees by utilizing Z-Gromov-Wasserstein distances for nonconformity scoring and introducing Score Conformalized Quantile Regression (SCQR) to generate adaptive prediction sets.
The paper introduces IoUCert, a novel formal verification framework that overcomes the challenges of non-linear coordinate transformations and IoU metrics to enable the first robustness verification of realistic, anchor-based object detection models like SSD and YOLO.
This paper introduces an incremental -NN graph construction method that guarantees connectivity by design, thereby enabling robust spectral clustering of text embeddings that outperforms standard approaches in low- regimes where disconnected components typically degrade performance.
This paper proposes a conditional variational autoencoder (CVAE) that efficiently and accurately reconstructs shock acceleration time series from shock response spectrum curves, overcoming the computational limitations and basis function constraints of traditional iterative optimization methods.
AOI is a secure, trainable multi-agent framework that automates Site Reliability Engineering by leveraging Group Relative Policy Optimization and a read-write separated architecture to distill expert knowledge into local models and convert failed trajectories into corrective signals, achieving state-of-the-art performance on the AIOpsLab benchmark while ensuring data privacy and safe execution.
RADAR is a scalable neural framework that enhances vehicle routing problem solvers for asymmetric scenarios by leveraging Singular Value Decomposition to encode static distance asymmetry and Sinkhorn normalization to model dynamic interaction asymmetry, thereby achieving superior generalization and performance on both synthetic and real-world benchmarks.
The paper proposes Stratum, a unified system infrastructure that decouples pipeline execution from agent reasoning to efficiently scale agentic ML pipeline search by integrating with existing Python libraries and utilizing an optimized Rust-based runtime, achieving up to 16.6x speedup.
This paper establishes a theoretical foundation for the superior parallelizability of linear RNNs by demonstrating that they correspond to log-depth arithmetic circuits (-complete), whereas nonlinear RNNs are fundamentally limited by their ability to solve - and -complete problems, thereby explaining why linear variants can be efficiently parallelized like transformers while traditional nonlinear RNNs cannot.
This paper proposes a DMD-augmented Unpaired Neural Schrödinger Bridge framework that enhances Ultra-Low Field (64 mT) MRI image quality by leveraging diffusion-guided distribution matching and anatomical structure preservation to achieve superior realism and structural fidelity in translating unpaired 64 mT scans to 3 T quality.
LoRA-MME is a parameter-efficient multi-model ensemble that combines LoRA-tuned UniXcoder, CodeBERT, GraphCodeBERT, and CodeBERTa encoders to achieve strong code comment classification performance, though its high computational cost ultimately limited its final competition score.