9426 papers
This paper introduces Clip21-SGD2M, a novel federated learning algorithm that combines clipping, heavy-ball momentum, and error feedback to achieve both optimal convergence rates for non-convex problems with heterogeneous data and near-optimal differential privacy guarantees without restrictive assumptions.
This survey proposes a principled, function-centric taxonomy grounded in Control as Inference to unify generative models in decision making into four distinct roles—Controllers, Modelers, Optimizers, and Evaluators—while critically analyzing their applications in high-stakes domains and outlining challenges for developing Generalist Physical Intelligence.
This paper introduces BACE-RUL, a bi-directional adversarial network with covariate encoding that predicts machine Remaining Useful Life using only current sensor measurements to overcome the limitations of prior knowledge and temporal mining, demonstrating superior performance over state-of-the-art methods on real-world datasets.
This paper identifies the "safety mirage" in Vision-Language Models, where supervised fine-tuning creates spurious correlations that leave models vulnerable to simple attacks and prone to over-refusal, and proposes machine unlearning as a superior alignment strategy that significantly reduces attack success rates and unnecessary rejections while preserving general capabilities.
This paper introduces a large-scale, mutation-based evaluation framework to assess the robustness of Large Language Models in fault localization, revealing that their reasoning is often brittle and reliant on syntactic cues rather than deep semantic understanding, as evidenced by a 78% failure rate when subjected to semantic-preserving code changes.
This paper introduces ms-Mamba, a novel multi-scale architecture that employs Mamba blocks with varying sampling rates to capture temporal information at different scales, achieving state-of-the-art forecasting performance with greater efficiency than existing Transformer and Mamba-based models.
The paper introduces TianQuan-S2S, a novel global subseasonal-to-seasonal weather forecasting model that integrates climatological states into patch embeddings and utilizes an uncertainty-augmented Transformer to overcome the limitations of over-smoothing and inadequate climate representation, thereby outperforming both traditional numerical methods and advanced data-driven models in deterministic and ensemble forecasting.
The paper introduces Noise2Ghost, a self-supervised deep learning method that achieves superior noise reduction and reconstruction quality in ghost imaging without requiring clean reference data, thereby enabling high-quality imaging in low-light scenarios such as dose-sensitive x-ray fluorescence and biological studies.
This paper proposes a novel, instance-specific Differentially Private framework based on the Propose-Test-Release mechanism that enables scalable and accurate estimation of network principal components on large real-world graphs, achieving a 180-fold runtime improvement over existing baselines while also providing the first DP solution for the Densest--subgraph problem.
This paper presents a variational inference formulation of log-homotopy particle flow as a Fisher-Rao gradient flow, deriving Gaussian and Gaussian mixture approximations that recover the Exact Daum and Huang flow under linear Gaussian assumptions while enhancing expressiveness for multi-modal estimation.
ReactDance is a novel diffusion framework that achieves high-fidelity, coherent long-form reactive dance generation by employing Hierarchical Finite Scalar Quantization for fine-grained spatial control and a Blockwise Local Context strategy for efficient, temporally consistent sequence synthesis.
This paper proposes MiCo, a hierarchical language agent framework that leverages large language models to design adaptive heuristics for solving the complex Online Dynamic Multidimensional Bin Packing problem in cloud VM scheduling, achieving a 96.9% competitive ratio in large-scale, real-world scenarios.
This paper introduces CausalPitfalls, a comprehensive benchmark designed to rigorously evaluate and expose the significant limitations of large language models in handling statistical causal inference pitfalls, such as Simpson's paradox, through both direct and code-assisted prompting protocols.
This paper introduces ShIOEnv, a grammar-constrained, self-supervised Bash environment that generates 2.1 million system-grounded input-output pairs to significantly improve the accuracy of modeling complex command-line execution behaviors compared to prior execution-free approaches.
VTool-R1 is a novel framework that leverages reinforcement learning to train vision-language models to generate multimodal chains of thought by strategically interleaving text with intermediate visual reasoning steps using Python-based editing tools, thereby enhancing performance on structured visual tasks without requiring process-based supervision.
This paper presents an attribute-efficient PAC learning algorithm for sparse halfspaces that achieves robustness against a constant malicious noise rate using samples by applying simple variants to hinge loss minimization under specific concentration and margin conditions.
This paper introduces a novel framework that enables direct finetuning of large language models using multi-kernel Boolean parameters without latent weights, significantly reducing complexity while outperforming existing ultra low-bit quantization and binarization techniques.
This paper introduces Continuous Chain of Thought (CoT2), a framework that replaces discrete token sampling with continuously-valued tokens to enable parallel exploration of multiple reasoning traces, offering theoretical guarantees for solving combinatorial problems and demonstrating improved performance through novel supervision and policy optimization strategies.
The paper introduces SealQA, a new benchmark comprising three challenging flavors (Seal-0, Seal-Hard, and LongSeal) designed to evaluate search-augmented language models on fact-seeking tasks with noisy or conflicting web results, revealing that even frontier models struggle significantly with reasoning accuracy, robustness to noise, and long-context document retrieval.
This systematic review analyzes 68 experiments deploying machine learning models on FPGAs for Earth Observation, introducing dual taxonomies for model architectures and implementation strategies to address the challenges of onboard processing in the NewSpace era.