7930 papers
This paper proposes a Coverage-Aware Web Crawling framework utilizing a Web--Knowledge--Web pipeline and ecological species-richness estimators to iteratively discover and map under-represented SME suppliers in specialized sectors, achieving superior precision and efficiency compared to baseline methods in the semiconductor equipment manufacturing industry.
This paper establishes a principled framework linking activation steering to weight updates, demonstrating that targeting post-block outputs achieves near-full fine-tuning accuracy with minimal parameters and that jointly adapting both spaces surpasses the performance limits of either method alone.
This paper proposes a reparameterized Tensor Ring functional decomposition that leverages Implicit Neural Representations and a structured basis combination to overcome the high-frequency modeling limitations of traditional methods, achieving superior performance in multi-dimensional data recovery tasks such as image inpainting and point cloud reconstruction.
This paper proposes a compact acoustic framework that combines multi-branch CNN feature extraction with an efficient Legendre Memory Unit (LMU) for temporal modeling and a calibrated posterior ensemble fusion strategy to achieve robust, real-time cross-domain infant cry classification despite limited annotations and strong domain shifts.
This paper introduces Whisper-RIR-Mega, a benchmark dataset pairing clean LibriSpeech utterances with real room impulse responses to evaluate and demonstrate the performance degradation of various Whisper models under reverberant conditions, while providing open-source resources for reproducible research on robust ASR.
This paper introduces RigidSSL, a rigidity-aware self-supervised learning framework that pretrains on static and dynamic protein structures using a bi-directional flow matching objective to jointly optimize geometric understanding and conformational dynamics, thereby significantly improving protein designability, novelty, and the modeling of realistic conformational ensembles.
mlx-vis is a Python library built on Apple's MLX framework that delivers GPU-accelerated dimensionality reduction, k-nearest neighbor graph construction, and Metal-based circle-splatting rendering for rapid visualization and animation on Apple Silicon devices.
This paper proposes "Traversal-as-Policy," a framework that distills sandboxed execution logs into verifiable Gated Behavior Trees to replace implicit LLM policies with explicit, state-conditioned macro traversals, thereby significantly improving success rates, eliminating safety violations, and reducing computational costs across diverse autonomous agent benchmarks.
This paper addresses the risk of amplified privacy leakage in sequential multi-agent LLM systems by formalizing compositional leakage through mutual information, deriving a theoretical bound on its propagation, and proposing a privacy-regularized training framework that enforces system-level privacy guarantees rather than relying on local agent constraints alone.
RoboLayout is a differentiable 3D scene generation framework that extends LayoutVLM by integrating explicit reachability constraints and a local refinement stage to create semantically coherent, physically feasible indoor environments tailored to the specific capabilities of diverse embodied agents.
This paper proposes a novel multimodal framework, the Clinical-Injection Transformer with a domain-adapted MAE, which integrates routine PAS-stained histopathology images and clinical data to achieve high-accuracy three-class prognosis prediction for pediatric lupus nephritis, addressing previous limitations in data availability and modality integration.
The paper introduces JAWS, a probabilistic regularization strategy that dynamically modulates Jacobian constraints based on local physical complexity to resolve the contraction-dissipation dilemma, thereby enabling memory-efficient, short-horizon optimization to achieve superior long-term stability and accuracy in neural operator rollouts for dynamical systems.
VDCook is a self-evolving, configurable video data operating system that enables researchers and domain teams to automatically generate, update, and manage specialized video training datasets for MLLMs through natural language queries, integrated retrieval-synthesis modules, and automated metadata annotation.
This paper establishes that while language-equivalent context-free grammars yield identical token masks in grammar-constrained decoding, their structural differences significantly impact computational efficiency by introducing variable state-space blowups and ambiguity costs, leading to fundamental lower bounds on decoding work and new distortion metrics for masked sampling.
This paper proposes a simple algebraic rearrangement of the Yates covariance decomposition for the Brier score that decomposes forecast error into three non-negative terms—variance mismatch, correlation deficit, and calibration-in-the-large—thereby making the conditions for optimal probabilistic forecasting transparent.
The paper introduces IntSeqBERT, a dual-stream Transformer model that combines continuous log-scale magnitude embeddings with modulo-spectrum embeddings to effectively learn the arithmetic structure of OEIS integer sequences, significantly outperforming standard tokenized baselines in both sequence modeling accuracy and next-term prediction via a probabilistic Chinese Remainder Theorem solver.
This study employs a stochastic-process model to demonstrate that the optimal autocorrelation of time-series signals for solving multi-armed bandit problems depends on the reward environment, with negative autocorrelation being advantageous in reward-rich settings and positive autocorrelation in reward-poor ones, while performance remains independent of autocorrelation when the sum of winning probabilities equals one.
This paper demonstrates that the Continuous-Time Koopman Autoencoder (CT-KAE) serves as a lightweight, stable, and efficient surrogate model for long-horizon ocean state forecasting, outperforming autoregressive Transformer baselines by maintaining bounded errors and consistent large-scale statistics over 2083-day rollouts while enabling resolution-invariant predictions.
This paper presents a task-based model demonstrating that while generative AI homogenizes individual skills, it can simultaneously increase aggregate inequality by shifting economic value toward concentrated complementary assets, with the net outcome determined by the technology's structure and labor market institutions rather than a single universal verdict.
This paper proposes CDDS, a novel cross-modal alignment algorithm that utilizes a dual-path UNet for constrained decoupling of semantic and modality components and a distribution sampling method to bridge the modality gap, thereby achieving superior semantic consistency and outperforming state-of-the-art methods by 6.6% to 14.2%.