Conan-Embedding-v2: Training an LLM from Scratch for Text Embeddings
arXiv:2509.12892v1 Announce Type: cross Abstract: Large language models (LLMs) have recently demonstrated excellent performance in text embedding tasks. Previous work…
Runge-Kutta Approximation and Decoupled Attention for Rectified Flow Inversion and Semantic Editing
arXiv:2509.12888v1 Announce Type: cross Abstract: Rectified flow (RF) models have recently demonstrated superior generative performance compared to DDIM-based diffusion models.…
Evalet: Evaluating Large Language Models by Fragmenting Outputs into Functions
arXiv:2509.11206v2 Announce Type: replace-cross Abstract: Practitioners increasingly rely on Large Language Models (LLMs) to evaluate generative AI outputs through “LLM-as-a-Judge”…
Situation Model of the Transport, Transport Emissions and Meteorological Conditions
arXiv:2509.10541v1 Announce Type: new Abstract: Air pollution in cities and the possibilities of reducing this pollution represents one of the…
Is In-Context Learning Learning?
arXiv:2509.10414v2 Announce Type: replace-cross Abstract: In-context learning (ICL) allows some autoregressive models to solve tasks via next-token prediction and without…
Dynamic Adaptive Parsing of Temporal and Cross-Variable Patterns for Network State Classification
arXiv:2509.11601v1 Announce Type: cross Abstract: Effective network state classification is a primary task for ensuring network security and optimizing performance.…
Intrinsic Dimension Estimating Autoencoder (IDEA) Using CancelOut Layer and a Projected Loss
arXiv:2509.10011v2 Announce Type: replace-cross Abstract: This paper introduces the Intrinsic Dimension Estimating Autoencoder (IDEA), which identifies the underlying intrinsic dimension…
Human-AI Collaboration Increases Efficiency in Regulatory Writing
arXiv:2509.09738v1 Announce Type: new Abstract: Background: Investigational New Drug (IND) application preparation is time-intensive and expertise-dependent, slowing early clinical development.…
OmniEVA: Embodied Versatile Planner via Task-Adaptive 3D-Grounded and Embodiment-aware Reasoning
arXiv:2509.09332v2 Announce Type: replace-cross Abstract: Recent advances in multimodal large language models (MLLMs) have opened new opportunities for embodied intelligence,…
Drone-Based Multispectral Imaging and Deep Learning for Timely Detection of Branched Broomrape in Tomato Farms
arXiv:2509.09972v1 Announce Type: cross Abstract: This study addresses the escalating threat of branched broomrape (Phelipanche ramosa) to California’s tomato industry,…