LF
No mentions found
This entity hasn't been tracked yet, or Iris is still building its knowledge base.
Related Articles from SNS
Neural Legendre-Fenchel transform with Hessian Preconditioning
Announce Type: new Abstract: The Legendre-Fenchel (LF) transform is a fundamental tool in convex analysis and machine learning that maps lower semi-continuous functions to their convex conjugates. In practice, when closed-form formula are not available for expressing convex conjugates of given functions, one must approximate them using various techniques. One recent such versatile numerical method is the deep Legendre transform method which relies on neural networks although it remains...
Contact-network organization and motion statistics in shear-thickening suspensions
Announce Type: cross Abstract: We use lubricated-flow discrete-element-method (LF-DEM) simulations to examine how contact-network organization shapes particle motion in dense shear-thickening suspensions. The primary system studied is a two-dimensional bidisperse monolayer where rigid clusters are identified by the $(3,3)$ pebble game; three-dimensional simulations are shown to have qualitatively similar rotational velocity statistics. Across the stress--solid-fraction state diagram,...
Bridged SBI: Correcting Biased Low-Fidelity Posteriors for Cost-Efficient High-Fidelity Inference
arXiv:2606.09155v1 Announce Type: new Abstract: Accurate calibration of particle-based simulators is crucial for robotic earthwork simulation, but analytical calibration is challenging due to this task's highly nonlinear particle dynamics and the black-box nature of conventional simulators. Although simulation-based inference (SBI) can estimate posterior distributions over simulation parameters solely from forward simulations, applying SBI directly to high-fidelity (HF) particle simulators...
What are Lebanon’s most important political parties?
What are Lebanon’s most important political parties? Lebanon’s many powerful parties reflect the coutntry’s social, sectarian, and political divides. Hezbollah is the most prominent of Lebanon’s political movements, and has long been the most powerful in the country.
Deterministic Execution of ROS~2 Applications via Lingua Franca
arXiv:2606.09203v1 Announce Type: new Abstract: The Robot Operating System~2 (ROS 2) is a widely used middleware for robotic systems, characterized by a publish-subscribe (pub-sub) communication mechanism in which computation is structured as callbacks dispatched by ROS 2 executors. Despite its popularity, the pub-sub pattern in ROS 2 is inherently nondeterministic: the order in which these callbacks run is nondeterministic even within a single executor, and distributed deployments add...
Late-Layer Fusion is Enough: Dual-Path Vision Token Routing for Multimodal Large Language Models under Visual Saturation
arXiv:2606.09131v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) commonly inherit the deep, symmetric Transformer backbone designed for unimodal text modeling, and apply the same computation uniformly to image and language tokens. This design overlooks a key modality asymmetry: image and text tokens differ substantially in information density, redundancy, and required reasoning depth. Through a layer-wise analysis of LLaVA-1.5, we observe that vision tokens tend to...
MLB post-hype check-in: What to make of former big...
Players like Corbin Carroll, Paul Skenes, Nick Kurtz and now Kevin McGonigle have spoiled it for all hyped Major League Baseball prospects in recent years: We expect instant stardom from them, forgetting that baseball, as the great Jimmy Dugan once said, is "supposed to be hard. If it wasn't hard, everyone would do it."
Learning a Semantic Calibration Network for Open-Vocabulary Semantic Segmentation
Announce Type: new Abstract: Semantic image segmentation assigns a predefined category label to each pixel, has achieved significant progress lately. Open-Vocabulary Segmentation (OVS) extends the segmentation task from a fixed set to an open set, enabling the identification and segmentation of novel concepts based on arbitrary text inputs, such as category names or descriptions. In this paper, we propose a novel Semantic Calibration Network (SCN) for open-vocabulary semantic segmentation.
What Makes LVLMs Hallucinate Less? Unveiling the Architectural Factors Behind Hallucination Robustness
arXiv:2605.30911v1 Announce Type: new Abstract: Hallucination remains one of the key challenges undermining the reliability of Large Vision-Language Models (LVLMs). But what makes an LVLM hallucinate less? Many existing efforts focus on improving internal components of the model.