1035593 results (page 52 of 41424)
-
Tstars-Tryon 1.0: Robust and Realistic Virtual Try-On for Diverse Fashion Items
Recent advances in image generation and editing have opened new opportunities for virtual try-on. However, existing methods still struggle to meet complex real-world demands. We present Tstars-Tryon 1.0, a commercial-scale virtual try-on system that is robust, realistic, versatile, and highly efficient. First, our system maintains a high success rate across challenging cases like extreme poses, se…
-
AnyRecon: Arbitrary-View 3D Reconstruction with Video Diffusion Model
Sparse-view 3D reconstruction is essential for modeling scenes from casual captures, but remain challenging for non-generative reconstruction. Existing diffusion-based approaches mitigates this issues by synthesizing novel views, but they often condition on only one or two capture frames, which restricts geometric consistency and limits scalability to large or diverse scenes. We propose AnyRecon, …
-
Calibration-Induced Systematics in SALT3 Training and Their Impact on Dark Energy Constraints from Stage IV Supernova Surveys
In the coming years, the Vera Rubin Observatory's Legacy Survey of Space and Time (Rubin-LSST) and the Nancy Grace Roman Space Telescope's (Roman) High Latitude Time Domain Survey (HLTDS) are expected to discover more than a million Type Ia supernovae (SNe Ia), several orders of magnitude more than current samples and with a tighter control on systematic uncertainties. One of the largest systemati…
-
Precision Kinematic Sunyaev--Zel'dovich Measurements Across Halo Mass and Redshift with DESI DR2 and ACT DR6: Part II. Bright Galaxy Survey and Emission-Line Galaxies
We present the first high-significance spectroscopic stacked kinetic Sunyaev-Zel'dovich (kSZ) measurements of circumgalactic gas profiles for both Bright Galaxy Survey (BGS) and Emission Line Galaxy (ELG) tracers, combining DESI Data Release 2 with ACT Data Release 6. Using reconstructed line-of-sight velocities from the DESI galaxies and high-resolution ACT temperature maps, we detect the kSZ sig…
-
Precision Kinematic Sunyaev--Zel'dovich Measurements Across Halo Mass and Redshift with DESI DR2 and ACT DR6: Part I. Luminous Red Galaxies
We present the most precise measurements of the kinetic Sunyaev-Zel'dovich (kSZ) effect around luminous red galaxies to date, detecting the signal at $18σ$ significance in both harmonic and configuration space. Our analysis cross-correlates 2.4 million spectroscopic LRGs from the Dark Energy Spectroscopic Instrument (DESI) DR2 sample with Data Release 6 (DR6) of the Atacama Cosmology Telescope (AC…
-
Viscously Stirring Particle Disks into Lorentzians and Gaussians to Infer Dynamical and Collisional Masses (ARKS XIII)
Disks (Keplerian or otherwise, particulate or fluid) are often assumed to have densities that drop off vertically as Gaussians. Recent mm-wave imaging of circumstellar debris disks contradicts this assumption, revealing vertical profiles in dust that resemble Lorentzians. As part of the ARKS ALMA Large Program, we calculate how Lorentzians and Gaussians define an evolutionary sequence for disks of…
-
PlayCoder: Making LLM-Generated GUI Code Playable
Large language models (LLMs) have achieved strong results in code generation, but their ability to generate GUI applications, especially games, remains insufficiently studied. Existing benchmarks mainly evaluate correctness through test cases, which are inadequate for GUI applications because these systems are interactive, event-driven, and require correct state transitions across sequences of use…
-
CityRAG: Stepping Into a City via Spatially-Grounded Video Generation
We address the problem of generating a 3D-consistent, navigable environment that is spatially grounded: a simulation of a real location. Existing video generative models can produce a plausible sequence that is consistent with a text (T2V) or image (I2V) prompt. However, the capability to reconstruct the real world under arbitrary weather conditions and dynamic object configurations is essential f…
-
DR-Venus: Towards Frontier Edge-Scale Deep Research Agents with Only 10K Open Data
Edge-scale deep research agents based on small language models are attractive for real-world deployment due to their advantages in cost, latency, and privacy. In this work, we study how to train a strong small deep research agent under limited open-data by improving both data quality and data utilization. We present DR-Venus, a frontier 4B deep research agent for edge-scale deployment, built entir…
-
Generalization at the Edge of Stability
Training modern neural networks often relies on large learning rates, operating at the edge of stability, where the optimization dynamics exhibit oscillatory and chaotic behavior. Empirically, this regime often yields improved generalization performance, yet the underlying mechanism remains poorly understood. In this work, we represent stochastic optimizers as random dynamical systems, which often…
-
Wan-Image: Pushing the Boundaries of Generative Visual Intelligence
We present Wan-Image, a unified visual generation system explicitly engineered to paradigm-shift image generation models from casual synthesizers into professional-grade productivity tools. While contemporary diffusion models excel at aesthetic generation, they frequently encounter critical bottlenecks in rigorous design workflows that demand absolute controllability, complex typography rendering,…
-
Phase Transitions in the Fluctuations of Functionals of Random Neural Networks
We establish central and non-central limit theorems for sequences of functionals of the Gaussian output of an infinitely-wide random neural network on the d-dimensional sphere . We show that the asymptotic behaviour of these functionals as the depth of the network increases depends crucially on the fixed points of the covariance function, resulting in three distinct limiting regimes: convergence t…
-
Safe Continual Reinforcement Learning in Non-stationary Environments
Reinforcement learning (RL) offers a compelling data-driven paradigm for synthesizing controllers for complex systems when accurate physical models are unavailable; however, most existing control-oriented RL methods assume stationarity and, therefore, struggle in real-world non-stationary deployments where system dynamics and operating conditions can change unexpectedly. Moreover, RL controllers a…
-
Generative Drifting for Conditional Medical Image Generation
Conditional medical image generation plays an important role in many clinically relevant imaging tasks. However, existing methods still face a fundamental challenge in balancing inference efficiency, patient-specific fidelity, and distribution-level plausibility, particularly in high-dimensional 3D medical imaging. In this work, we propose GDM, a generative drifting framework that reformulates det…
-
UniT: Toward a Unified Physical Language for Human-to-Humanoid Policy Learning and World Modeling
Scaling humanoid foundation models is bottlenecked by the scarcity of robotic data. While massive egocentric human data offers a scalable alternative, bridging the cross-embodiment chasm remains a fundamental challenge due to kinematic mismatches. We introduce UniT (Unified Latent Action Tokenizer via Visual Anchoring), a framework that establishes a unified physical language for human-to-humanoid…
-
Greedy Routing in a Sequentially Grown One-Dimensional Random Graph
We analyze greedy routing in a random graph G_n constructed on the vertex set V = {1, 2, ..., n} embedded in Z. Vertices are inserted according to a uniform random permutation pi, and each newly inserted vertex connects to its nearest already-inserted neighbors on the left and right (if they exist). This work addresses a conjecture originating from empirical studies (Ponomarenko et al., 2011; Malk…
-
Sensitivity Uncertainty Alignment in Large Language Models
We propose Sensitivity-Uncertainty Alignment (SUA), a framework for analyzing failures of large language models under adversarial and ambiguous inputs. We argue that adversarial sensitivity and ambiguity reflect a common issue: misalignment between prediction instability and model uncertainty. A reliable model should express higher uncertainty when its predictions are unstable; failure to do so le…
-
FASTER: Value-Guided Sampling for Fast RL
Some of the most performant reinforcement learning algorithms today can be prohibitively expensive as they use test-time scaling methods such as sampling multiple action candidates and selecting the best one. In this work, we propose FASTER, a method for getting the benefits of sampling-based test-time scaling of diffusion-based policies without the computational cost by tracing the performance ga…
-
FB-NLL: A Feature-Based Approach to Tackle Noisy Labels in Personalized Federated Learning
Personalized Federated Learning (PFL) aims to learn multiple task-specific models rather than a single global model across heterogeneous data distributions. Existing PFL approaches typically rely on iterative optimization-such as model update trajectories-to cluster users that need to accomplish the same tasks together. However, these learning-dynamics-based methods are inherently vulnerable to lo…
-
VLA Foundry: A Unified Framework for Training Vision-Language-Action Models
We present VLA Foundry, an open-source framework that unifies LLM, VLM, and VLA training in a single codebase. Most open-source VLA efforts specialize on the action training stage, often stitching together incompatible pretraining pipelines. VLA Foundry instead provides a shared training stack with end-to-end control, from language pretraining to action-expert fine-tuning. VLA Foundry supports bot…
-
Breaking the UV Luminosity Function Degeneracy:Self-Interacting Dark Matter Constraints from Reionization Topology
Self-interacting dark matter (SIDM) is the leading framework resolving small-scale cold dark matter (CDM) crises, yet high-redshift SIDM constraints are fundamentally limited by degeneracies between dark matter microphysics and galaxy formation astrophysics. We demonstrate that the UV luminosity function alone cannot constrain SIDM: star formation suppression from SIDM halo core formation is fully…
-
Benign Overfitting in Adversarial Training for Vision Transformers
Despite the remarkable success of Vision Transformers (ViTs) across a wide range of vision tasks, recent studies have revealed that they remain vulnerable to adversarial examples, much like Convolutional Neural Networks (CNNs). A common empirical defense strategy is adversarial training, yet the theoretical underpinnings of its robustness in ViTs remain largely unexplored. In this work, we present…
-
Coherent Direct Multipath SLAM
Challenging indoor and urban environments with severe multipath propagation and obstructed LoS (OLoS) degrade classical radio frequency (RF) positioning. Multipath-based simultaneous localization and mapping (MP-SLAM) is a promising remedy, building and exploiting a map of the propagation environment to enhance the robustness. Emerging distributed multiple-input multiple-output (D-MIMO)/extremely …
-
Adaptive MSD-Splitting: Enhancing C4.5 and Random Forests for Skewed Continuous Attributes
The discretization of continuous numerical attributes remains a persistent computational bottleneck in the induction of decision trees, particularly as dataset dimensions scale. Building upon the recently proposed MSD-Splitting technique -- which bins continuous data using the empirical mean and standard deviation to dramatically improve the efficiency and accuracy of the C4.5 algorithm -- we intr…
-
ReImagine: Rethinking Controllable High-Quality Human Video Generation via Image-First Synthesis
Human video generation remains challenging due to the difficulty of jointly modeling human appearance, motion, and camera viewpoint under limited multi-view data. Existing methods often address these factors separately, resulting in limited controllability or reduced visual quality. We revisit this problem from an image-first perspective, where high-quality human appearance is learned via image ge…