Papers
Research papers from arXiv and related sources
TaxonRL: Reinforcement Learning with Intermediate Rewards for Interpretable Fine-Grained Visual Reasoning
Traditional vision-language models struggle with contrastive fine-grained taxonomic reasoning, particularly when distinguishing between visually similar species within the same genus or family. We ...
Maximilian von Klinski, Maximilian Schall
ManipulationNet: An Infrastructure for Benchmarking Real-World Robot Manipulation with Physical Skill Challenges and Embodied Multimodal Reasoning
Dexterous manipulation enables robots to purposefully alter the physical world, transforming them from passive observers into active agents in unstructured environments. This capability is the corn...
Yiting Chen, Kenneth Kimble, Edward H. Adelson, Tamim Asfour, Podshara Chanrungmaneekul, Sachin C...
A Selection Aware View of Black Hole-Galaxy Coevolution at High Redshift
The large population of broad-line Active Galactic Nuclei (AGN) observed with the James Webb Space Telescope (JWST) at $z \gtrsim 4$ opens a new window onto the black hole-galaxy connection in the ...
Francesco Ziparo, Stefano Carniani, Simona Gallerani, Bartolomeo Trefoloni
A Soft Robotic Demonstration in the Stratospher
Machines designed for operation in Space, as well as other extreme environments, need to be both resilient and adaptable when mission parameters change. Soft robots offer advantages in adaptability...
Codrin Tugui, Tirth Thakar, Anatol Gogoj, Alexander White, Ang Leo Li, Alexander Yin, Edward Pomi...
Tendon Force Modeling for Sim2Real Transfer of Reinforcement Learning Policies for Tendon-Driven Robots
Robots which make use of soft or compliant inter- actions often leverage tendon-driven actuation which enables actuators to be placed more flexibly, and compliance to be maintained. However, contro...
Valentin Yuryev, Josie Hughes
Underrepresented in Foundation Model Pretraining Data? A One-Shot Probe
Large-scale Vision-Language Foundation Models (VLFMs), such as CLIP, now underpin a wide range of computer vision research and applications. VLFMs are often adapted to various domain-specific tasks...
Chris Vorster, Mayug Maniparambil, Noel E. O'Connor, Noel Murphy, Derek Molloy
Hold-One-Shot-Out (HOSO) for Validation-Free Few-Shot CLIP Adapters
In many CLIP adaptation methods, a blending ratio hyperparameter controls the trade-off between general pretrained CLIP knowledge and the limited, dataset-specific supervision from the few-shot cas...
Chris Vorster, Mayug Maniparambil, Noel E. O'Connor, Noel Murphy, Derek Molloy
What Does Flow Matching Bring To TD Learning?
Recent work shows that flow matching can be effective for scalar Q-value function estimation in reinforcement learning (RL), but it remains unclear why or how this approach differs from standard cr...
Bhavya Agrawalla, Michal Nauman, Aviral Kumar
A spectral inference method for determining the number of communities in networks
To characterize the community structure in network data, researchers have developed various block-type models, including the stochastic block model, the degree-corrected stochastic block model, the...
Yujia Wu, Xiucai Ding, Jingfei Zhang, Wei Lan, Chih-Ling Tsai
$V_1$: Unifying Generation and Self-Verification for Parallel Reasoners
Test-time scaling for complex reasoning tasks shows that leveraging inference-time compute, by methods such as independently sampling and aggregating multiple solutions, results in significantly be...
Harman Singh, Xiuyu Li, Kusha Sareen, Monishwaran Maheswaran, Sijun Tan, Xiaoxia Wu, Junxiong Wan...
Compliant In-hand Rolling Manipulation Using Tactile Sensing
We investigate in-hand rolling manipulation using a multifingered robot hand, where each finger is compliant and equipped with a tactile fingertip providing contact location and wrench information....
Huan Weng, Yifei Chen, Kevin M. Lynch
The effect of chemical vapor infiltration process parameters on flexural strength of porous α-SiC: A numerical model
The flexural strength variability of α-SiC based ceramics at elevated temperatures creates the need for an Integrated Computational Materials Engineering (ICME) framework that relates the strength ...
Joseph J. Marziale, Jason Sun, Eric A. Walker, Yu Chen, David Salac, James Chen
Statistical Inference for Score Decompositions
We introduce inference methods for score decompositions, which partition scoring functions for predictive assessment into three interpretable components: miscalibration, discrimination, and uncerta...
Timo Dimitriadis, Marius Puke
Grid-agnostic volume of fluid approach with interface sharpening and surface tension for compressible multiphase flows
The interfacial diffusion associated with finite volume method (FVM) discretizations of multiphase flows creates the need for an interface sharpening mechanism. Such solutions for structured quadri...
J. Marziale, J. Sun, D. Salac, J. Chen
Atmospheric neutrino constraints on Lorentz invariance violation with the first six detection units of KM3NeT/ORCA
Lorentz invariance is a fundamental symmetry underlying both the Standard Model of particle physics and General Relativity. Testing its validity provides a direct means of searching for new physics...
KM3NeT Collaboration, O. Adriani, A. Albert, A. R. Alhebsi, S. Alshalloudi, S. Alves Garre, F. A...
Learning Read-Once Determinants and the Principal Minor Assignment Problem
A symbolic determinant under rank-one restriction computes a polynomial of the form $\det(A_0+A_1y_1+\ldots+A_ny_n)$, where $A_0,A_1,\ldots,A_n$ are square matrices over a field $\mathbb{F}$ and $r...
Abhiram Aravind, Abhranil Chatterjee, Sumanta Ghosh, Rohit Gurjar, Roshan Raj, Chandan Saha
Cluster-Level Experiments using Temporal Switchback Designs: Precision Gains in Pricing A/B Tests at LATAM Airlines
Experimentation is central to modern digital businesses, but many operational decisions cannot be randomized at the user level. In such cases, cluster-level experiments, where clusters are usually ...
Nicolás Ferrari-Ortiz, Sebastián Orellana-Montini, Timur Abbiasov, Marie Garkavenko, Rutger Lit
Predicting oscillations in complex networks with delayed feedback
Oscillatory dynamics are common features of complex networks, often playing essential roles in regulating function. Across scales from gene regulatory networks to ecosystems, delayed feedback mecha...
Shijie Liu, Jinliang Han, Tim Rogers, Yongzheng Sun
DiverseDiT: Towards Diverse Representation Learning in Diffusion Transformers
Recent breakthroughs in Diffusion Transformers (DiTs) have revolutionized the field of visual synthesis due to their superior scalability. To facilitate DiTs' capability of capturing meaningful int...
Mengping Yang, Zhiyu Tan, Binglei Li, Xiaomeng Yang, Hesen Chen, Hao Li
Continuous Ventricular Volumetric Quantification in Patients with Arrhythmias using Real-Time 3D CMR-MOTUS
Conventional cardiovascular magnetic resonance (CMR) cine imaging relies on binning multiple heartbeats into a single cardiac cycle, which fails in arrhythmic patients where beat-to-beat variabilit...
Thomas E. Olausson, Maarten L. Terpstra, Rizwan Ahmad, Edwin Versteeg, Casper Beijst, Yuchi Han, ...