Papers
Research papers from arXiv and related sources
When Rubrics Fail: Error Enumeration as Reward in Reference-Free RL Post-Training for Virtual Try-On
Reinforcement learning with verifiable rewards (RLVR) and Rubrics as Rewards (RaR) have driven strong gains in domains with clear correctness signals and even in subjective domains by synthesizing ...
Wisdom Ikezogwo, Mehmet Saygin Seyfioglu, Ranjay Krishna, Karim Bouyarmane
Physics of active polymers: scaling analysis via a compounding formula
Active polymeric systems exhibit a rich spectrum of non-equilibrium phenomena arising from stochastic forces that explicitly break detailed balance. Despite the rapid growth of experimental and num...
Takahiro Sakaue, Enrico Carlon
The Fragility Of Moral Judgment In Large Language Models
People increasingly use large language models (LLMs) for everyday moral and interpersonal guidance, yet these systems cannot interrogate missing context and judge dilemmas as presented. We introduc...
Tom van Nuenen, Pratik S. Sachdeva
JoinActors: A Modular Library for Actors with Join Patterns
Join patterns are a high-level programming construct for message-passing applications. They offer an intuitive and declarative approach for specifying how concurrent and distributed components coor...
Ayman Hussein, Philipp Haller, Ioannis Karras, Hernán Melgratti, Alceste Scalas, Emilio Tuosto
Test-then-Punish: A Statistical Approach to Repeated Games
We study discounted infinitely repeated games in which players agree on a cooperative mixed action profile but, at each step, observe only the realized pure actions. This form of imperfect monitori...
Aymeric Capitaine, Antoine Scheid, Etienne Boursier, Alain Durmus, Michael I. Jordan
Identification of an Unreported Structure Type in GdNiSn4 and Its Implications for Materials Prediction
Crystal structures define how matter is organized at the atomic level. In the realm of crystalline inorganic materials, new structure types are rarely found, and most experimentally-realized struct...
Xin Zhang, Scott B. Lee, Sudipta Chatterjee, Hanqi Pi, Yi Yang, Fatmagül Katmer, Emily G. Ward, D...
From Decoupled to Coupled: Robustness Verification for Learning-based Keypoint Detection with Joint Specifications
Keypoint detection underpins many vision tasks, including pose estimation, viewpoint recovery, and 3D reconstruction, yet modern neural models remain vulnerable to small input perturbations. Despit...
Xusheng Luo, Changliu Liu
Long-Integration Magnetar Burst Observatory (LIMBO): Instrument Summary and Early FRB Rate Constraints
The Long-Integration Magnetar Burst Observatory (LIMBO) is a real-time radio transient detection pipeline designed to search for dispersed fast radio bursts (FRBs) from Galactic magnetars. Deployed...
Darby McCauley, Aaron Parsons, Wei Liu, Wenbin Lu, Dirk Wright, Dan Werthimer
Advancing the Effective-One-Body Framework in the Test-Mass Limit
We present SEOB-TML, an enhanced effective-one-body (EOB) framework for the test-mass limit, optimized for quasi-circular, spin-aligned binary black holes. On the dynamical side, we introduce a qua...
Nami Nishimura, Alessandra Buonanno, Guglielmo Faggioli, Maarten van de Meent, Gaurav Khanna
Exocomets of $β$ Pictoris II: Two dynamical families of exocomets simulated with REBOUND
We investigate the dynamical evolution of particles in the $β$ Pic system to determine likely formation pathways to the present-day observed exocomet populations. We aim to relate these results to ...
K. P. Jaworska, H. J. Hoeijmakers
Vertical Structure of Protoplanetary Disks in Scattered Light: A large sample analysis
High-resolution scattered-light imaging has revealed complex morphologies in protoplanetary and circumstellar disks. Measuring the vertical height of the scattering surface is key to understanding ...
J. Byrne, C. Ginski, R. F. van Capelleveen, N. Fitzgerald, A. Garufi, C. Coyne, C. Lawlor, D. McL...
Core-bound waves on a Gross-Pitaevskii vortex
We find the dispersion relations of two elusive families of core-bound excitations of the Gross-Pitaevskii (GP) vortex, varicose (axisymmetric) and fluting (quadrupole) waves. For wavelengths of or...
Evan Papoutsis, Nathan Apfel, Nir Navon
POET-X: Memory-efficient LLM Training by Scaling Orthogonal Transformation
Efficient and stable training of large language models (LLMs) remains a core challenge in modern machine learning systems. To address this challenge, Reparameterized Orthogonal Equivalence Training...
Zeju Qiu, Lixin Liu, Adrian Weller, Han Shi, Weiyang Liu
Censored LLMs as a Natural Testbed for Secret Knowledge Elicitation
Large language models sometimes produce false or misleading responses. Two approaches to this problem are honesty elicitation -- modifying prompts or weights so that the model answers truthfully --...
Helena Casademunt, Bartosz Cywiński, Khoi Tran, Arya Jakkli, Samuel Marks, Neel Nanda
cuRoboV2: Dynamics-Aware Motion Generation with Depth-Fused Distance Fields for High-DoF Robots
Effective robot autonomy requires motion generation that is safe, feasible, and reactive. Current methods are fragmented: fast planners output physically unexecutable trajectories, reactive control...
Balakumar Sundaralingam, Adithyavairavan Murali, Stan Birchfield
NL2GDS: LLM-aided interface for Open Source Chip Design
The growing complexity of hardware design and the widening gap between high-level specifications and register-transfer level (RTL) implementation hinder rapid prototyping and system design. We intr...
Max Eland, Jeyan Thiyagalingam, Dinesh Pamunuwa, Roshan Weerasekera
Observing and Controlling Features in Vision-Language-Action Models
Vision-Language-Action Models (VLAs) have shown remarkable progress towards embodied intelligence. While their architecture partially resembles that of Large Language Models (LLMs), VLAs exhibit hi...
Hugo Buurmeijer, Carmen Amo Alonso, Aiden Swann, Marco Pavone
Towards Provably Unbiased LLM Judges via Bias-Bounded Evaluation
As AI models progress beyond simple chatbots into more complex workflows, we draw ever closer to the event horizon beyond which AI systems will be utilized in autonomous, self-maintaining feedback ...
Benjamin Feuer, Lucas Rosenblatt, Oussama Elachqar
Towards 3D Scene Understanding of Gas Plumes in LWIR Hyperspectral Images Using Neural Radiance Fields
Hyperspectral images (HSI) have many applications, ranging from environmental monitoring to national security, and can be used for material detection and identification. Longwave infrared (LWIR) HS...
Scout Jarman, Zigfried Hampel-Arias, Adra Carr, Kevin R. Moon
Leveraging LLM Parametric Knowledge for Fact Checking without Retrieval
Trustworthiness is a core research challenge for agentic AI systems built on Large Language Models (LLMs). To enhance trust, natural language claims from diverse sources, including human-written te...
Artem Vazhentsev, Maria Marina, Daniil Moskovskiy, Sergey Pletenev, Mikhail Seleznyov, Mikhail Sa...