Papers
Research papers from arXiv and related sources
FreeTalk: Emotional Topology-Free 3D Talking Heads
Speech-driven 3D facial animation has advanced rapidly, yet most approaches remain tied to registered template meshes, preventing effective deployment on raw 3D scans with arbitrary topology. At th...
Federico Nocentini, Thomas Besnier, Claudio Ferrari, Stefano Berretti, Mohamed Daoudi
Not All Invariants Are Equal: Curating Training Data to Accelerate Program Verification with SLMs
The synthesis of inductive loop invariants is a critical bottleneck in automated program verification. While Large Language Models (LLMs) show promise in mitigating this issue, they often fail on h...
Ido Pinto, Yizhak Yisrael Elboher, Haoze Wu, Nina Narodytska, Guy Katz
Seeking SOTA: Time-Series Forecasting Must Adopt Taxonomy-Specific Evaluation to Dispel Illusory Gains
We argue that the current practice of evaluating AI/ML time-series forecasting models, predominantly on benchmarks characterized by strong, persistent periodicities and seasonalities, obscures real...
Raeid Saqur, Christoph Bergmeir, Blanka Horvath, Daniel Schmidt, Frank Rudzicz, Terry Lyons
Understanding Reasoning in LLMs through Strategic Information Allocation under Uncertainty
LLMs often exhibit Aha moments during reasoning, such as apparent self-correction following tokens like "Wait," yet their underlying mechanisms remain unclear. We introduce an information-theoretic...
Jeonghye Kim, Xufang Luo, Minbeom Kim, Sangmook Lee, Dongsheng Li, Yuqing Yang
A practical randomized trust-region method to escape saddle points in high dimension
Without randomization, escaping the saddle points of $f \colon \mathbb{R}^d \to \mathbb{R}$ requires at least $Ω(d)$ pieces of information about $f$ (values, gradients, Hessian-vector products). Wi...
Radu-Alexandru Dragomir, Xiaowen Jiang, Bonan Sun, Nicolas Boumal
Agentic workflow enables the recovery of critical materials from complex feedstocks via selective precipitation
We present a multi-agentic workflow for critical materials recovery that deploys a series of AI agents and automated instruments to recover critical materials from produced water and magnet leachat...
Andrew Ritchhart, Sarah I. Allec, Pravalika Butreddy, Krista Kulesa, Qingpu Wang, Dan Thien Nguye...
Standard Model tests with smeared experiment and theory
For Standard Model processes in which on-shell intermediate hadronic states contribute - including inclusive semileptonic decays and long-distance effects in rare exclusive decays such as $D\to π\e...
Andreas Jüttner
RSGen: Enhancing Layout-Driven Remote Sensing Image Generation with Diverse Edge Guidance
Diffusion models have significantly mitigated the impact of annotated data scarcity in remote sensing (RS). Although recent approaches have successfully harnessed these models to enable diverse and...
Xianbao Hou, Yonghao He, Zeyd Boukhers, John See, Hu Su, Wei Sui, Cong Yang
Talk, Evaluate, Diagnose: User-aware Agent Evaluation with Automated Error Analysis
Agent applications are increasingly adopted to automate workflows across diverse tasks. However, due to the heterogeneous domains they operate in, it is challenging to create a scalable evaluation ...
Penny Chong, Harshavardhan Abichandani, Jiyuan Shen, Atin Ghosh, Min Pyae Moe, Yifan Mai, Daniel ...
ViFeEdit: A Video-Free Tuner of Your Video Diffusion Transformer
Diffusion Transformers (DiTs) have demonstrated remarkable scalability and quality in image and video generation, prompting growing interest in extending them to controllable generation and editing...
Ruonan Yu, Zhenxiong Tan, Zigeng Chen, Songhua Liu, Xinchao Wang
Seeing Beyond: Extrapolative Domain Adaptive Panoramic Segmentation
Cross-domain panoramic semantic segmentation has attracted growing interest as it enables comprehensive 360° scene understanding for real-world applications. However, it remains particularly challe...
Yuanfan Zheng, Kunyu Peng, Xu Zheng, Kailun Yang
Agent Lifecycle Toolkit (ALTK): Reusable Middleware Components for Robust AI Agents
As AI agents move from demos into enterprise deployments, their failure modes become consequential: a misinterpreted tool argument can corrupt production data, a silent reasoning error can go undet...
Zidane Wright, Jason Tsay, Anupama Murthi, Osher Elhadad, Diego Del Rio, Saurabh Goyal, Kiran Kat...
Probing the neutrino mass through semileptonic meson decays
We argue that a detailed analysis of semileptonic decays can test the possibility of a massive neutrino. The key observable, related to the forward-backward asymmetry, is exactly zero for a massles...
Damir Bečirević, Claire Chevallier, Svjetlana Faifer, Nejc Košnik, Lovre Pavičić
Financial Transaction Retrieval and Contextual Evidence for Knowledge-Grounded Reasoning
Nowadays, success of financial organizations heavily depends on their ability to process digital traces generated by their clients, e.g., transaction histories, gathered from various sources to imp...
Artem Sakhno, Daniil Tomilov, Yuliana Shakhvalieva, Inessa Fedorova, Daria Ruzanova, Omar Zoloev,...
Evasive Intelligence: Lessons from Malware Analysis for Evaluating AI Agents
Artificial intelligence (AI) systems are increasingly adopted as tool-using agents that can plan, observe their environment, and take actions over extended time periods. This evolution challenges c...
Simone Aonzo, Merve Sahin, Aurélien Francillon, Daniele Perito
Unlocking the Value of Text: Event-Driven Reasoning and Multi-Level Alignment for Time Series Forecasting
Existing time series forecasting methods primarily rely on the numerical data itself. However, real-world time series exhibit complex patterns associated with multimodal information, making them di...
Siyuan Wang, Peng Chen, Yihang Wang, Wanghui Qiu, Chenjuan Guo, Bin Yang, Yang Shu
The Steep-spectrum Radio-loud AGN Luminosity Function and Its Implications for Black Hole Growth and Star Formation
We study the cosmic evolution of radio-loud active galactic nuclei (AGNs) using a beaming-minimized sample of 4{,}555 steep-spectrum sources over $0<z\lesssim4$, compiled from the XXL survey, VLA-C...
Wenjie Wang, Zunli Yuan, B. Šlaus, Hongwei Yu, Yu Luo
The Social Sycophancy Scale: A psychometrically validated measure of sycophancy
Large Language Model (LLM) sycophancy is a growing concern. The current literature has largely examined sycophancy in contexts with clear right and wrong answers, like coding. However, AI is increa...
Jean Rehani, Victoria Oldemburgo de Mello, Dariya Ovsyannikova, Ashton Anderson, Michael Inzlicht
Deep Reinforcement Learning for Fano Hypersurfaces
We design a deep reinforcement learning algorithm to explore a high-dimensional integer lattice with sparse rewards, training a feedforward neural network as a dynamic search heuristic to steer exp...
Marc Truter
MV2UV: Generating High-quality UV Texture Maps with Multiview Prompts
Generating high-quality textures for 3D assets is a challenging task. Existing multiview texture generation methods suffer from the multiview inconsistency and missing textures on unseen parts, whi...
Zheng Zhang, Qinchuan Zhang, Yuteng Ye, Zhi Chen, Penglei Ji, Mengfei Li, Wenxiao Zhang, Yuan Liu