Tootfinder

InstaInpaint: Instant 3D-Scene Inpainting with Masked Large Reconstruction Model
Junqi You, Chieh Hubert Lin, Weijie Lyu, Zhengbo Zhang, Ming-Hsuan Yang
https://arxiv.org/abs/2506.10980

InstaInpaint: Instant 3D-Scene Inpainting with Masked Large Reconstruction Model
Recent advances in 3D scene reconstruction enable real-time viewing in virtual and augmented reality. To support interactive operations for better immersiveness, such as moving or editing objects, 3D scene inpainting methods are proposed to repair or complete the altered geometry. However, current approaches rely on lengthy and computationally intensive optimization, making them impractical for real-time or online applications. We propose InstaInpaint, a reference-based feed-forward framework t…

You Are What You Say: Exploiting Linguistic Content for VoicePrivacy Attacks
\"Unal Ege Gaznepoglu, Anna Leschanowsky, Ahmad Aloradi, Prachi Singh, Daniel Tenbrinck, Emanu\"el A. P. Habets, Nils Peters
https://arxiv.org/abs/2506.09521

You Are What You Say: Exploiting Linguistic Content for VoicePrivacy Attacks
Speaker anonymization systems hide the identity of speakers while preserving other information such as linguistic content and emotions. To evaluate their privacy benefits, attacks in the form of automatic speaker verification (ASV) systems are employed. In this study, we assess the impact of intra-speaker linguistic content similarity in the attacker training and evaluation datasets, by adapting BERT, a language model, as an ASV system. On the VoicePrivacy Attacker Challenge datasets, our metho…

Generalizing while preserving monotonicity in comparison-based preference learning models
Julien Fageot, Peva Blanchard, Gilles Bareilles, L\^e-Nguy\^en Hoang
https://arxiv.org/abs/2506.08616

Generalizing while preserving monotonicity in comparison-based preference learning models
If you tell a learning model that you prefer an alternative $a$ over another alternative $b$, then you probably expect the model to be monotone, that is, the valuation of $a$ increases, and that of $b$ decreases. Yet, perhaps surprisingly, many widely deployed comparison-based preference learning models, including large language models, fail to have this guarantee. Until now, the only comparison-based preference learning algorithms that were proved to be monotone are the Generalized Bradley-Ter…

This https://arxiv.org/abs/2409.08906 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_ees…

Gaussian is All You Need: A Unified Framework for Solving Inverse Problems via Diffusion Posterior Sampling
Diffusion models can generate a variety of high-quality images by modeling complex data distributions. Trained diffusion models can also be very effective image priors for solving inverse problems. Most of the existing diffusion-based methods integrate data consistency steps by approximating the likelihood function within the diffusion reverse sampling process. In this paper, we show that the existing approximations are either insufficient or computationally inefficient. To address these issues…

This https://arxiv.org/abs/2504.04178 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csIR_…

MSL: Not All Tokens Are What You Need for Tuning LLM as a Recommender
Large language models (LLMs), known for their comprehension capabilities and extensive knowledge, have been increasingly applied to recommendation systems (RS). Given the fundamental gap between the mechanism of LLMs and the requirement of RS, researchers have focused on fine-tuning LLMs with recommendation-specific data to enhance their performance. Language Modeling Loss (LML), originally designed for language generation tasks, is commonly adopted. However, we identify two critical limitation…

This https://arxiv.org/abs/2505.01287 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csDS_…

Shuffling Cards When You Are of Very Little Brain: Low Memory Generation of Permutations
How can we generate a permutation of the numbers $1$ through $n$ so that it is hard to guess the next element given the history so far? The twist is that the generator of the permutation (the ``Dealer") has limited memory, while the ``Guesser" has unlimited memory. With unbounded memory (actually $n$ bits suffice), the Dealer can generate a truly random permutation where $\ln n$ is the expected number of correct guesses. Our main results establish tight bounds for the relationship between the…

This https://arxiv.org/abs/2505.24198 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csRO_…

Learning Gentle Humanoid Locomotion and End-Effector Stabilization Control
Can your humanoid walk up and hand you a full cup of beer, without spilling a drop? While humanoids are increasingly featured in flashy demos like dancing, delivering packages, traversing rough terrain, fine-grained control during locomotion remains a significant challenge. In particular, stabilizing a filled end-effector (EE) while walking is far from solved, due to a fundamental mismatch in task dynamics: locomotion demands slow-timescale, robust control, whereas EE stabilization requires rap…

Taylor Series Kinematics
Craig W. Looney
https://arxiv.org/abs/2506.06170 https://arxiv.org/pdf/2506.06170

Taylor Series Kinematics
Has it ever occurred to you that the kinematic equations for uniformly accelerated one-dimensional motion are Taylor series expansions? If not, you are in good company. I didn't know this myself until a colleague pointed it out to me many years ago, and I was stunned to learn something new and wonderful about something so familiar. Accordingly, my first objective in this paper is to clearly present the not-widely-known Taylor series derivations of these basic equations to a population primed to…

This https://arxiv.org/abs/2402.08533 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csGT_…

Grace Period is All You Need: Individual Fairness without Revenue Loss in Revenue Management
Imagine you and a friend purchase identical items at a store, yet only your friend received a discount. Would your friend's discount make you feel unfairly treated by the store? And would you be less willing to purchase from that store again in the future? Based on a large-scale online survey that we ran on Prolific, it turns out that the answers to the above questions are positive. Therefore, when allocating resources to different customers, sellers should consider both the total reward and in…

Could an axion-like particle be hidden in $\eta_c\to\gamma\gamma$?
Zhi-Jun Li, Zheng-Yun You, Xiao-Rui Lyu
https://arxiv.org/abs/2506.04144 https://…

Could an axion-like particle be hidden in $η_c\toγγ$?
We discuss the possibility of an axion-like particle being merged in the recent observation of $η_c \to γγ$ at BESIII and find that it cannot be excluded in the current experimental data. The mass, width, and coupling strengths of the axion-like particle are extracted, and several other channels to confirm or exclude the existence of such an axion-like particle are also discussed.

Single-pulse-based interstellar scintillation studies of RRATs
Zi-wei Wu, Wei-wei Zhu, Zi-yao Fang, Qiu-yang Fu, Ji-guang Lu, Ling-qi Meng, Chen-Chen Miao, Xue-li Miao, Jia-rui Niu, Rukeya Rejiefu, Xun Shi, Chao Wang, Meng-yao Xue, Mao Yuan, You-ling Yue, Chun-feng Zhang, Zhen Zhang, Shi-jun Dang, Yu-lan Liu
https://arxiv.org/ab…

Single-pulse-based interstellar scintillation studies of RRATs
The nature of irregularly spaced pulses of rotating radio transients (RRATs) complicates interstellar scintillation studies. In this letter, we report the primary scintillation parameters of a sample of RRATs using pairwise correlations of pulse spectra. Moreover, from the measured scintillation velocities, we constrain their transverse velocities. We also find a reduced modulation index, $\rm{m=0.13\pm0.01}$, for RRAT~J1538+2345. Several possible explanations are discussed. Furthermore, the si…

Breaker: Removing Shortcut Cues with User Clustering for Single-slot Recommendation System
Chao Wang, Yue Zheng, Yujing Zhang, Yan Feng, Zhe Wang, Xiaowei Shi, An You, Yu Chen
https://arxiv.org/abs/2506.00828

Breaker: Removing Shortcut Cues with User Clustering for Single-slot Recommendation System
In a single-slot recommendation system, users are only exposed to one item at a time, and the system cannot collect user feedback on multiple items simultaneously. Therefore, only pointwise modeling solutions can be adopted, focusing solely on modeling the likelihood of clicks or conversions for items by users to learn user-item preferences, without the ability to capture the ranking information among different items directly. However, since user-side information is often much more abundant tha…

Ladies and gentlemen and others, this is why I recommend hosting your own forge, like forgejo: https://mastodon.social/@mcc/114536667832141959
Also, as I recently discovered: Github git implementation is pretty dumb and reports unsolvable conflicts that are automatically solved by…

NextQuill: Causal Preference Modeling for Enhancing LLM Personalization
Xiaoyan Zhao, Juntao You, Yang Zhang, Wenjie Wang, Hong Cheng, Fuli Feng, See-Kiong Ng, Tat-Seng Chua
https://arxiv.org/abs/2506.02368

NextQuill: Causal Preference Modeling for Enhancing LLM Personalization
Personalizing large language models (LLMs) for individual users has become increasingly important as they are progressively integrated into real-world applications to support users' daily lives. However, existing personalization approaches often fail to distinguish which components of model predictions and training data truly reflect user preferences, leading to superficial personalization alignment. In this paper, we introduce NextQuill, a novel LLM personalization alignment framework grounded…