Tootfinder

A look at Justin Sun's lawsuit against Bloomberg for publishing his holdings, which he claims he provided confidentially to qualify for its Billionaires Index (Molly White/Citation Needed)
https://www.citationneeded.news/justin-sun-bloomberg-lawsuit/

As he builds US power, Justin Sun fights to control his story
A crypto billionaire who once feared arrest in the US is now a Trump business adviser and White House guest. His lawsuit against Bloomberg reveals what he doesn't want Americans to know about his crypto fortune.

A look at Justin Sun's lawsuit against Bloomberg for publishing his holdings, which he claims he provided confidentially to qualify for its Billionaires Index (Molly White/Citation Needed)
https://www.citationneeded.news/justin-sun-bloomberg-lawsuit/

As he builds US power, Justin Sun fights to control his story
A crypto billionaire who once feared arrest in the US is now a Trump business adviser and White House guest. His lawsuit against Bloomberg reveals what he doesn't want Americans to know about his crypto fortune.

ParaAegis: Parallel Protection for Flexible Privacy-preserved Federated Learning
Zihou Wu (School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China), Yuecheng Li (School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China), Tianchi Liao (School of Software Engineering, Sun Yat-sen University, Zhuhai, China), Jian Lou (School of Software Engineering, Sun Yat-sen University, Zhuhai, China), Chuan Chen (School of Computer Science and E…

ParaAegis: Parallel Protection for Flexible Privacy-preserved Federated Learning
Federated learning (FL) faces a critical dilemma: existing protection mechanisms like differential privacy (DP) and homomorphic encryption (HE) enforce a rigid trade-off, forcing a choice between model utility and computational efficiency. This lack of flexibility hinders the practical implementation. To address this, we introduce ParaAegis, a parallel protection framework designed to give practitioners flexible control over the privacy-utility-efficiency balance. Our core innovation is a strat…

Replaced article(s) found for cs.CV. https://arxiv.org/list/cs.CV/new
[4/4]:
- IRL-VLA: Training an Vision-Language-Action Policy via Reward World Model
Jiang, Gao, Wang, Sun, Wang, Heng, Sun, Tang, Zhu, Chai, Wang, Gu, Jiang, Sun

Three dimensional magnetic reconnection mediated with plasmoids and the resulted multi-thermal emissions in the cool atmosphere of the Sun
Guanchong Cheng, Lei Ni, Robert Cameron, Hardi Peter, Yajie Chen, Jun Lin
https://arxiv.org/abs/2508.11013

Three dimensional magnetic reconnection mediated with plasmoids and the resulted multi-thermal emissions in the cool atmosphere of the Sun
Flux emergence is ubiquitous in the Sun's lower atmosphere, where the emerging magnetic flux can reconnect with the pre-existing magnetic field. We investigate plasmoid formation and the resulting multi-thermal emissions during three-dimensional magnetic reconnection in the lower solar atmosphere. We performed 3D radiation magnetohydrodynamic simulations using the MURaM code, which incorporates solar convection and radiative transfer. A flat magnetic flux sheet was introduced into the convectio…

Notwithstanding the awful ping times this would need billions of times more material than is available in the whole solar system, including the sun.
Or roughly as much shit as comes out of that man’s mouth.

Using Doppler Imaging to model stellar activity and search for planets around Sun-like stars
Baptiste Klein, Suzanne Aigrain, Michael Cretignier, Xavier Dumusque, Khaled Al Moulla, Jean-Fran\c{c}ois Donati, Niamh K. O'Sullivan, Haochuan Yu, Andrew Collier Cameron, Oscar Barrag\'an, Annelies Mortier, Alessandro Sozzetti
https://arxi…

Using Doppler Imaging to model stellar activity and search for planets around Sun-like stars
Doppler Imaging (DI) is a well-established technique to map a physical field at a stellar surface from a time series of high-resolution spectra. In this proof-of-concept study, we aim to show that traditional DI algorithms, originally designed for rapidly-rotating stars, have also the ability to model the activity of Sun-like stars, when observed with new-generation highly-stable spectrographs, and search for low-mass planets around them. We used DI to retrieve the relative brightness distribut…

Muscle beaches, drag racing, and drones falling into the sea. Summer in Odesa hasn’t stopped: https://benborges.xyz/2025/08/18/muscle-beaches-drag-racing-and.html

At the park with the kid.
Playground looks like it was semi recently pressure washed but this little guy hung on in a corner.
#LichenSubscribe

Five years ago, I put my iPhone 11 in a case and have been using it since then without any issues. None of my previous phones ever lasted that long. It’s really a shame that Apple is now giving gold bars to wannabe sun kings … 😞

🇺🇦 #NowPlaying on KEXP's #Early
Brittany Davis:
🎵 Sun and Moon
#BrittanyDavis
https://brittany-davis.bandcamp.com/track/sun-and-moon
https://open.spotify.com/track/56ZVz1WYmhu86W7ZQ85mud

Zahlen, bitte! Riesenauflage dank Zeitungsente – The Moon Great Hoax
1835 erschienen in der New York Sun sechs Artikel über Leben auf dem Mond, die lange für Aufsehen sorgten – bis herauskam, dass sie frei erfunden waren.

The ‘Obfuscated C Code Contest’ Confronts the Age of AI https://thenewstack.io/the-obfuscated-c-code-contest-confronts-the-age-of-ai/ - I was sitting at the next Sun 3/60 over from Ian Phillipps at Cambridge Consultants Ltd in the UK in 1988 when he was wri…

The 'Obfuscated C Code Contest' Confronts the Age of AI
The contest, which encourages programmers to have fun with C by writing intentionally difficult-to-understand code, was celebrated with a live online ceremony, a revival of a 40-year-old tradition.

Surprise during today's #Bochum (Germany) #sunset - the Sun set right behind the famous #Tetraeder - https://www.tetraeder-bottrop.de - which is 22.3 km away from my vantage point as the crow flies.

May It Be Time
- four years old and I'm still proud of it -
#NowPlaying #OriginalMusic
https://muz4now.…

Jules Witcover, the journalist known for his long-running syndicated column Politics Today co-written with his Baltimore Sun colleague Jack Germond, died at 98 (Bart Barnes/Washington Post)
https://www.washingtonpost.com/obituaries/2025/08/18/jules-witcover-dead/

Jules Witcover, political columnist who relished the horse race, dies at 98
He was one of the best-sourced political reporters of his generation, known for a long-running column he wrote with Baltimore Sun colleague Jack Germond.

Age of Information Aided Intelligent Grant-Free Massive Access for Heterogeneous mMTC Traffic
Zhongwen Sun, Wei Chen, Yuxuan Sun, Bo Ai
https://arxiv.org/abs/2509.14503 https://…

Age of Information Aided Intelligent Grant-Free Massive Access for Heterogeneous mMTC Traffic
With the arrival of 6G, the Internet of Things (IoT) traffic is becoming more and more complex and diverse. To meet the diverse service requirements of IoT devices, massive machine-type communications (mMTC) becomes a typical scenario, and more recently, grant-free random access (GF-RA) presents a promising direction due to its low signaling overhead. However, existing GF-RA research primarily focuses on improving the accuracy of user detection and data recovery, without considering the heterog…

Good morning!

Our brand-new institute brochure is here! 🌞🪐✨
Across 40 pages, you’ll find an overview of our research topics, methods, and infrastructure—plus insights into public events, training, and more.
Enjoy reading! Follow this link: https://www.mps.mpg.de/8480541/institute-brochure…

A traveling exhibit called Arte de Lšgrimas—"Art of Tears"—is now on display at Yale Divinity School, showcasing artwork by migrant children and depicting the sorrows and traumas they endured on their journeys. Read our new story by Kim Lawton. https://divinity.yale.edu/news…

@… just released a ui update. I haven't explored, I just popped in to check if East of the Sun was in my busking book and omg it's suddenly beautiful! 😮

So the Chinese have got a new type of battery that works at - 40ºC !
This will be game-changing in the arctic and antarctica, hopefully making diesel generators obsolete. Charge the batteries during the endless sun of the summer, use the energy during the endless night of the winter...

CATL says next-gen sodium-ion battery supports 500 km range, readies for 2026 mass production
CATL announced its sodium-ion battery achieves 175 Wh/kg and 500 km range, with certified safety and 2026 mass supply.

The sun has risen
Morning tasks are completed
It's time for a nap.
#dailyhaikuprompt - morning
#haiku
#poem

Boosts appreciated.
Sign making advice:
#NoKings was my 5th protest since 2017 and my 3rd this year. I'd love to get better at making signs.
I was thinking of buying a cheap projector I could hook up to my Mac, project onto poster board, draw light outlines from the projection, and then fill them in with markers.
Anyone have a recommendation for a sub $100 projector?
…

Sonnet 130 - CXXX
My mistress' eyes are nothing like the sun;
Coral is far more red, than her lips red:
If snow be white, why then her breasts are dun;
If hairs be wires, black wires grow on her head.
I have seen roses damasked, red and white,
But no such roses see I in her cheeks;
And in some perfumes is there more delight
Than in the breath that from my mistress reeks.
I love to hear her speak, yet well I know
That music hath …

#Neurotypicals: You need to be bored. Next time you go to the gym, don't listen to that podcast. Just try to be in your head for a while. Maybe you'll think about the meaning of life, and maybe you'll figure it out.
My #ADHD brain trying to unload the dishwasher without a podcast: Hey, Remember the intro to Clifford the Big Red Dog? That song? You sort of paid attention to it for a few seconds while our kid was watching it. I remember those 5 seconds. Let's sing that intro... just that first part though. We're just going to keep doing that, over and over, hundreds of times in a row.
Neurotypicals: People don't like to be bored. People will give themselves electric shocks to not be bored. They don't want to think about the big questions
My ADHD brain, still trying to unload the dishwasher without a podcast: ♪ Welcome to Birdwell island, Sun and the sky is smilin' ♪ ♪ ♪ Welcome to Birdwell island, Sun and the sky is smilin' ♪ ♪ ♪ Welcome to Birdwell island, Sun and the sky is smilin' ♪ ♪ ♪ Welcome to Birdwell island, Sun and the sky is smilin' ♪ ♪ ♪ Welcome to Birdwell island, Sun and the sky is smilin' ♪ ♪ ♪ Welcome to Birdwell island, Sun and the sky is smilin' ♪ ♪ ♪ Welcome to Birdwell island, Sun and the sky is smilin' ♪ ♪ ♪ Welcome to Birdwell island, Sun and the sky is smilin' ♪ ♪ ♪ Welcome to Birdwell island, Sun and the sky is smilin' ♪ ♪ ♪ Welcome to Birdwell island, Sun and the sky is smilin' ♪ ♪
https://youtu.be/orQKfIXMiA8

SMILES Data Release II: Probing Galaxy Evolution during Cosmic Noon and Beyond with NIRSpec Medium-Resolution Spectra
Yongda Zhu, Nina Bonaventura, Yang Sun, George H. Rieke, Stacey Alberts, Jianwei Lyu, Jane E. Morrison, Zhiyuan Ji, Eiichi Egami, Jakob M. Helton, Marcia J. Rieke, Pierluigi Rinaldi, Fengwu Sun, Christopher N. A. Willmer
https://

SMILES Data Release II: Probing Galaxy Evolution during Cosmic Noon and Beyond with NIRSpec Medium-Resolution Spectra
We present the second data release of the Systematic Mid-Infrared Instrument (MIRI) Legacy Extragalactic Survey (SMILES), focusing on JWST/NIRSpec medium-resolution spectroscopy of galaxies across cosmic time. This release includes spectroscopic observations of 166 galaxies spanning $0 < z < 7.5$, sampling star-forming galaxies, quiescent systems, and active galactic nuclei (AGN), with an emphasis on galaxies at cosmic noon ($z \sim 1$-3). We describe the target selection strategy, the observat…

Brian Schottenheimer shares feelings on dealing with infamous sun glare in Week 7 https://www.si.com/nfl/cowboys/news/brian-schottenheimer-shares-feelings-dealing-infamous-sun-glare-nfl-week-7

SynBench: A Benchmark for Differentially Private Text Generation
Yidan Sun, Viktor Schlegel, Srinivasan Nandakumar, Iqra Zahid, Yuping Wu, Yulong Wu, Hao Li, Jie Zhang, Warren Del-Pinto, Goran Nenadic, Siew Kei Lam, Anil Anthony Bharath
https://arxiv.org/abs/2509.14594

SynBench: A Benchmark for Differentially Private Text Generation
Data-driven decision support in high-stakes domains like healthcare and finance faces significant barriers to data sharing due to regulatory, institutional, and privacy concerns. While recent generative AI models, such as large language models, have shown impressive performance in open-domain tasks, their adoption in sensitive environments remains limited by unpredictable behaviors and insufficient privacy-preserving datasets for benchmarking. Existing anonymization methods are often inadequate…

Picture in picture.
#Photography #prince_edward_island

AgentCTG: Harnessing Multi-Agent Collaboration for Fine-Grained Precise Control in Text Generation
Xinxu Zhou, Jiaqi Bai, Zhenqi Sun, Fanxiang Zeng, Yue Liu
https://arxiv.org/abs/2509.13677

AgentCTG: Harnessing Multi-Agent Collaboration for Fine-Grained Precise Control in Text Generation
Although significant progress has been made in many tasks within the field of Natural Language Processing (NLP), Controlled Text Generation (CTG) continues to face numerous challenges, particularly in achieving fine-grained conditional control over generation. Additionally, in real scenario and online applications, cost considerations, scalability, domain knowledge learning and more precise control are required, presenting more challenge for CTG. This paper introduces a novel and scalable frame…

Tonight I ate fried scallops and clam fritters beside the water as the sun went down. Got a little chilly but otherwise a great evening to cap off a fun day at the zoo.

DEFENDCLI: {Command-Line} Driven Attack Provenance Examination
Peilun Wu, Nan Sun, Nour Moustafa, Youyang Qu, Ming Ding
https://arxiv.org/abs/2508.12553 https://

DEFENDCLI: {Command-Line} Driven Attack Provenance Examination
Endpoint Detection and Response (EDR) solutions embrace the method of attack provenance graph to discover unknown threats through system event correlation. However, this method still faces some unsolved problems in the fields of interoperability, reliability, flexibility, and practicability to deliver actionable results. Our research highlights the limitations of current solutions in detecting obfuscation, correlating attacks, identifying low-frequency events, and ensuring robust context awaren…

CollabVLA: Self-Reflective Vision-Language-Action Model Dreaming Together with Human
Nan Sun, Yongchang Li, Chenxu Wang, Huiying Li, Huaping Liu
https://arxiv.org/abs/2509.14889

CollabVLA: Self-Reflective Vision-Language-Action Model Dreaming Together with Human
In this work, we present CollabVLA, a self-reflective vision-language-action framework that transforms a standard visuomotor policy into a collaborative assistant. CollabVLA tackles key limitations of prior VLAs, including domain overfitting, non-interpretable reasoning, and the high latency of auxiliary generative models, by integrating VLM-based reflective reasoning with diffusion-based action generation under a mixture-of-experts design. Through a two-stage training recipe of action groundin…

TRACY: Benchmarking Execution Efficiency of LLM-Based Code Translation
Zhihao Gong, Zeyu Sun, Dong Huang, Qingyuan Liang, Jie M. Zhang, Dan Hao
https://arxiv.org/abs/2508.11468 …

TRACY: Benchmarking Execution Efficiency of LLM-Based Code Translation
Automatic code translation is a fundamental task in modern software development. While the advent of Large Language Models (LLMs) has significantly improved the correctness of code translation, the critical dimension of execution efficiency remains overlooked. To address this gap, we introduce TRACY, the first comprehensive benchmark designed to evaluate the execution efficiency of LLM-translated code. TRACY is constructed through an LLM-driven two-stage pipeline: an initial stage generates a s…

@… @… the shirt and the sun doing all the hard work 🥰

Human Digital Twin: Data, Models, Applications, and Challenges
Rong Pan, Hongyue Sun, Xiaoyu Chen, Giulia Pedrielli, Jiapeng Huang
https://arxiv.org/abs/2508.13138 https://

Human Digital Twin: Data, Models, Applications, and Challenges
Human digital twins (HDTs) are dynamic, data-driven virtual representations of individuals, continuously updated with multimodal data to simulate, monitor, and predict health trajectories. By integrating clinical, physiological, behavioral, and environmental inputs, HDTs enable personalized diagnostics, treatment planning, and anomaly detection. This paper reviews current approaches to HDT modeling, with a focus on statistical and machine learning techniques, including recent advances in anomal…

Proposal of cavity quantum acoustodynamics platform based on Lithium Niobate-on-Sapphire chip
Xin-Biao Xu, Lintao Xiao, Bo Zhang, Weiting Wang, Jia-Qi Wang, Yu Zeng, Yuan-Hao Yang, Bao-Zhen Wang, Xiaoxuan Pan, Guang-Can Guo, Luyan Sun, Chang-Ling Zou
https://arxiv.org/abs/2509.14728

Proposal of cavity quantum acoustodynamics platform based on Lithium Niobate-on-Sapphire chip
A scalable hybrid cavity quantum acoustodynamics (QAD) platform is proposed. The architecture integrates superconducting transmon qubits with phononic integrated circuits on a single chip made by lithium niobate-on-sapphire substrate. The platform supports tightly confined and guided phononic modes in unsuspended waveguides and microring structures, while the superconducting qubits reside on the sapphire substrate. Efficient piezoelectric coupling between the phononic modes and transmon qubits …

It’s a few days early for Torontohenge, but it was still pretty sweet.

Dynamical degrees of affine-triangular automorphisms in dimension four
Enbo Shao, Xiaosong Sun
https://arxiv.org/abs/2509.14584 https://arxiv.org/pdf/2509.…

Dynamical degrees of affine-triangular automorphisms in dimension four
In this paper, let k be the affine n-space over an arbitrary field k. We show that dynamical degrees of affine-triangular automorphisms in dimension 4 are algebraic integers of degree not larger than 4. As a consequence, if char(k) is not equal to 2, then dynamical degrees of quadratic automorphisms in dimension 4 are algebraic integers of degree not larger than 4. We also explore some results in higher dimensions. These results partially give the affirmative answer to the Conjecture in DF21

An Intelligent Mobile Application to Monitor and Correct Sitting Posture Using Raspberry Pi and MediaPipe Pose Detection
Yung-Chen (Hailey), Hsieh, Yu Sun
https://arxiv.org/abs/2508.11683

An Intelligent Mobile Application to Monitor and Correct Sitting Posture Using Raspberry Pi and MediaPipe Pose Detection
Poor posture has become an increasingly prevalent concern due to students and workers spending extended amounts of time sitting at a desk. To address this issue, we developed PoseTrack, a mobile application that uses a Raspberry Pi Camera and Mediapipe Pose landmarks to monitor the userś posture and provide real time feedback. The system detects poor posture, including forward lean, slouching, hunched shoulders, crossed legs, etc. Some challenges we faced were obtaining posture data, transferr…

The Aubin Property for Generalized Equations over $C^2$-cone Reducible Sets
Jiaming Ma, Defeng Sun
https://arxiv.org/abs/2509.14194 https://arxiv.org/pdf/2…

The Aubin Property for Generalized Equations over $C^2$-cone Reducible Sets
This paper establishes the equivalence of the Aubin property and the strong regularity for generalized equations over $C^2$-cone reducible sets. This result resolves a long-standing question in variational analysis and extends the well-known equivalence theorem for polyhedral sets to a significantly broader class of non-polyhedral cases. Our proof strategy departs from traditional variational techniques, integrating insights from convex geometry with powerful tools from algebraic topology. A co…

Anatomic Feature Fusion Model for Diagnosing Calcified Pulmonary Nodules on Chest X-Ray
Hyeonjin Choi, Yang-gon Kim, Dong-yeon Yoo, Ju-sung Sun, Jung-won Lee
https://arxiv.org/abs/2508.12562

Anatomic Feature Fusion Model for Diagnosing Calcified Pulmonary Nodules on Chest X-Ray
Accurate and timely identification of pulmonary nodules on chest X-rays can differentiate between life-saving early treatment and avoidable invasive procedures. Calcification is a definitive indicator of benign nodules and is the primary foundation for diagnosis. In actual practice, diagnosing pulmonary nodule calcification on chest X-rays predominantly depends on the physician's visual assessment, resulting in significant diversity in interpretation. Furthermore, overlapping anatomical element…

Dynamic Quality-Latency Aware Routing for LLM Inference in Wireless Edge-Device Networks
Rui Bao, Nan Xue, Yaping Sun, Zhiyong Chen
https://arxiv.org/abs/2508.11291 https://

Dynamic Quality-Latency Aware Routing for LLM Inference in Wireless Edge-Device Networks
The integration of wireless communications and Large Language Models (LLMs) is poised to unlock ubiquitous intelligent services, yet deploying them in wireless edge-device collaborative environments presents a critical trade-off between inference quality and end-to-end latency. A fundamental mismatch exists between task complexity and resource allocation: offloading simple queries invites prohibitive latency, while on-device models lack the capacity for demanding computations. To address this c…

Diagnostic-Guided Dynamic Profile Optimization for LLM-based User Simulators in Sequential Recommendation
Hongyang Liu, Zhu Sun, Tianjun Wei, Yan Wang, Jiajie Zhu, Xinghua Qu
https://arxiv.org/abs/2508.12645

Diagnostic-Guided Dynamic Profile Optimization for LLM-based User Simulators in Sequential Recommendation
Recent advances in large language models (LLMs) have enabled realistic user simulators for developing and evaluating recommender systems (RSs). However, existing LLM-based simulators for RSs face two major limitations: (1) static and single-step prompt-based inference that leads to inaccurate and incomplete user profile construction; (2) unrealistic and single-round recommendation-feedback interaction pattern that fails to capture real-world scenarios. To address these limitations, we propose D…

Activity-Cycle Variations of Convection Scales in Subsurface Layers of the Sun
Alexander V. Getling, Alexander G. Kosovichev
https://arxiv.org/abs/2508.12465 https://

Activity-Cycle Variations of Convection Scales in Subsurface Layers of the Sun
We use subsurface-flow velocity maps inferred by time--distance helioseismology from Doppler measurements with the Helioseismic and Magnetic Imager (HMI) of the Solar Dynamics Observatory (SDO) to investigate variations of large-scale convection during Solar Cycles 24 and 25 in the 19-Mm-deep layer. The spatial power spectra of the horizontal-flow divergence reveal well-defined characteristic scales of solar supergranulation in the upper 4 Mm layer, while the giant-cell scale is prominent below…

Flow Matching-Based Active Learning for Radio Map Construction with Low-Altitude UAVs
Hao Sun, Shicong Liu, Xianghao Yu, Ying Sun
https://arxiv.org/abs/2509.13822 https://

Flow Matching-Based Active Learning for Radio Map Construction with Low-Altitude UAVs
The employment of unmanned aerial vehicles (UAVs) in the lowaltitude economy necessitates precise and real-time radio maps for reliable communication and safe navigation. However, constructing such maps is hindered by the infeasibility of exhaustive measurements due to UAVs' limited flight endurance. To address this, we propose a novel active learning framework for low-altitude radio map construction based on limited measurements. First, a Plug-and-Play (PnP)-refined flow matching algorithm is …

Yay, here comes #Mercury, too: it's the dot in the bright twilight strip, a bit to the right of the red light and waaay below Jupiter and Venus. Could also see it - with some effort - with the naked eye. The planet will get brighter every day now but will also move closer to the Sun.

The Times and The Sun removed stories about a "royal cleaner" who claimed to have worked for the Royal Family, published based on questionable press releases (Rob Waugh/Press Gazette)
https://pressgazette.co.uk/news/royal-

Royal cleaner stories removed by Times and Sun after authenticity questions
Stories featuring a ‘royal cleaner’ who claimed to have worked for the Royals have been withdrawn over questions about their authenticity.

Masked Diffusion Models as Energy Minimization
Sitong Chen, Shen Nie, Jiacheng Sun, Zijin Feng, Zhenguo Li, Ji-Rong Wen, Chongxuan Li
https://arxiv.org/abs/2509.13866 https://…

Masked Diffusion Models as Energy Minimization
We present a systematic theoretical framework that interprets masked diffusion models (MDMs) as solutions to energy minimization problems in discrete optimal transport. Specifically, we prove that three distinct energy formulations--kinetic, conditional kinetic, and geodesic energy--are mathematically equivalent under the structure of MDMs, and that MDMs minimize all three when the mask schedule satisfies a closed-form optimality condition. This unification not only clarifies the theoretical fo…

It's fall in Dallas. Get ready for Cowboys' annual battle with late-afternoon sun https://cowboyswire.usatoday.com/story/sports/nfl/cowboys/2025/10/15/cowboys-brian-schottenheimer-sun-debate-att-stadium/8…

Has GPT-5 Achieved Spatial Intelligence? An Empirical Study
Zhongang Cai, Yubo Wang, Qingping Sun, Ruisi Wang, Chenyang Gu, Wanqi Yin, Zhiqian Lin, Zhitao Yang, Chen Wei, Xuanke Shi, Kewang Deng, Xiaoyang Han, Zukai Chen, Jiaqi Li, Xiangyu Fan, Hanming Deng, Lewei Lu, Bo Li, Ziwei Liu, Quan Wang, Dahua Lin, Lei Yang
https://arxiv.org/abs/2…

Has GPT-5 Achieved Spatial Intelligence? An Empirical Study
Multi-modal models have achieved remarkable progress in recent years. Nevertheless, they continue to exhibit notable limitations in spatial understanding and reasoning, which are fundamental capabilities to achieving artificial general intelligence. With the recent release of GPT-5, allegedly the most powerful AI model to date, it is timely to examine where the leading models stand on the path toward spatial intelligence. First, we propose a comprehensive taxonomy of spatial tasks that unifies …

🇺🇦 #NowPlaying on KEXP's #MiddayShow
Built to Spill:
🎵 Kicked It in the Sun
#BuilttoSpill
https://jonahhall.bandcamp.com/track/kicked-it-in-the-sun-built-to-spill
https://open.spotify.com/track/6JT3dTww2LuGrtze7j5jw9

MAPF-World: Action World Model for Multi-Agent Path Finding
Zhanjiang Yang, Meng Li, Yang Shen, Yueming Li, Lijun Sun
https://arxiv.org/abs/2508.12087 https://

MAPF-World: Action World Model for Multi-Agent Path Finding
Multi-agent path finding (MAPF) is the problem of planning conflict-free paths from the designated start locations to goal positions for multiple agents. It underlies a variety of real-world tasks, including multi-robot coordination, robot-assisted logistics, and social navigation. Recent decentralized learnable solvers have shown great promise for large-scale MAPF, especially when leveraging foundation models and large datasets. However, these agents are reactive policy models and exhibit limi…

Novel Parasitic Dual-Scale Modeling for Efficient and Accurate Multilingual Speech Translation
Chenyang Le, Yinfeng Xia, Huiyan Li, Manhong Wang, Yutao Sun, Xingyang Ma, Yanmin Qian
https://arxiv.org/abs/2508.11189

Novel Parasitic Dual-Scale Modeling for Efficient and Accurate Multilingual Speech Translation
Recent advancements in speech-to-text translation have led to the development of multilingual models capable of handling multiple language pairs simultaneously. However, these unified models often suffer from large parameter sizes, making it challenging to balance inference efficiency and performance, particularly in local deployment scenarios. We propose an innovative Parasitic Dual-Scale Approach, which combines an enhanced speculative sampling method with model compression and knowledge dist…

Zeeman Doppler Imaging of $\tau$Ceti: The Weakest Magnetic Field Detected in a Sun-like Star
Federica Chiti, Oleg Kochukhov, Jennifer L. van Saders, Travis S. Metcalfe
https://arxiv.org/abs/2509.12310 …

Zeeman Doppler Imaging of $τ$Ceti: The Weakest Magnetic Field Detected in a Sun-like Star
For nearly a decade, observations have shown that many older Sun-like stars spin faster than predicted, a phenomenon known as weakened magnetic braking (WMB). The leading hypothesis for WMB is a weakening of the large-scale dipole field, which leads to a less efficient angular momentum loss. To test this hypothesis on a star known to be in the WMB regime, we present the first Zeeman Doppler Imaging (ZDI) map of the Sun-like star $τ$Ceti, reconstructed using spectropolarimetric data from the Ca…

An at first pretty uneventful #Bochum, Germany, #sunset today - but with a funny "finale": the first picture is a wider view with a bit of green, followed by three super-close-ups covering the last 3 seconds of the Sun disappearing behind the horizon in very turbulent air. With a laterally separated #GreenSegment at the very end!

Fully Spiking Actor-Critic Neural Network for Robotic Manipulation
Liwen Zhang, Heng Deng, Guanghui Sun
https://arxiv.org/abs/2508.12038 https://arxiv.org/…

Fully Spiking Actor-Critic Neural Network for Robotic Manipulation
This study proposes a hybrid curriculum reinforcement learning (CRL) framework based on a fully spiking neural network (SNN) for 9-degree-of-freedom robotic arms performing target reaching and grasping tasks. To reduce network complexity and inference latency, the SNN architecture is simplified to include only an input and an output layer, which shows strong potential for resource-constrained environments. Building on the advantages of SNNs-high inference speed, low energy consumption, and spik…

Efficient and Verifiable Privacy-Preserving Convolutional Computation for CNN Inference with Untrusted Clouds
Jinyu Lu, Xinrong Sun, Yunting Tao, Tong Ji, Fanyu Kong, Guoqiang Yang
https://arxiv.org/abs/2508.12832

Efficient and Verifiable Privacy-Preserving Convolutional Computation for CNN Inference with Untrusted Clouds
The widespread adoption of convolutional neural networks (CNNs) in resource-constrained scenarios has driven the development of Machine Learning as a Service (MLaaS) system. However, this approach is susceptible to privacy leakage, as the data sent from the client to the untrusted cloud server often contains sensitive information. Existing CNN privacy-preserving schemes, while effective in ensuring data confidentiality through homomorphic encryption and secret sharing, face efficiency bottlenec…

Towards Robust Agentic CUDA Kernel Benchmarking, Verification, and Optimization
Robert Tjarko Lange, Qi Sun, Aaditya Prasad, Maxence Faldor, Yujin Tang, David Ha
https://arxiv.org/abs/2509.14279

Towards Robust Agentic CUDA Kernel Benchmarking, Verification, and Optimization
Recent advances in large language models (LLMs) demonstrate their effectiveness in scaling test-time compute for software engineering tasks. However, these approaches often focus on high-level solutions, with limited attention to optimizing low-level CUDA kernel implementations. Additionally, existing kernel generation benchmarks suffer from exploitable loopholes and insufficient diversity in testing conditions, hindering true generalization assessment. To address these limitations, we introduc…

Ashes or Breath: Exploring Moral Dilemmas of Life and Cultural Legacy through Mixed Reality Gaming
Black Sun, Ge Kacy Fu, Shichao Guo
https://arxiv.org/abs/2508.13074 https://…

Ashes or Breath: Exploring Moral Dilemmas of Life and Cultural Legacy through Mixed Reality Gaming
Traditional approaches to teaching moral dilemmas often rely on abstract, disembodied scenarios that limit emotional engagement and reflective depth. To address this gap, we developed \textit{Ashes or Breath}, a Mixed Reality game delivered via head-mounted displays(MR-HMDs). This places players in an ethical crisis: they must save a living cat or a priceless cultural artifact during a museum fire. Designed through an iterative, values-centered process, the experience leverages embodied interac…

From Pixels to Urban Policy-Intelligence: Recovering Legacy Effects of Redlining with a Multimodal LLM
Anthony Howell, Nancy Wu, Sharmistha Bagchi, Yushim Kim, Chayn Sun
https://arxiv.org/abs/2509.15132

From Pixels to Urban Policy-Intelligence: Recovering Legacy Effects of Redlining with a Multimodal LLM
This paper shows how a multimodal large language model (MLLM) can expand urban measurement capacity and support tracking of place-based policy interventions. Using a structured, reason-then-estimate pipeline on street-view imagery, GPT-4o infers neighborhood poverty and tree canopy, which we embed in a quasi-experimental design evaluating the legacy of 1930s redlining. GPT-4o recovers the expected adverse socio-environmental legacy effects of redlining, with estimates statistically indistinguis…

The New York Sun is reviving its print product for the first time since 2008, with weekly editions published in a Berliner format on Fridays (Sara Fischer/Axios)
https://www.axios.com/2025/10/14/new-york-sun-print-edition

Exclusive: The New York Sun revives print edition
Newspapers have rarely revived print editions in an era of declining circulation.

Resource Allocation for Mutualistic Symbiotic Radio with Hybrid Active-Passive Communications
Hong Guo, Yinghui Ye, Haijian Sun, Liqin Shi, Rose Qingyang Hu
https://arxiv.org/abs/2509.14567

Resource Allocation for Mutualistic Symbiotic Radio with Hybrid Active-Passive Communications
Mutualistic SR is a communication paradigm that offers high spectrum efficiency and low power consumption, where the SU transmits information by modulating and backscattering the PT's signal, enabling shared use of spectrum and power with PT. In return, the PT's performance can be enhanced by SU's backscattered signal, forming a mutualistic relationship. However, the low modulation rate causes extremely inferior transmission rates for SUs. To improve the SU transmission rate, this paper propose…

Representation Quantization for Collaborative Filtering Augmentation
Yunze Luo, Yinjie Jiang, Gaode Chen, Jingchi Wang, Shicheng Wang, Ruina Sun, Jiang Yuezihan, Jun Zhang, Jian Liang, Han Li, Kun Gai, Kaigui Bian
https://arxiv.org/abs/2508.11194

Representation Quantization for Collaborative Filtering Augmentation
As the core algorithm in recommendation systems, collaborative filtering (CF) algorithms inevitably face the problem of data sparsity. Since CF captures similar users and items for recommendations, it is effective to augment the lacking user-user and item-item homogeneous linkages. However, existing methods are typically limited to connecting through overlapping interacted neighbors or through similar attributes and contents. These approaches are constrained by coarse-grained, sparse attributes…

A Computational Pipeline for Patient-Specific Modeling of Thoracic Aortic Aneurysm: From Medical Image to Finite Element Analysis
Jiasong Chen, Linchen Qian, Ruonan Gong, Christina Sun, Tongran Qin, Thuy Pham, Caitlin Martin, Mohammad Zafar, John Elefteriades, Wei Sun, Liang Liang
https://arxiv.org/abs/2509.12596

A Computational Pipeline for Patient-Specific Modeling of Thoracic Aortic Aneurysm: From Medical Image to Finite Element Analysis
The aorta is the body's largest arterial vessel, serving as the primary pathway for oxygenated blood within the systemic circulation. Aortic aneurysms consistently rank among the top twenty causes of mortality in the United States. Thoracic aortic aneurysm (TAA) arises from abnormal dilation of the thoracic aorta and remains a clinically significant disease, ranking as one of the leading causes of death in adults. A thoracic aortic aneurysm ruptures when the integrity of all aortic wall layers …

NeMo: A Neuron-Level Modularizing-While-Training Approach for Decomposing DNN Models
Xiaohan Bi, Binhang Qi, Hailong Sun, Xiang Gao, Yue Yu, Xiaojun Liang
https://arxiv.org/abs/2508.11348

NeMo: A Neuron-Level Modularizing-While-Training Approach for Decomposing DNN Models
With the growing incorporation of deep neural network (DNN) models into modern software systems, the prohibitive construction costs have become a significant challenge. Model reuse has been widely applied to reduce training costs, but indiscriminately reusing entire models may incur significant inference overhead. Consequently, DNN modularization has gained attention, enabling module reuse by decomposing DNN models. The emerging modularizing-while-training (MwT) paradigm, which incorporates mod…

Brain-HGCN: A Hyperbolic Graph Convolutional Network for Brain Functional Network Analysis
Junhao Jia, Yunyou Liu, Cheng Yang, Yifei Sun, Feiwei Qin, Changmiao Wang, Yong Peng
https://arxiv.org/abs/2509.14965

Brain-HGCN: A Hyperbolic Graph Convolutional Network for Brain Functional Network Analysis
Functional magnetic resonance imaging (fMRI) provides a powerful non-invasive window into the brain's functional organization by generating complex functional networks, typically modeled as graphs. These brain networks exhibit a hierarchical topology that is crucial for cognitive processing. However, due to inherent spatial constraints, standard Euclidean GNNs struggle to represent these hierarchical structures without high distortion, limiting their clinical performance. To address this limita…

The Maximum Coverage Model and Recommendation System for UAV Vertiports Location Planning
Chunliang Hua, Xiao Hu, Jiayang Sun, Zeyuan Yang
https://arxiv.org/abs/2508.12651 https…

The Maximum Coverage Model and Recommendation System for UAV Vertiports Location Planning
As urban aerial mobility (UAM) infrastructure development accelerates globally, cities like Shenzhen are planning large-scale vertiport networks (e.g., 1,200+ facilities by 2026). Existing planning frameworks remain inadequate for this complexity due to historical limitations in data granularity and real-world applicability. This paper addresses these gaps by first proposing the Capacitated Dynamic Maximum Covering Location Problem (CDMCLP), a novel optimization framework that simultaneously mo…

Empathy-R1: A Chain-of-Empathy and Reinforcement Learning Framework for Long-Form Mental Health Support
Xianrong Yao, Dong She, Chenxu Zhang, Yimeng Zhang, Yueru Sun, Noman Ahmed, Yang Gao, Zhanpeng Jin
https://arxiv.org/abs/2509.14851

Empathy-R1: A Chain-of-Empathy and Reinforcement Learning Framework for Long-Form Mental Health Support
Empathy is critical for effective mental health support, especially when addressing Long Counseling Texts (LCTs). However, existing Large Language Models (LLMs) often generate replies that are semantically fluent but lack the structured reasoning necessary for genuine psychological support, particularly in a Chinese context. To bridge this gap, we introduce Empathy-R1, a novel framework that integrates a Chain-of-Empathy (CoE) reasoning process with Reinforcement Learning (RL) to enhance respon…

GeoAware-VLA: Implicit Geometry Aware Vision-Language-Action Model
Ali Abouzeid, Malak Mansour, Zezhou Sun, Dezhen Song
https://arxiv.org/abs/2509.14117 https://

GeoAware-VLA: Implicit Geometry Aware Vision-Language-Action Model
Vision-Language-Action (VLA) models often fail to generalize to novel camera viewpoints, a limitation stemming from their difficulty in inferring robust 3D geometry from 2D images. We introduce GeoAware-VLA, a simple yet effective approach that enhances viewpoint invariance by integrating strong geometric priors into the vision backbone. Instead of training a visual encoder or relying on explicit 3D data, we leverage a frozen, pretrained geometric vision model as a feature extractor. A trainabl…

Crypto investor Justin Sun files a lawsuit against Bloomberg, seeking to block the media company from publishing a detailed breakdown of his crypto holdings (Vivian Nguyen/Crypto Briefing)
https://cryptobriefing.com/justin-sun-lawsuit-bloomberg-crypto/

Justin Sun sues Bloomberg over plan to publish confidential crypto holdings
Justin Sun lawsuit aims to stop Bloomberg from publishing confidential crypto holdings, alleging breach of agreement and security risks.

Cowboys' defensive progress, CeeDee Lamb's impact and ... the sun: 3 things I'm watching https://www.nytimes.com/athletic/6724747/2025/10/17/cowboys-ceedee-lamb-dak-prescott-commanders/

Variables Ordering Optimization in Boolean Characteristic Set Method Using Simulated Annealing and Machine Learning-based Time Prediction
Minzhong Luo, Yudong Sun, Yin Long
https://arxiv.org/abs/2509.14754

Variables Ordering Optimization in Boolean Characteristic Set Method Using Simulated Annealing and Machine Learning-based Time Prediction
Solving systems of Boolean equations is a fundamental task in symbolic computation and algebraic cryptanalysis, with wide-ranging applications in cryptography, coding theory, and formal verification. Among existing approaches, the Boolean Characteristic Set (BCS) method[1] has emerged as one of the most efficient algorithms for tackling such problems. However, its performance is highly sensitive to the ordering of variables, with solving times varying drastically under different orderings for f…

DuetUI: A Bidirectional Context Loop for Human-Agent Co-Generation of Task-Oriented Interfaces
Yuan Xu, Shaowen Xiang, Yizhi Song, Ruoting Sun, Xin Tong
https://arxiv.org/abs/2509.13444

DuetUI: A Bidirectional Context Loop for Human-Agent Co-Generation of Task-Oriented Interfaces
Large Language Models are reshaping task automation, yet remain limited in complex, multi-step real-world tasks that require aligning with vague user intent and enabling dynamic user override. From a formative study with 12 participants, we found that end-users actively seek to shape generative interfaces rather than relying on one-shot outputs. To address this, we introduce the human-agent co-generation paradigm, materialized in DuetUI. This LLM-empowered system unfolds alongside task progress…

The #Sun Reversed Its Decades-long Weakening Trend in 2008: https://iopscience.iop.org/article/10.3847/2041-8213/adf3a6 -> NASA Analysis Shows Sun’s Activity Ramping Up: https://www.jpl.nasa.gov/news/nasa-analysis-shows-suns-activity-ramping-up/

Bridging Past and Future: Distribution-Aware Alignment for Time Series Forecasting
Yifan Hu, Jie Yang, Tian Zhou, Peiyuan Liu, Yujin Tang, Rong Jin, Liang Sun
https://arxiv.org/abs/2509.14181

Bridging Past and Future: Distribution-Aware Alignment for Time Series Forecasting
Representation learning techniques like contrastive learning have long been explored in time series forecasting, mirroring their success in computer vision and natural language processing. Yet recent state-of-the-art (SOTA) forecasters seldom adopt these representation approaches because they have shown little performance advantage. We challenge this view and demonstrate that explicit representation alignment can supply critical information that bridges the distributional gap between input hist…

AIM-Bench: Evaluating Decision-making Biases of Agentic LLM as Inventory Manager
Xuhua Zhao, Yuxuan Xie, Caihua Chen, Yuxiang Sun
https://arxiv.org/abs/2508.11416 https://

AIM-Bench: Evaluating Decision-making Biases of Agentic LLM as Inventory Manager
Recent advances in mathematical reasoning and the long-term planning capabilities of large language models (LLMs) have precipitated the development of agents, which are being increasingly leveraged in business operations processes. Decision models to optimize inventory levels are one of the core elements of operations management. However, the capabilities of the LLM agent in making inventory decisions in uncertain contexts, as well as the decision-making biases (e.g. framing effect, etc.) of th…

SEDEG:Sequential Enhancement of Decoder and Encoder's Generality for Class Incremental Learning with Small Memory
Hongyang Chen, Shaoling Pu, Lingyu Zheng, Zhongwu Sun
https://arxiv.org/abs/2508.12932

SEDEG:Sequential Enhancement of Decoder and Encoder's Generality for Class Incremental Learning with Small Memory
In incremental learning, enhancing the generality of knowledge is crucial for adapting to dynamic data inputs. It can develop generalized representations or more balanced decision boundaries, preventing the degradation of long-term knowledge over time and thus mitigating catastrophic forgetting. Some emerging incremental learning methods adopt an encoder-decoder architecture and have achieved promising results. In the encoder-decoder achitecture, improving the generalization capabilities of bot…

CSGO: Generalized Optimization for Cold Start in Wireless Collaborative Edge LLM Systems
Xuran Liu, Nan Xue, Rui Bao, Yaping Sun, Zhiyong Chen, Meixia Tao, Xiaodong Xu, Shuguang Cui
https://arxiv.org/abs/2508.11287

CSGO: Generalized Optimization for Cold Start in Wireless Collaborative Edge LLM Systems
While deploying large language models on edge devices promises low-latency and privacy-preserving AI services, it is hindered by limited device resources. Although pipeline parallelism facilitates distributed inference, existing approaches often ignore the cold-start latency caused by on-demand model loading. In this paper, we propose a latency-aware scheduling framework that overlaps model loading with computation and communication to minimize total inference latency. Based on device and model…

Chicago Public Media, which owns the Sun-Times and public radio station WBEZ, names Kimbriell Kelly as EIC effective September 2, succeeding Jennifer Kho (David Roeder/Chicago Sun Times)
https://chicago.suntimes.com/media/2025/08/14/kimbriell-…

Kimbriell Kelly named editor-in-chief at Sun-Times, WBEZ
A Pulitzer Prize winner, Kelly has a background in investigative reporting. She will succeed Jennifer Kho, who will work on a project dealing with the future of public media.

A Stitch in Time Saves Nine: Proactive Self-Refinement for Language Models
Jinyi Han, Xinyi Wang, Haiquan Zhao, Tingyun li, Zishang Jiang, Sihang Jiang, Jiaqing Liang, Xin Lin, Weikang Zhou, Zeye Sun, Fei Yu, Yanghua Xiao
https://arxiv.org/abs/2508.12903

A Stitch in Time Saves Nine: Proactive Self-Refinement for Language Models
Recent advances in self-refinement have demonstrated significant potential for improving the outputs of large language models (LLMs) through iterative refinement. However, most existing self-refinement methods rely on a reactive process with a fixed number of iterations, making it difficult to determine the optimal timing and content of refinement based on the evolving generation context. Inspired by the way humans dynamically refine their thoughts during execution, we propose ProActive Self-Re…

StableTracker: Learning to Stably Track Target via Differentiable Simulation
Fanxing Li, Shengyang Wang, Fangyu Sun, Shuyu Wu, Dexin Zuo, Wenxian Yu, Danping Zou
https://arxiv.org/abs/2509.14147

StableTracker: Learning to Stably Track Target via Differentiable Simulation
FPV object tracking methods heavily rely on handcraft modular designs, resulting in hardware overload and cumulative error, which seriously degrades the tracking performance, especially for rapidly accelerating or decelerating targets. To address these challenges, we present \textbf{StableTracker}, a learning-based control policy that enables quadrotors to robustly follow the moving target from arbitrary perspectives. The policy is trained using backpropagation-through-time via differentiable s…

Cowboys Coach Brian Schottenheimer Downplays Effect Sun Can Have at AT

Trustworthy AI Psychotherapy: Multi-Agent LLM Workflow for Counseling and Explainable Mental Disorder Diagnosis
Mithat Can Ozgun, Jiahuan Pei, Koen Hindriks, Lucia Donatelli, Qingzhi Liu, Xin Sun, Junxiao Wang
https://arxiv.org/abs/2508.11398

Trustworthy AI Psychotherapy: Multi-Agent LLM Workflow for Counseling and Explainable Mental Disorder Diagnosis
LLM-based agents have emerged as transformative tools capable of executing complex tasks through iterative planning and action, achieving significant advancements in understanding and addressing user needs. Yet, their effectiveness remains limited in specialized domains such as mental health diagnosis, where they underperform compared to general applications. Current approaches to integrating diagnostic capabilities into LLMs rely on scarce, highly sensitive mental health datasets, which are ch…

On-Policy RL Meets Off-Policy Experts: Harmonizing Supervised Fine-Tuning and Reinforcement Learning via Dynamic Weighting
Wenhao Zhang, Yuexiang Xie, Yuchang Sun, Yanxi Chen, Guoyin Wang, Yaliang Li, Bolin Ding, Jingren Zhou
https://arxiv.org/abs/2508.11408

On-Policy RL Meets Off-Policy Experts: Harmonizing Supervised Fine-Tuning and Reinforcement Learning via Dynamic Weighting
Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL) are two prominent post-training paradigms for refining the capabilities and aligning the behavior of Large Language Models (LLMs). Existing approaches that integrate SFT and RL often face the risk of disrupting established model patterns and inducing overfitting to expert data. To address this, we present a novel investigation into the unified view of SFT and RL through an off-policy versus on-policy lens. We propose CHORD, a framewor…

ScaleCUA: Scaling Open-Source Computer Use Agents with Cross-Platform Data
Zhaoyang Liu, JingJing Xie, Zichen Ding, Zehao Li, Bowen Yang, Zhenyu Wu, Xuehui Wang, Qiushi Sun, Shi Liu, Weiyun Wang, Shenglong Ye, Qingyun Li, Zeyue Tian, Gen Luo, Xiangyu Yue, Biqing Qi, Kai Chen, Bowen Zhou, Yu Qiao, Qifeng Chen, Wenhai Wang
https://arxiv.org/…

ScaleCUA: Scaling Open-Source Computer Use Agents with Cross-Platform Data
Vision-Language Models (VLMs) have enabled computer use agents (CUAs) that operate GUIs autonomously, showing great potential, yet progress is limited by the lack of large-scale, open-source computer use data and foundation models. In this work, we introduce ScaleCUA, a step toward scaling open-source CUAs. It offers a large-scale dataset spanning 6 operating systems and 3 task domains, built via a closed-loop pipeline uniting automated agents with human experts. Trained on this scaled-up data,…

RationAnomaly: Log Anomaly Detection with Rationality via Chain-of-Thought and Reinforcement Learning
Song Xu, Yilun Liu, Minggui He, Mingchen Dai, Ziang Chen, Chunguang Zhao, Jingzhou Du, Shimin Tao, Weibin Meng, Shenglin Zhang, Yongqian Sun, Boxing Chen, Daimeng Wei
https://arxiv.org/abs/2509.14693…

RationAnomaly: Log Anomaly Detection with Rationality via Chain-of-Thought and Reinforcement Learning
Logs constitute a form of evidence signaling the operational status of software systems. Automated log anomaly detection is crucial for ensuring the reliability of modern software systems. However, existing approaches face significant limitations: traditional deep learning models lack interpretability and generalization, while methods leveraging Large Language Models are often hindered by unreliability and factual inaccuracies. To address these issues, we propose RationAnomaly, a novel framewor…

One #GreenSegment after another left the setting #Sun as seen from #Bochum, Germany, today: here are just a few samples, see https://www.facebook.com/media/set/?vanity=dan.fischer.393&set=a.10231040902980919 for the full sequence!

CoDiEmb: A Collaborative yet Distinct Framework for Unified Representation Learning in Information Retrieval and Semantic Textual Similarity
Bowen Zhang, Zixin Song, Chunquan Chen, Qian-Wen Zhang, Di Yin, Xing Sun
https://arxiv.org/abs/2508.11442

CoDiEmb: A Collaborative yet Distinct Framework for Unified Representation Learning in Information Retrieval and Semantic Textual Similarity
Learning unified text embeddings that excel across diverse downstream tasks is a central goal in representation learning, yet negative transfer remains a persistent obstacle. This challenge is particularly pronounced when jointly training a single encoder for Information Retrieval (IR) and Semantic Textual Similarity (STS), two essential but fundamentally disparate tasks for which naive co-training typically yields steep performance trade-offs. We argue that resolving this conflict requires sys…

Dual-Actor Fine-Tuning of VLA Models: A Talk-and-Tweak Human-in-the-Loop Approach
Piaopiao Jin, Qi Wang, Guokang Sun, Ziwen Cai, Pinjia He, Yangwei You
https://arxiv.org/abs/2509.13774

Dual-Actor Fine-Tuning of VLA Models: A Talk-and-Tweak Human-in-the-Loop Approach
Vision-language-action (VLA) models demonstrate strong generalization in robotic manipulation but face challenges in complex, real-world tasks. While supervised fine-tuning with demonstrations is constrained by data quality, reinforcement learning (RL) offers a promising alternative. We propose a human-in-the-loop dual-actor fine-tuning framework grounded in RL. The framework integrates a primary actor for robust multi-task performance with a refinement actor for latent-space adaptation. Beyond…

Wan-Animate: Unified Character Animation and Replacement with Holistic Replication
Gang Cheng, Xin Gao, Li Hu, Siqi Hu, Mingyang Huang, Chaonan Ji, Ju Li, Dechao Meng, Jinwei Qi, Penchong Qiao, Zhen Shen, Yafei Song, Ke Sun, Linrui Tian, Feng Wang, Guangyuan Wang, Qi Wang, Zhongjian Wang, Jiayu Xiao, Sheng Xu, Bang Zhang, Peng Zhang, Xindi Zhang, Zhe Zhang, Jingren Zhou, Lian Zhuo

Wan-Animate: Unified Character Animation and Replacement with Holistic Replication
We introduce Wan-Animate, a unified framework for character animation and replacement. Given a character image and a reference video, Wan-Animate can animate the character by precisely replicating the expressions and movements of the character in the video to generate high-fidelity character videos. Alternatively, it can integrate the animated character into the reference video to replace the original character, replicating the scene's lighting and color tone to achieve seamless environmental i…

A Universal Banach--Bregman Framework for Stochastic Iterations: Unifying Stochastic Mirror Descent, Learning and LLM Training
Johnny R. Zhang (Independent Researcher), Xiaomei Mi (University of Manchester), Gaoyuan Du (Amazon), Qianyi Sun (Microsoft), Shiqi Wang (Meta), Jiaxuan Li (Amazon), Wenhua Zhou (Independent Researcher)
https://arx…

A Universal Banach--Bregman Framework for Stochastic Iterations: Unifying Stochastic Mirror Descent, Learning and LLM Training
Stochastic optimization powers the scalability of modern artificial intelligence, spanning machine learning, deep learning, reinforcement learning, and large language model training. Yet, existing theory remains largely confined to Hilbert spaces, relying on inner-product frameworks and orthogonality. This paradigm fails to capture non-Euclidean settings, such as mirror descent on simplices, Bregman proximal methods for sparse learning, natural gradient descent in information geometry, or Kullb…

Crosslisted article(s) found for cs.AI. https://arxiv.org/list/cs.AI/new
[6/10]:
- CRoC: Context Refactoring Contrast for Graph Anomaly Detection with Limited Supervision
Siyue Xie, Da Sun Handason Tam, Wing Cheong Lau

Crosslisted article(s) found for cs.CL. https://arxiv.org/list/cs.CL/new
[1/2]:
- Masked Diffusion Models as Energy Minimization
Sitong Chen, Shen Nie, Jiacheng Sun, Zijin Feng, Zhenguo Li, Ji-Rong Wen, Chongxuan Li

UltraHiT: A Hierarchical Transformer Architecture for Generalizable Internal Carotid Artery Robotic Ultrasonography
Teng Wang, Haojun Jiang, Yuxuan Wang, Zhenguo Sun, Xiangjie Yan, Xiang Li, Gao Huang
https://arxiv.org/abs/2509.13832

UltraHiT: A Hierarchical Transformer Architecture for Generalizable Internal Carotid Artery Robotic Ultrasonography
Carotid ultrasound is crucial for the assessment of cerebrovascular health, particularly the internal carotid artery (ICA). While previous research has explored automating carotid ultrasound, none has tackled the challenging ICA. This is primarily due to its deep location, tortuous course, and significant individual variations, which greatly increase scanning complexity. To address this, we propose a Hierarchical Transformer-based decision architecture, namely UltraHiT, that integrates high-lev…

Replaced article(s) found for cs.CV. https://arxiv.org/list/cs.CV/new
[3/7]:
- ETVA: Evaluation of Text-to-Video Alignment via Fine-grained Question Generation and Answering
Kaisi Guan, Zhengfeng Lai, Yuchong Sun, Peng Zhang, Wei Liu, Kieran Liu, Meng Cao, Ruihua Song

Crosslisted article(s) found for cs.CL. https://arxiv.org/list/cs.CL/new
[2/2]:
- Bridging Human and LLM Judgments: Understanding and Narrowing the Gap
Felipe Maia Polo, Xinhe Wang, Mikhail Yurochkin, Gongjun Xu, Moulinath Banerjee, Yuekai Sun

RoboRetriever: Single-Camera Robot Object Retrieval via Active and Interactive Perception with Dynamic Scene Graph
Hecheng Wang, Jiankun Ren, Jia Yu, Lizhe Qi, Yunquan Sun
https://arxiv.org/abs/2508.12916

RoboRetriever: Single-Camera Robot Object Retrieval via Active and Interactive Perception with Dynamic Scene Graph
Humans effortlessly retrieve objects in cluttered, partially observable environments by combining visual reasoning, active viewpoint adjustment, and physical interaction-with only a single pair of eyes. In contrast, most existing robotic systems rely on carefully positioned fixed or multi-camera setups with complete scene visibility, which limits adaptability and incurs high hardware costs. We present \textbf{RoboRetriever}, a novel framework for real-world object retrieval that operates using …

OmniD: Generalizable Robot Manipulation Policy via Image-Based BEV Representation
Jilei Mao, Jiarui Guan, Yingjuan Tang, Qirui Hu, Zhihang Li, Junjie Yu, Yongjie Mao, Yunzhe Sun, Shuang Liu, Xiaozhu Ju
https://arxiv.org/abs/2508.11898

OmniD: Generalizable Robot Manipulation Policy via Image-Based BEV Representation
The visuomotor policy can easily overfit to its training datasets, such as fixed camera positions and backgrounds. This overfitting makes the policy perform well in the in-distribution scenarios but underperform in the out-of-distribution generalization. Additionally, the existing methods also have difficulty fusing multi-view information to generate an effective 3D representation. To tackle these issues, we propose Omni-Vision Diffusion Policy (OmniD), a multi-view fusion framework that synthe…