Tootfinder

In Ukraine, the war looks incredibly different than it is portrayed by western reporters writing from their armchairs far away.
Giorgio has been on the ground in the heat of things for almost 1400 days.
He knows all the roads along the front lines, but also the tunnels that many do not even know exist.
As Trump repeats the Kremlin's plan for subjugating Ukraine, finding the truth becomes harder and harder.
Giorgio shares the receipts, and he provides a glimpse of…

ProRe: A Proactive Reward System for GUI Agents via Reasoner-Actor Collaboration
Gaole Dai, Shiqi Jiang, Ting Cao, Yuqing Yang, Yuanchun Li, Rui Tan, Mo Li, Lili Qiu
https://arxiv.org/abs/2509.21823

ProRe: A Proactive Reward System for GUI Agents via Reasoner-Actor Collaboration
Reward is critical to the evaluation and training of large language models (LLMs). However, existing rule-based or model-based reward methods struggle to generalize to GUI agents, where access to ground-truth trajectories or application databases is often unavailable, and static trajectory-based LLM-as-a-Judge approaches suffer from limited accuracy. To address these challenges, we propose ProRe, a proactive reward system that leverages a general-purpose reasoner and domain-specific evaluator a…

CapRL: Stimulating Dense Image Caption Capabilities via Reinforcement Learning
Long Xing, Xiaoyi Dong, Yuhang Zang, Yuhang Cao, Jianze Liang, Qidong Huang, Jiaqi Wang, Feng Wu, Dahua Lin
https://arxiv.org/abs/2509.22647

CapRL: Stimulating Dense Image Caption Capabilities via Reinforcement Learning
Image captioning is a fundamental task that bridges the visual and linguistic domains, playing a critical role in pre-training Large Vision-Language Models (LVLMs). Current state-of-the-art captioning models are typically trained with Supervised Fine-Tuning (SFT), a paradigm that relies on expensive, non-scalable data annotated by humans or proprietary models. This approach often leads to models that memorize specific ground-truth answers, limiting their generality and ability to generate diver…

Right after graduating in 2015, I was offered a job at the #BBC, working on scaling iPlayer. Well, continuing to scale iPlayer. It's one of my great what ifs.
It's an organisation I hugely admire, for many of the reasons that it is being attacked so viciously right now. Truth matters. Finding common ground matters. Keep the faith.

Going beyond the genocide, warcrimes of rape, torture, kidnapping, and worse, Ukrainians suffer even worse shock at Trump's "peace" plan.
Each day finds new shame and outrage at my fellow Americans.
Friend link bypasses paywall so the world can get a glimpse of the truth in Ukraine.
Thanks to Giorgio, a true hero who reports from the trenches of democracy, on the ground, in Ukraine:

CCNeXt: An Effective Self-Supervised Stereo Depth Estimation Approach
Alexandre Lopes, Roberto Souza, Helio Pedrini
https://arxiv.org/abs/2509.22627 https://

CCNeXt: An Effective Self-Supervised Stereo Depth Estimation Approach
Depth Estimation plays a crucial role in recent applications in robotics, autonomous vehicles, and augmented reality. These scenarios commonly operate under constraints imposed by computational power. Stereo image pairs offer an effective solution for depth estimation since it only needs to estimate the disparity of pixels in image pairs to determine the depth in a known rectified system. Due to the difficulty in acquiring reliable ground-truth depth data across diverse scenarios, self-supervis…

In situ ionospheric observations near lunar south pole by the Langmuir Probe on #Chandrayaan-3 lander: https://academic.oup.com/mnras/article/542/4/2647/8223395?login=false -> Chandrayaan-3's RAMBHA-LP Instrument Delivers Critical 'Ground Truth' on the Moon’s Plasma Environment: https://www.isro.gov.in/Chandrayaan3RAMBHALP_GroundTruth.html

Variance-Bounded Evaluation without Ground Truth: VB-Score
Kaihua Ding
https://arxiv.org/abs/2509.22751 https://arxiv.org/pdf/2509.22751

Variance-Bounded Evaluation without Ground Truth: VB-Score
Reliable evaluation is a central challenge in machine learning when tasks lack ground truth labels or involve ambiguity and noise. Conventional frameworks, rooted in the Cranfield paradigm and label-based metrics, fail in such cases because they cannot assess how robustly a system performs under uncertain interpretations. We introduce VB-Score, a variance-bounded evaluation framework that measures both effectiveness and robustness without requiring ground truth. Given a query or input, VB-Score…

Update from Ukraine as the latest outrageous insult and threat are proposed as an absurdist "peace" plan.
Giorgio is on the ground in Ukraine, publishing when he gets access to electricity and an internet connection.
He shares the friend link so we can all help fight the information war by sharing truth and shining a light on the darkness that masquerades as human hearts within Trump and Putin.
Please support his work, truth, and the people of Ukraine - share the …

VeriEquivBench: An Equivalence Score for Ground-Truth-Free Evaluation of Formally Verifiable Code
Lingfei Zeng, Fengdi Che, Xuhan Huang, Fei Ye, Xu Xu, Binhang Yuan, Jie Fu
https://arxiv.org/abs/2510.06296

VeriEquivBench: An Equivalence Score for Ground-Truth-Free Evaluation of Formally Verifiable Code
Formal verification is the next frontier for ensuring the correctness of code generated by Large Language Models (LLMs). While methods that co-generate code and formal specifications in formal languages, like Dafny, can, in principle, prove alignment with user intent, progress is bottlenecked by specification quality evaluation. Current benchmarks rely on matching against ground-truth specifications, a manual and expertise-intensive process that has limited existing datasets to a few hundred si…

MAGA media
is flexing its ability to
shape the debate over antifa and violent crime in American cities,
-- empowered by allies in the White House
hungry for evidence of left-wing terrorism.
The Trump administration is using clips of violent street clashes
— paired with testimony from MAGA-aligned reporters on the ground
— to falsely depict Democratic-led cities as engulfed in chaos.

MAGA media wages asymmetric warfare on antifa
MAGA-aligned journalists frame their coverage as exposing the "truth" mainstream outlets ignore.

Replaced article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[2/14]:
- Learning-based Sketches for Frequency Estimation in Data Streams without Ground Truth
Xinyu Yuan, Yan Qiao, Meng Li, Zhenchun Wei, Cuiying Feng, Zonghui Wang, Wenzhi Chen

Not in Sync: Unveiling Temporal Bias in Audio Chat Models
Jiayu Yao, Shenghua Liu, Yiwei Wang, Rundong Cheng, Lingrui Mei, Baolong Bi, Zhen Xiong, Xueqi Cheng
https://arxiv.org/abs/2510.12185

Not in Sync: Unveiling Temporal Bias in Audio Chat Models
Large Audio Language Models (LALMs) are increasingly applied to audio understanding and multimodal reasoning, yet their ability to locate when events occur remains underexplored. We present the first systematic study of temporal bias in LALMs, revealing a key limitation in their timestamp prediction. For example, when asked "At which second does the lecturer introduce the key formula?", models often predict timestamps that are consistently earlier or later than the ground truth. Through control…

Novel phase unwrapping approach based on lateral resolution
Alim Yolalmaz, Jeroen Kalkman
https://arxiv.org/abs/2510.05347 https://arxiv.org/pdf/2510.05347…

Novel phase unwrapping approach based on lateral resolution
The phase unwrapping plays a key role in obtaining a ground-truth phase of the wrapped phase. High-accurate unwrapped phases are demanded in various research fields such as optical holography, optical diffraction tomography, and magnetic resonance imaging. Unfortunately, the ground-truth phase is not accessible due to 2pi ambiguity which arises from phase jumps in the wrapped phase. In this paper, we propose a novel approach to improve the accuracy of unwrapping process. We increase the samplin…

Multi-Granularity Sequence Denoising with Weakly Supervised Signal for Sequential Recommendation
Liang Li, Zhou Yang, Xiaofei Zhu
https://arxiv.org/abs/2510.10564 https://

Multi-Granularity Sequence Denoising with Weakly Supervised Signal for Sequential Recommendation
Sequential recommendation aims to predict the next item based on user interests in historical interaction sequences. Historical interaction sequences often contain irrelevant noisy items, which significantly hinders the performance of recommendation systems. Existing research employs unsupervised methods that indirectly identify item-granularity irrelevant noise by predicting the ground truth item. Since these methods lack explicit noise labels, they are prone to misidentify users' interested i…

Scalable Offline Metrics for Autonomous Driving
Animikh Aich, Adwait Kulkarni, Eshed Ohn-Bar
https://arxiv.org/abs/2510.08571 https://arxiv.org/pdf/2510.08…

Scalable Offline Metrics for Autonomous Driving
Real-World evaluation of perception-based planning models for robotic systems, such as autonomous vehicles, can be safely and inexpensively conducted offline, i.e., by computing model prediction error over a pre-collected validation dataset with ground-truth annotations. However, extrapolating from offline model performance to online settings remains a challenge. In these settings, seemingly minor errors can compound and result in test-time infractions or collisions. This relationship is unders…

Replaced article(s) found for cs.DB. https://arxiv.org/list/cs.DB/new
[1/1]:
- Learning-based Sketches for Frequency Estimation in Data Streams without Ground Truth
Xinyu Yuan, Yan Qiao, Meng Li, Zhenchun Wei, Cuiying Feng, Zonghui Wang, Wenzhi Chen

MARS-Sep: Multimodal-Aligned Reinforced Sound Separation
Zihan Zhang, Xize Cheng, Zhennan Jiang, Dongjie Fu, Jingyuan Chen, Zhou Zhao, Tao Jin
https://arxiv.org/abs/2510.10509 h…

MARS-Sep: Multimodal-Aligned Reinforced Sound Separation
Universal sound separation faces a fundamental misalignment: models optimized for low-level signal metrics often produce semantically contaminated outputs, failing to suppress perceptually salient interference from acoustically similar sources. To bridge this gap, we introduce MARS-Sep, a reinforcement learning framework that reformulates separation as decision making. Instead of simply regressing ground-truth masks, MARS-Sep learns a factorized Beta mask policy that is optimized by a clipped t…

Artificial-Intelligence Grading Assistance for Handwritten Components of a Calculus Exam
Gerd Kortemeyer, Alexander Caspar, Daria Horica
https://arxiv.org/abs/2510.05162 https:/…

Artificial-Intelligence Grading Assistance for Handwritten Components of a Calculus Exam
We investigate whether contemporary multimodal LLMs can assist with grading open-ended calculus at scale without eroding validity. In a large first-year exam, students' handwritten work was graded by GPT-5 against the same rubric used by teaching assistants (TAs), with fractional credit permitted; TA rubric decisions served as ground truth. We calibrated a human-in-the-loop filter that combines a partial-credit threshold with an Item Response Theory (2PL) risk measure based on the deviation bet…

Giorgio reports from the trenches of democracy on the ground in Ukraine.
He risks his life to report from the front lines so that the world might learn the truth of what is happening in Ukraine.
His is a singular voice that few others dare to experience, certainly not US media, who fail to do their job as the world is overrun with evil and lies.
Giorgio shares the friend link so the truth can be more easily shared. Please support Giorgio's work, and support Ukraine in …

The Front That’s Not On Maps
Live from Ukraine 🇺🇦

Skill of Long-Range Forecasts of Ocean Wave Spectra from the Navy ESPC Version 2 System
W. E. Rogers, M. A. Janiga
https://arxiv.org/abs/2510.06484 https://

Skill of Long-Range Forecasts of Ocean Wave Spectra from the Navy ESPC Version 2 System
We report the outcome of evaluations of the skill of long-range forecasts from the ocean wave model component of the Navy's global coupled modeling system. Specifically, the model output is taken from a single member of the ensemble system, and we evaluate the skill of predicting seven model "wave height" parameters, computed from: energy in four frequency bands, energy in all bands combined, swell energy, and wind sea energy. The model is evaluated using two methods of "ground truth". The firs…

Towards Label-Free Biological Reasoning Synthetic Dataset Creation via Uncertainty Filtering
Josefa Lia Stoisser, Lawrence Phillips, Aditya Misra, Tom A. Lamb, Philip Torr, Marc Boubnovski Martell, Julien Fauqueur, Kaspar M\"artens
https://arxiv.org/abs/2510.05871

Towards Label-Free Biological Reasoning Synthetic Dataset Creation via Uncertainty Filtering
Synthetic chain-of-thought (CoT) traces are widely used to train large reasoning models (LRMs), improving generalization by providing step-level supervision. Yet most approaches require ground-truth labels to seed or filter these traces - an expensive bottleneck in domains like biology where wet-lab data are scarce. We propose a label-free alternative: uncertainty-based filtering, which uses a model's own confidence - quantified through established uncertainty metrics like self-consistency and …

E-MoFlow: Learning Egomotion and Optical Flow from Event Data via Implicit Regularization
Wenpu Li, Bangyan Liao, Yi Zhou, Qi Xu, Pian Wan, Peidong Liu
https://arxiv.org/abs/2510.12753

E-MoFlow: Learning Egomotion and Optical Flow from Event Data via Implicit Regularization
The estimation of optical flow and 6-DoF ego-motion, two fundamental tasks in 3D vision, has typically been addressed independently. For neuromorphic vision (e.g., event cameras), however, the lack of robust data association makes solving the two problems separately an ill-posed challenge, especially in the absence of supervision via ground truth. Existing works mitigate this ill-posedness by either enforcing the smoothness of the flow field via an explicit variational regularizer or leveraging…

DexMan: Learning Bimanual Dexterous Manipulation from Human and Generated Videos
Jhen Hsieh, Kuan-Hsun Tu, Kuo-Han Hung, Tsung-Wei Ke
https://arxiv.org/abs/2510.08475 https://…

DexMan: Learning Bimanual Dexterous Manipulation from Human and Generated Videos
We present DexMan, an automated framework that converts human visual demonstrations into bimanual dexterous manipulation skills for humanoid robots in simulation. Operating directly on third-person videos of humans manipulating rigid objects, DexMan eliminates the need for camera calibration, depth sensors, scanned 3D object assets, or ground-truth hand and object motion annotations. Unlike prior approaches that consider only simplified floating hands, it directly controls a humanoid robot and …

Reducing Simulation Dependence in Neutrino Telescopes with Masked Point Transformers
Felix J. Yu, Nicholas Kamp, Carlos A. Arg\"uelles
https://arxiv.org/abs/2510.01733 http…

Reducing Simulation Dependence in Neutrino Telescopes with Masked Point Transformers
Machine learning techniques in neutrino physics have traditionally relied on simulated data, which provides access to ground-truth labels. However, the accuracy of these simulations and the discrepancies between simulated and real data remain significant concerns, particularly for large-scale neutrino telescopes that operate in complex natural media. In recent years, self-supervised learning has emerged as a powerful paradigm for reducing dependence on labeled datasets. Here, we present the fir…

Multi-Marginal Flow Matching with Adversarially Learnt Interpolants
Oskar Kviman, Kirill Tamogashev, Nicola Branchini, V\'ictor Elvira, Jens Lagergren, Nikolay Malkin
https://arxiv.org/abs/2510.01159

Multi-Marginal Flow Matching with Adversarially Learnt Interpolants
Learning the dynamics of a process given sampled observations at several time points is an important but difficult task in many scientific applications. When no ground-truth trajectories are available, but one has only snapshots of data taken at discrete time steps, the problem of modelling the dynamics, and thus inferring the underlying trajectories, can be solved by multi-marginal generalisations of flow matching algorithms. This paper proposes a novel flow matching method that overcomes the …

Pseudo2Real: Task Arithmetic for Pseudo-Label Correction in Automatic Speech Recognition
Yi-Cheng Lin, Yu-Hsuan Li Liang, Hsuan Su, Tzu-Quan Lin, Shang-Tse Chen, Yun-Nung Chen, Hung-yi Lee
https://arxiv.org/abs/2510.08047

Pseudo2Real: Task Arithmetic for Pseudo-Label Correction in Automatic Speech Recognition
Robust ASR under domain shift is crucial because real-world systems encounter unseen accents and domains with limited labeled data. Although pseudo-labeling offers a practical workaround, it often introduces systematic, accent-specific errors that filtering fails to fix. We ask: How can we correct these recurring biases without target ground truth? We propose a simple parameter-space correction: in a source domain containing both real and pseudo-labeled data, two ASR models are fine-tuned from …

Can We Hide Machines in the Crowd? Quantifying Equivalence in LLM-in-the-loop Annotation Tasks
Jiaman He, Zikang Leng, Dana McKay, Damiano Spina, Johanne R. Trippas
https://arxiv.org/abs/2510.06658

Can We Hide Machines in the Crowd? Quantifying Equivalence in LLM-in-the-loop Annotation Tasks
Many evaluations of large language models (LLMs) in text annotation focus primarily on the correctness of the output, typically comparing model-generated labels to human-annotated ``ground truth'' using standard performance metrics. In contrast, our study moves beyond effectiveness alone. We aim to explore how labeling decisions -- by both humans and LLMs -- can be statistically evaluated across individuals. Rather than treating LLMs purely as annotation systems, we approach LLMs as an alternat…

Say One Thing, Do Another? Diagnosing Reasoning-Execution Gaps in VLM-Powered Mobile-Use Agents
Lingzhong Dong, Ziqi Zhou, Shuaibo Yang, Haiyue Sheng, Pengzhou Cheng, Zongru Wu, Zheng Wu, Gongshen Liu, Zhuosheng Zhang
https://arxiv.org/abs/2510.02204

Say One Thing, Do Another? Diagnosing Reasoning-Execution Gaps in VLM-Powered Mobile-Use Agents
Mobile-use agents powered by vision-language models (VLMs) have shown great potential in interpreting natural language instructions and generating corresponding actions based on mobile graphical user interface. Recent studies suggest that incorporating chain-of-thought (CoT) reasoning tends to improve the execution accuracy. However, existing evaluations emphasize execution accuracy while neglecting whether CoT reasoning aligns with ground-truth actions. This oversight fails to assess potential…

In Ukraine, the fog of war is enhanced with atmospheric fog.
It is not only the physical battles that are affected by this fog, but also the global speculation about a scene most journalists refuse to visit and report from.
Like blind men describing an elephant that lives in the next town away from them, they publish lies and rumors they can not substantiate.
Giorgio is actually on the ground in Ukraine, reporting the truth he witnesses first-hand.
The Russians would…

May the West Emerge From the Fog
Live from Ukraine 🇺🇦

Ukrainian update: Trump does not speak for Ukrainian people, and he is in fact, a conniving thief and murderous war criminal.
As the news of Ukraine is dominated by Russian spokesmen Witkoff and Kushner, it is refreshing to have a perspective not steeped in greed, cruelty, and deceit.
Giorgio reports from the trenches of democracy, on the ground in Ukraine.
He shares the friend link to bypass the paywall, and give truth a fighting chance of being discovered by those who ca…

AI-Enhanced Kinematic Modeling of Flexible Manipulators Using Multi-IMU Sensor Fusion
Amir Hossein Barjini, Jouni Mattila
https://arxiv.org/abs/2510.02975 https://

AI-Enhanced Kinematic Modeling of Flexible Manipulators Using Multi-IMU Sensor Fusion
This paper presents a novel framework for estimating the position and orientation of flexible manipulators undergoing vertical motion using multiple inertial measurement units (IMUs), optimized and calibrated with ground truth data. The flexible links are modeled as a series of rigid segments, with joint angles estimated from accelerometer and gyroscope measurements acquired by cost-effective IMUs. A complementary filter is employed to fuse the measurements, with its parameters optimized throug…

No MoCap Needed: Post-Training Motion Diffusion Models with Reinforcement Learning using Only Textual Prompts
Girolamo Macaluso, Lorenzo Mandelli, Mirko Bicchierai, Stefano Berretti, Andrew D. Bagdanov
https://arxiv.org/abs/2510.06988

No MoCap Needed: Post-Training Motion Diffusion Models with Reinforcement Learning using Only Textual Prompts
Diffusion models have recently advanced human motion generation, producing realistic and diverse animations from textual prompts. However, adapting these models to unseen actions or styles typically requires additional motion capture data and full retraining, which is costly and difficult to scale. We propose a post-training framework based on Reinforcement Learning that fine-tunes pretrained motion diffusion models using only textual prompts, without requiring any motion ground truth. Our appr…

Comparison of Unsupervised Metrics for Evaluating Judicial Decision Extraction
Ivan Leonidovich Litvak, Anton Kostin, Fedor Lashkin, Tatiana Maksiyan, Sergey Lagutin
https://arxiv.org/abs/2510.01792

Comparison of Unsupervised Metrics for Evaluating Judicial Decision Extraction
The rapid advancement of artificial intelligence in legal natural language processing demands scalable methods for evaluating text extraction from judicial decisions. This study evaluates 16 unsupervised metrics, including novel formulations, to assess the quality of extracting seven semantic blocks from 1,000 anonymized Russian judicial decisions, validated against 7,168 expert reviews on a 1--5 Likert scale. These metrics, spanning document-based, semantic, structural, pseudo-ground truth, an…

Replication and Information Extraction in a Minimal Agent-Environment Model
Sebastiano Ariosto, Jerome Garnier-Brun, Luca Saglietti, Davide Straziota
https://arxiv.org/abs/2509.23212

Replication and Information Extraction in a Minimal Agent-Environment Model
We consider an unsupervised classifying agent that evolves by enforcing self-consistency of its labels under continual exposure to a data-generating environment. Because the agent's predictions feed back into its own regularized updates, the dynamics can stabilize into self-sustaining modes of operation, which we coin functional replicators. Remarkably, such replicators can spontaneously align with the latent structure of the environment, despite never being exposed to ground-truth labels or se…

The situation in Ukraine is both horrific and inspiring.
The terror Russia has been unleashing for over 1300 days needs to be more widely understood and recognized.
US media will not do its job, they refuse to address the terror and truth that is so apparent and easily reported - if they only cared to do so.
Georgio is a journalist on the ground in Ukraine, reporting from the trenches of democracy.
He provides the receipts and gut-wrenching reports of Russian fuckery…

Wooden Windows and Steel Hearts
Live from Ukraine 🇺🇦

Self-supervised learning for phase retrieval
Victor Sechaud (Phys-ENS), Patrice Abry (Phys-ENS), Laurent Jacques (ICTEAM), Juli\'an Tachella (Phys-ENS, CNRS)
https://arxiv.org/abs/2509.26203

Self-supervised learning for phase retrieval
In recent years, deep neural networks have emerged as a solution for inverse imaging problems. These networks are generally trained using pairs of images: one degraded and the other of high quality, the latter being called 'ground truth'. However, in medical and scientific imaging, the lack of fully sampled data limits supervised learning. Recent advances have made it possible to reconstruct images from measurement data alone, eliminating the need for references. However, these methods remain l…

OTR: Synthesizing Overlay Text Dataset for Text Removal
Jan Zdenek, Wataru Shimoda, Kota Yamaguchi
https://arxiv.org/abs/2510.02787 https://arxiv.org/pdf/2…

OTR: Synthesizing Overlay Text Dataset for Text Removal
Text removal is a crucial task in computer vision with applications such as privacy preservation, image editing, and media reuse. While existing research has primarily focused on scene text removal in natural images, limitations in current datasets hinder out-of-domain generalization or accurate evaluation. In particular, widely used benchmarks such as SCUT-EnsText suffer from ground truth artifacts due to manual editing, overly simplistic text backgrounds, and evaluation metrics that do not ca…

Incentive-Aligned Multi-Source LLM Summaries
Yanchen Jiang, Zhe Feng, Aranyak Mehta
https://arxiv.org/abs/2509.25184 https://arxiv.org/pdf/2509.25184

Incentive-Aligned Multi-Source LLM Summaries
Large language models (LLMs) are increasingly used in modern search and answer systems to synthesize multiple, sometimes conflicting, texts into a single response, yet current pipelines offer weak incentives for sources to be accurate and are vulnerable to adversarial content. We introduce Truthful Text Summarization (TTS), an incentive-aligned framework that improves factual robustness without ground-truth labels. TTS (i) decomposes a draft synthesis into atomic claims, (ii) elicits each sourc…

Equivariant Splitting: Self-supervised learning from incomplete data
Victor Sechaud, J\'er\'emy Scanvic, Quentin Barth\'elemy, Patrice Abry, Juli\'an Tachella
https://arxiv.org/abs/2510.00929

Equivariant Splitting: Self-supervised learning from incomplete data
Self-supervised learning for inverse problems allows to train a reconstruction network from noise and/or incomplete data alone. These methods have the potential of enabling learning-based solutions when obtaining ground-truth references for training is expensive or even impossible. In this paper, we propose a new self-supervised learning strategy devised for the challenging setting where measurements are observed via a single incomplete observation model. We introduce a new definition of equiva…

China provides the materials and technologies Russia needs for making the drones that attack Ukrainian civilians.
Because Russia is shit, they often send drones that fail to explode, providing excellent evidence of the bits and pieces coming from China and the west.
Giorgio is on the ground in Ukraine, gathering receipts from the wreckage and reporting from the trenches of democracy.
He shares the friend link so the world can learn the truth of what their governments are do…

China’s Signature On Russian Terror
Live from Ukraine 🇺🇦

What You See is What You Ask: Evaluating Audio Descriptions
Divy Kala, Eshika Khandelwal, Makarand Tapaswi
https://arxiv.org/abs/2510.00808 https://arxiv.o…

What You See is What You Ask: Evaluating Audio Descriptions
Audio descriptions (ADs) narrate important visual details in movies, enabling Blind and Low Vision (BLV) users to understand narratives and appreciate visual details. Existing works in automatic AD generation mostly focus on few-second trimmed clips, and evaluate them by comparing against a single ground-truth reference AD. However, writing ADs is inherently subjective. Through alignment and analysis of two independent AD tracks for the same movies, we quantify the subjectivity in when and whet…

With Trump's help, Putin is breaking records for number of missels fired - beating Hitler's Nazi Germany for all of 1945.
Giorgio is a hero reporting from the trenches of democracy, on the ground in Ukraine.
He often takes selfies in front of the rubble of civilian buildings destroyed by Russia.
Look at his face and witness the terror and disgust mixed with overwhelming heartbreak and sorrow - see the face of a man who witnesses the truth of Trump's "peace&…

Pokrovsk Is Encircled. By Fake News.
Live from Ukraine 🇺🇦

VisualOverload: Probing Visual Understanding of VLMs in Really Dense Scenes
Paul Gavrikov, Wei Lin, M. Jehanzeb Mirza, Soumya Jahagirdar, Muhammad Huzaifa, Sivan Doveh, Serena Yeung-Levy, James Glass, Hilde Kuehne
https://arxiv.org/abs/2509.25339

VisualOverload: Probing Visual Understanding of VLMs in Really Dense Scenes
Is basic visual understanding really solved in state-of-the-art VLMs? We present VisualOverload, a slightly different visual question answering (VQA) benchmark comprising 2,720 question-answer pairs, with privately held ground-truth responses. Unlike prior VQA datasets that typically focus on near global image understanding, VisualOverload challenges models to perform simple, knowledge-free vision tasks in densely populated (or, overloaded) scenes. Our dataset consists of high-resolution scans …

Autoproof: Automated Segmentation Proofreading for Connectomics
Gary B Huang, William M Katz, Stuart Berg, Louis Scheffer
https://arxiv.org/abs/2509.26585 https://

Autoproof: Automated Segmentation Proofreading for Connectomics
Producing connectomes from electron microscopy (EM) images has historically required a great deal of human proofreading effort. This manual annotation cost is the current bottleneck in scaling EM connectomics, for example, in making larger connectome reconstructions feasible, or in enabling comparative connectomics where multiple related reconstructions are produced. In this work, we propose using the available ground-truth data generated by this manual annotation effort to learn a machine lear…

It is just weird and creepy how Putin lies about everything.
Thankfully there is a journalist on the ground in Ukraine who provides the receipts to verify the truth.
He shares the friend link to bypass the paywall, because he knows how important it is to get this news out.
It is important that this evidence of warcrimes is shown to the world. Please boost and share.

Encircled Reality
Live from Ukraine 🇺🇦

As Ukraine continues to bear the brunt of Russian cruelty. global disfunction, corruption, and apathy, provide the worst assault of all.
Each day is a new depth of shame and disappointment in the behavior of my fellow Americans.
Giorgio shares the receipts from the ground in Ukraine. He provides unparalleled access and perspective on the situation in Ukraine.
Friend link bypasses the paywall, please share and support Giorgio's work, and help the world learn the truth of…

BRIDGE - Building Reinforcement-Learning Depth-to-Image Data Generation Engine for Monocular Depth Estimation
Dingning Liu, Haoyu Guo, Jingyi Zhou, Tong He
https://arxiv.org/abs/2509.25077

BRIDGE - Building Reinforcement-Learning Depth-to-Image Data Generation Engine for Monocular Depth Estimation
Monocular Depth Estimation (MDE) is a foundational task for computer vision. Traditional methods are limited by data scarcity and quality, hindering their robustness. To overcome this, we propose BRIDGE, an RL-optimized depth-to-image (D2I) generation framework that synthesizes over 20M realistic and geometrically accurate RGB images, each intrinsically paired with its ground truth depth, from diverse source depth maps. Then we train our depth estimation model on this dataset, employing a hybri…