Tootfinder

Little progress made so far on Ukraine peace deal, German Chancellor says: https://benborges.xyz/2025/08/24/little-progress-made-so-far.html

OpenGVL - Benchmarking Visual Temporal Progress for Data Curation
Pawe{\l} Budzianowski, Emilia Wi\'snios, Gracjan G\'oral, Igor Kulakov, Viktor Petrenko, Krzysztof Walas
https://arxiv.org/abs/2509.17321

OpenGVL - Benchmarking Visual Temporal Progress for Data Curation
Data scarcity remains one of the most limiting factors in driving progress in robotics. However, the amount of available robotics data in the wild is growing exponentially, creating new opportunities for large-scale data utilization. Reliable temporal task completion prediction could help automatically annotate and curate this data at scale. The Generative Value Learning (GVL) approach was recently proposed, leveraging the knowledge embedded in vision-language models (VLMs) to predict task prog…

Intern-S1: A Scientific Multimodal Foundation Model
Lei Bai, Zhongrui Cai, Maosong Cao, Weihan Cao, Chiyu Chen, Haojiong Chen, Kai Chen, Pengcheng Chen, Ying Chen, Yongkang Chen, Yu Cheng, Yu Cheng, Pei Chu, Tao Chu, Erfei Cui, Ganqu Cui, Long Cui, Ziyun Cui, Nianchen Deng, Ning Ding, Nanqin Dong, Peijie Dong, Shihan Dou, Sinan Du, Haodong Duan, Caihua Fan, Ben Gao, Changjiang Gao, Jianfei Gao, Songyang Gao, Yang Gao, Zhangwei Gao, Jiaye Ge, Qiming Ge, Lixin Gu, Yuzhe Gu, Aijia Guo, Qi…

Intern-S1: A Scientific Multimodal Foundation Model
In recent years, a plethora of open-source foundation models have emerged, achieving remarkable progress in some widely attended fields, with performance being quite close to that of closed-source models. However, in high-value but more challenging scientific professional fields, either the fields still rely on expert models, or the progress of general foundation models lags significantly compared to those in popular areas, far from sufficient for transforming scientific research and leaving su…

Top AI researchers and executives in SV are working 80 to 100 hours a week, driven by intense competition, as AI's rapid progress compresses product timelines (Wall Street Journal)
https://www.wsj.com/tech/ai/ai-race-tech-w

Benchmarking Computer Science Survey Generation
Weihang Su, Anzhe Xie, Qingyao Ai, Jianming Long, Jiaxin Mao, Ziyi Ye, Yiqun Liu
https://arxiv.org/abs/2508.15658 https://…

Benchmarking Computer Science Survey Generation
Scientific survey articles play a vital role in summarizing research progress, yet their manual creation is becoming increasingly infeasible due to the rapid growth of academic literature. While large language models (LLMs) offer promising capabilities for automating this process, progress in this area is hindered by the absence of standardized benchmarks and evaluation protocols. To address this gap, we introduce SurGE (Survey Generation Evaluation), a new benchmark for evaluating scientific s…

Is This What You Call Progress? #CreativeProcess https://muz4now.com/2025/is-this-what-you-call-progress-creativeprocess/

Is This What You Call Progress? #CreativeProcess
Stan Stewart - @muz4now

#abundance g…

Work In Progress | Australia Explained
Real stories of migrants who've made Australia their home and are building careers in vital industries...
Great Australian Pods Podcast Directory: https://www.greataustralianpods.com/work-in-progress-3/

ChatGPT 5: "Unlike speculations about Neuralink Blindsight, everything about The vOICe is fully substantiated and open to independent review" https://chatgpt.com/share/68d1ae58-aee8-8004-91fb-c08a4bfc4206

ChatGPT - Neuralink Blindsight progress
A conversational AI system that listens, learns, and challenges

Purdy happy with progress: 'We'll see' for Week 3 https://www.espn.com/nfl/story/_/id/46307308/niners-purdy-happy-progress-says-see-week-3

I2VWM: Robust Watermarking for Image to Video Generation
Guanjie Wang, Zehua Ma, Han Fang, Weiming Zhang
https://arxiv.org/abs/2509.17773 https://arxiv.org…

I2VWM: Robust Watermarking for Image to Video Generation
The rapid progress of image-guided video generation (I2V) has raised concerns about its potential misuse in misinformation and fraud, underscoring the urgent need for effective digital watermarking. While existing watermarking methods demonstrate robustness within a single modality, they fail to trace source images in I2V settings. To address this gap, we introduce the concept of Robust Diffusion Distance, which measures the temporal persistence of watermark signals in generated videos. Buildin…

#Python Friday #297: Progress Bars Everywhere With Tqdm
https://pythonfriday.dev/2025/09/297-progress-bars-everywhere-with-tqdm/

#297: Progress Bars Everywhere With Tqdm - Python Friday
None

CCrepairBench: A High-Fidelity Benchmark and Reinforcement Learning Framework for C Compilation Repair
Weixuan Sun, Jucai Zhai, Dengfeng Liu, Xin Zhang, Xiaojun Wu, Qiaobo Hao, AIMgroup, Yang Fang, Jiuyang Tang
https://arxiv.org/abs/2509.15690

CCrepairBench: A High-Fidelity Benchmark and Reinforcement Learning Framework for C++ Compilation Repair
The automated repair of C++ compilation errors presents a significant challenge, the resolution of which is critical for developer productivity. Progress in this domain is constrained by two primary factors: the scarcity of large-scale, high-fidelity datasets and the limitations of conventional supervised methods, which often fail to generate semantically correct patches.This paper addresses these gaps by introducing a comprehensive framework with three core contributions. First, we present CCr…

Q&A with David Luan, head of Amazon's AGI research lab, on leaving Adept in a reverse acquihire deal, why he believes progress on AI models has slowed, and more (Alex Heath/The Verge)
https://www.theverge.com/decoder-podcast-w

Amazon is betting on agents to win the AI race
David Luan, the head of Amazon’s AGI lab, on GPT-5, agents, and the path to winning the AI race.

I made some progress modeling a NeoPixel bike light I've been working on...
#3DPrinting #bikeTooter

MoEcho: Exploiting Side-Channel Attacks to Compromise User Privacy in Mixture-of-Experts LLMs
Ruyi Ding, Tianhong Xu, Xinyi Shen, Aidong Adam Ding, Yunsi Fei
https://arxiv.org/abs/2508.15036

MoEcho: Exploiting Side-Channel Attacks to Compromise User Privacy in Mixture-of-Experts LLMs
The transformer architecture has become a cornerstone of modern AI, fueling remarkable progress across applications in natural language processing, computer vision, and multimodal learning. As these models continue to scale explosively for performance, implementation efficiency remains a critical challenge. Mixture of Experts (MoE) architectures, selectively activating specialized subnetworks (experts), offer a unique balance between model accuracy and computational cost. However, the adaptive …

Zelensky, Trump’s envoy Kellogg discuss front-line progress, US weapons deals: https://benborges.xyz/2025/09/23/zelensky-trumps-envoy-kellogg-discuss.html

LoCaL: Countering Surface Bias in Code Evaluation Metrics
Simantika Bhattacharjee Dristi, Matthew B. Dwyer
https://arxiv.org/abs/2509.15397 https://arxiv.o…

LoCaL: Countering Surface Bias in Code Evaluation Metrics
With the increasing popularity of large language models (LLMs) and LLM-based agents, reliable and effective code evaluation metrics (CEMs) have become crucial for progress across several software engineering tasks. While popular benchmarks often provide test cases to assess the correctness of generated code, crafting and executing test cases is expensive. Reference-based CEMs provide a cheaper alternative by scoring a candidate program based on its functional similarity to a reference. Although…

Robust self-testing of quantum steering assemblages via operator inequalities
Beata Zjawin
https://arxiv.org/abs/2509.15699 https://arxiv.org/pdf/2509.1569…

Robust self-testing of quantum steering assemblages via operator inequalities
Robust self-testing provides a framework for certifying quantum resources under experimental imperfections. Improving robustness bounds for quantum resources such as quantum states, steering assemblages, and measurements is a constant effort that ensures relevance in the experimental realm. Despite progress in analytic self-testing methods for quantum states and measurements, extending these techniques to device-independent certification of steering assemblages has remained an open challenge, w…

An Overview of Crystals and Double Quiver Yangians
Jiakang Bao
https://arxiv.org/abs/2509.16918 https://arxiv.org/pdf/2509.16918

An Overview of Crystals and Double Quiver Yangians
In this review, we summarize the recent progress on the crystal melting models and the quiver algebras regarding the BPS counting. We shall consider the constructions of crystals for generic quivers and discuss the so-called double quiver Yangians/algebras. This is an invited review for International Journal of Modern Physics A.

Is This What You Call Progress?
#FolkSong #ReleaseProgress

Is This What You Call Progress? #CreativeProcess
Stan Stewart - @muz4now

Computational Scaffolding of Composition, Value, and Color for Disciplined Drawing
Jiaju Ma, Chau Vu, Asya Lyubavina, Catherine Liu, Jingyi Li
https://arxiv.org/abs/2509.17268 h…

Computational Scaffolding of Composition, Value, and Color for Disciplined Drawing
One way illustrators engage in disciplined drawing - the process of drawing to improve technical skills - is through studying and replicating reference images. However, for many novice and intermediate digital artists, knowing how to approach studying a reference image can be challenging. It can also be difficult to receive immediate feedback on their works-in-progress. To help these users develop their professional vision, we propose ArtKrit, a tool that scaffolds the process of replicating a …

Sometimes in life, like in dance, stepping back isn't a mistake or setback but an essential move to create space, rhythm, and shape for the next big leap forward. full article @ https://www.brichapman.com/p/the-backward-step

The Backward Step
why progress isn't always forward, and what dance, tides, and breath can teach us about real growth

Pretty happy with the progress of Xogot on iPhone and the iOS 26 support.
Axolotl Rex even made it to the launch screen!

Virtual Consistency for Audio Editing
Matthieu Cervera, Francesco Paissan, Mirco Ravanelli, Cem Subakan
https://arxiv.org/abs/2509.17219 https://arxiv.org/…

Virtual Consistency for Audio Editing
Free-form, text-based audio editing remains a persistent challenge, despite progress in inversion-based neural methods. Current approaches rely on slow inversion procedures, limiting their practicality. We present a virtual-consistency based audio editing system that bypasses inversion by adapting the sampling process of diffusion models. Our pipeline is model-agnostic, requiring no fine-tuning or architectural changes, and achieves substantial speed-ups over recent neural editing baselines. Cr…

Raiders Get Concerning Giants Comparison Over Ashton Jeanty https://heavy.com/sports/nfl/las-vegas-raiders/concerning-giants-comparison-ashton-jeanty/?adt_ei=[email]

#Amazon has kept pushing back the date when they say they will enable CDK CLI anonymous telemetry collection. Current enable date is Oct 1, 2025.
Lots of comments suggesting it should be an opt-in, not opt-out.
https://git…

❗ NOTICE: CDK CLI will begin to collect anonymous telemetry data on or after Oct 1st, 2025 · Issue #34892 · aws/aws-cdk
Status In-Progress. Doc page on CLI Telemetry: https://docs.aws.amazon.com/cdk/v2/guide/cli-telemetry.html Last communication on 8/29/25: Hi all, I'm updating the launch date on this thread to say ...

The partial #SolarEclipse from Dunedin, New Zealand: a screencap from 18:42 UTC. Meanwhile https://www.timeanddate.com/eclipse/in/new-zealand/dunedin?iso=20250921 is simulating the eclipse's progress live. At maximum 3/4 of the disk will be covered.

Anisotropic Cosmic Ray Transport resulting from Magnetic Mirroring and Resonant Curvature Scattering
Jeremiah L\"ubke, Frederic Effenberger, Mike Wilbert, Horst Fichtner, Rainer Grauer
https://arxiv.org/abs/2509.15320

Anisotropic Cosmic Ray Transport resulting from Magnetic Mirroring and Resonant Curvature Scattering
The transport of cosmic rays through turbulent astrophysical plasmas still constitutes an open problem. Building on recent progress, we study the combined effect of magnetic mirroring and resonant curvature scattering on parallel and perpendicular transport. We conduct test particle simulations in snapshots of an anisotropic magnetohydrodynamics simulation, and record magnetic moment variation and field line curvature around pitch angle reversals. We find for strongly magnetized particles that …

New migration patterns in high planet-star mass ratio systems in disks with low viscosity
Mariana S\'anchez, Sijme-Jan Paardekooper, Nienke van der Marel, Pablo Ben\'itez-Llambay, Gijs D. Mulders
https://arxiv.org/abs/2509.15719

New migration patterns in high planet-star mass ratio systems in disks with low viscosity
Migration of giant planets remains a complex topic. While significant progress has been made for high-viscosity disks, the migration of planets with large planet-star mass ratios in low-viscosity environments is still not fully understood. We study the migration of such planets in disks with $α= 10^{-4}$ and derive analytical prescriptions applicable across stellar masses, from Sun-like stars to M dwarfs. Using hydrodynamical simulations with FARGO3D, we explored planets with mass ratios $10^{…

Cosmic inventory of the background fields of relativistic particles in the Universe
Jonathan Biteau
https://arxiv.org/abs/2509.17954 https://arxiv.org/pdf/…

Cosmic inventory of the background fields of relativistic particles in the Universe
The extragalactic background is composed of the emission from all astrophysical sources, both resolved and unresolved, in addition to any diffuse components. In the last decade, there has been significant progress in our understanding of the cosmic history of extragalactic emissions associated with stellar evolution and accretion onto supermassive black holes, largely enabled by the extensive body of multi-wavelength data. The brightness of the extragalactic sky is now measured in photons, neut…

The latest poll from Data for Progress
found that nearly six in 10 American voters would blame the GOP or Trump for a government shutdown,
-- not Democrats
One expert told Newsweek that the poll's findings aren't "terribly surprising."
Congress is facing an end-of-the-month deadline to pass a budget bill to fund the federal government or face a shutdown.
The impacts of a shutdown are myriad
—hundreds of thousands of federal workers may be …

Republicans Get Warning About Government Shutdown in New Poll
A new poll shed light on whether voters would blame Democrats or Republicans for a government shutdown.

Competing Supramolecular Structures: Dielectric and Rheological Spectroscopy on Glycerol/Propanol Mixtures
Jan Philipp Gabriel
https://arxiv.org/abs/2509.15341 https://

Competing Supramolecular Structures: Dielectric and Rheological Spectroscopy on Glycerol/Propanol Mixtures
Significant progress has been made in recent years in understanding the dynamics of pure hydrogen-bonded systems by analyzing the spectral shape of various susceptibilities. Monohydroxy- and polyalcohols are currently considered to form transient supramolecular hydrogen-bonded structures in the form of chains, rings, and networks. This complex dynamic behavior has been identified in network-forming glycerol and chain-forming propanol by combining dielectric and light-scattering spectra. We appl…

WiFiSim: Simulating WiFi Probe Requests via AOSP Analysis and Device Behavior Modeling
Lifei Hao, Yue Cheng, Min Wang, Bing Jia, Baoqi Huang
https://arxiv.org/abs/2509.15501 htt…

WiFiSim: Simulating WiFi Probe Requests via AOSP Analysis and Device Behavior Modeling
WiFi probe request (PR) frames encode fine-grained device interactions and serve as a critical basis for mobility and crowd analytics. However, pervasive MAC address randomization and the scarcity of labeled datasets hinder progress in PR-based studies. We introduce WiFiSim, a simulation framework that reconstructs PR generation through Android Open Source Project (AOSP) protocol analysis and finite-state device behavior modeling. WiFiSim identifies the key determinants of PR structure and timi…

From Near-Integrable to Far-from-Integrable: A Unified Picture of Thermalization and Heat Transport
Weicheng Fu, Zhen Wang, Yisen Wang, Yong Zhang, Hong Zhao
https://arxiv.org/abs/2508.15566

From Near-Integrable to Far-from-Integrable: A Unified Picture of Thermalization and Heat Transport
Whether and how a system approaches equilibrium is central in nonequilibrium statistical physics, crucial to understanding thermalization and transport. Bogoliubov's three-stage (initial, kinetic, and hydrodynamic) evolution hypothesis offers a qualitative framework, but quantitative progress has focused on near-integrable systems like dilute gases. In this work, we investigate the relaxation dynamics of a one-dimensional diatomic hard-point (DHP) gas, presenting a phase diagram that characteri…

Overview of complex organic molecule observations in protostellar systems
P. Nazari
https://arxiv.org/abs/2508.15771 https://arxiv.org/pdf/2508.15771

Overview of complex organic molecule observations in protostellar systems
Complex organic molecules (COMs) have been detected abundantly at various stages of star formation, particularly in the warm protostellar phase. The progress in gas-phase measurements has been accelerated by the advent of the Atacama Large Millimeter/submillimeter Array and in ice measurements by the James Webb Space Telescope. Particularly, the community has moved from single-source studies of COMs to statistical analyses because of these powerful instruments. In this article, I review surveys…

Investigation of hadronic cross sections of cosmic ray carbon and oxygen on BGO from 200 GeV to 10 TeV energy at the DAMPE experiment
F. Alemanno, Q. An, P. Azzarello, F. C. T. Barbato, P. Bernardini, X. J. Bi, H. Boutin, I. Cagnoli, M. S. Cai, E. Casilli, E. Catanzani, J. Chang, D. Y. Chen, J. L. Chen, Z. F. Chen, Z. X. Chen, P. Coppin, M. Y. Cui, T. S. Cui, Y. X. Cui, I. De Mitri, F. de Palma, A. Di Giovanni, T. K. Dong, Z. X. Dong, G. Donvito, J. L. Duan, K. K. Duan, R. R. Fan, Y. Z…

Investigation of hadronic cross sections of cosmic ray carbon and oxygen on BGO from 200 GeV to 10 TeV energy at the DAMPE experiment
The Dark Matter Particle Explorer (DAMPE) has made significant progress in measuring the fluxes of cosmic rays. These new measurements are pivotal in advancing our understanding of the origins and propagation mechanisms of cosmic rays. The bismuth germanium oxide (BGO) calorimeter plays a crucial role in these measurements, particularly in the precise determination of cosmic ray fluxes. However, for a calorimetric experiment like DAMPE, uncertainties in hadronic models persist as a major barrie…

AI-based Methods for Simulating, Sampling, and Predicting Protein Ensembles
Bowen Jing, Bonnie Berger, Tommi Jaakkola
https://arxiv.org/abs/2509.17224 https://

AI-based Methods for Simulating, Sampling, and Predicting Protein Ensembles
Advances in deep learning have opened an era of abundant and accurate predicted protein structures; however, similar progress in protein ensembles has remained elusive. This review highlights several recent research directions towards AI-based predictions of protein ensembles, including coarse-grained force fields, generative models, multiple sequence alignment perturbation methods, and modeling of ensemble descriptors. An emphasis is placed on realistic assessments of the technological maturit…

A Comprehensive Review of Agricultural Parcel and Boundary Delineation from Remote Sensing Images: Recent Progress and Future Perspectives
Juepeng Zheng, Zi Ye, Yibin Wen, Jianxi Huang, Zhiwei Zhang, Qingmei Li, Qiong Hu, Baodong Xu, Lingyuan Zhao, Haohuan Fu
https://arxiv.org/abs/2508.14558

A Comprehensive Review of Agricultural Parcel and Boundary Delineation from Remote Sensing Images: Recent Progress and Future Perspectives
Powered by advances in multiple remote sensing sensors, the production of high spatial resolution images provides great potential to achieve cost-efficient and high-accuracy agricultural inventory and analysis in an automated way. Lots of studies that aim at providing an inventory of the level of each agricultural parcel have generated many methods for Agricultural Parcel and Boundary Delineation (APBD). This review covers APBD methods for detecting and delineating agricultural parcels and syst…

Monolithic Expandable-FOV Metalens Enabled by Radially Gradient-Tilted Meta-Atoms
Feiyang Zhang, Guoxia Han, Yihan Tian, Yanbin Ma, Xianghua Yu, Xiaolong Liu
https://arxiv.org/abs/2509.17524

Monolithic Expandable-FOV Metalens Enabled by Radially Gradient-Tilted Meta-Atoms
Metalens, as the most promising and applicable emerging optical device, has long been constrained by the limited field of view (FOV). Recent studies employing phase engineering or multi-layer strategies have made some progress, but they all rely on upright meta-atoms. This leads us to consider whether tilted meta-atoms could represent a promising yet underexplored approach for enhancing the field of view? In this work, we introduce the control of the tilt angle of meta-atoms as a new degree of …

Enhancing Generative Auto-bidding with Offline Reward Evaluation and Policy Search
Zhiyu Mou, Yiqin Lv, Miao Xu, Cheems Wang, Yixiu Mao, Qichen Ye, Chao Li, Rongquan Bai, Chuan Yu, Jian Xu, Bo Zheng
https://arxiv.org/abs/2509.15927

Enhancing Generative Auto-bidding with Offline Reward Evaluation and Policy Search
Auto-bidding is an essential tool for advertisers to enhance their advertising performance. Recent progress has shown that AI-Generated Bidding (AIGB), which formulates the auto-bidding as a trajectory generation task and trains a conditional diffusion-based planner on offline data, achieves superior and stable performance compared to typical offline reinforcement learning (RL)-based auto-bidding methods. However, existing AIGB methods still encounter a performance bottleneck due to their negle…

This is way funnier than it has any right to be.
https://bsky.app/profile/thebasement.nz/post/3liuqrev75s2c

Multi-Physics: A Comprehensive Benchmark for Multimodal LLMs Reasoning on Chinese Multi-Subject Physics Problems
Zhongze Luo, Zhenshuai Yin, Yongxin Guo, Zhichao Wang, Jionghao Zhu, Xiaoying Tang
https://arxiv.org/abs/2509.15839

Multi-Physics: A Comprehensive Benchmark for Multimodal LLMs Reasoning on Chinese Multi-Subject Physics Problems
While multimodal LLMs (MLLMs) demonstrate remarkable reasoning progress, their application in specialized scientific domains like physics reveals significant gaps in current evaluation benchmarks. Specifically, existing benchmarks often lack fine-grained subject coverage, neglect the step-by-step reasoning process, and are predominantly English-centric, failing to systematically evaluate the role of visual information. Therefore, we introduce \textbf {Multi-Physics} for Chinese physics reasonin…

8yo curriculum this year includes office 365 and keeping reading progress in spreadsheets.
Cruel and unusual punishment.

To Zip Through the Cost Analysis of Probabilistic Programs
Matthias Hetzenberger, Georg Moser, Florian Zuleger
https://arxiv.org/abs/2508.14249 https://arx…

To Zip Through the Cost Analysis of Probabilistic Programs
Probabilistic programming and the formal analysis of probabilistic algorithms are active areas of research, driven by the widespread use of randomness to improve performance. While functional correctness has seen substantial progress, automated reasoning about expected runtime remains comparatively limited. In this work, we address this challenge by introducing a refinement-typed probability monad in Liquid Haskell. Our monad enables automated reasoning about expected values and costs by encodi…

Probing jet hadrochemistry in Pb--Pb collisions with ALICE
Sierra Cantway (for the ALICE Collaboration)
https://arxiv.org/abs/2508.14987 https://arxiv.org/…

Probing jet hadrochemistry in Pb--Pb collisions with ALICE
Jet substructure measurements in heavy-ion collisions provide constraints on jet quenching and the medium response in the QGP. Though there has been remarkable progress in inclusive-charged-hadron jet substructure measurements, understanding the identified particle composition of jets and their modification in heavy-ion collisions has proven challenging. Jet quenching models predict that the jet hadrochemical composition may be modified in heavy-ion collisions due to jet-medium interactions, as…

Future progress in artificial intelligence: A survey of expert opinion
Vincent C. M\"uller, Nick Bostrom
https://arxiv.org/abs/2508.11681 https://arxi…

Future progress in artificial intelligence: A survey of expert opinion
There is, in some quarters, concern about high-level machine intelligence and superintelligent AI coming up in a few decades, bringing with it significant risks for humanity. In other quarters, these issues are ignored or considered science fiction. We wanted to clarify what the distribution of opinions actually is, what probability the best experts currently assign to high-level machine intelligence coming up within a particular time-frame, which risks they see with that development, and how f…

Exploiting Policy Idling for Dexterous Manipulation
Annie S. Chen, Philemon Brakel, Antonia Bronars, Annie Xie, Sandy Huang, Oliver Groth, Maria Bauza, Markus Wulfmeier, Nicolas Heess, Dushyant Rao
https://arxiv.org/abs/2508.15669

Exploiting Policy Idling for Dexterous Manipulation
Learning-based methods for dexterous manipulation have made notable progress in recent years. However, learned policies often still lack reliability and exhibit limited robustness to important factors of variation. One failure pattern that can be observed across many settings is that policies idle, i.e. they cease to move beyond a small region of states when they reach certain states. This policy idling is often a reflection of the training data. For instance, it can occur when the data contain…

Just finished Transiruby, along with a 9k-line journal file for it. I almost got 100, but not quite; I don't have time to go back to it before the semester starts though.
If you like exploration games, it's an excellent one, with great level design & tons of secrets. It actually makes you do significant secret-finding and map-reading in order to beat the game, not just for extras or a special ending, which is something that a lot of metroidvania games since Super Metroid don't do. My one complaint is that the map system isn't perfect, and finding obscure secrets to progress is fine when the map hints at them but much less fun when it hints incorrectly (I looked one progress item up in a speedrun video because of this).
Decently cool movement mechanics, although the combat does take a back seat and almost all of the bosses are easy (I beat the final two bosses in the third and second tries respectively). I don't think that's any better or worse than a game like Nine Sols where the final boss took me hundreds of tries though; just a different flavor. The world-building isn't as rich as the more epic metroidvanias like Hollow Knight or Lone Fungus (or again, Nine Sols) but again I'm fine with that. It's just a more casual game that has really excellent level design & exploration poetics.
#AmPlaying

Quote post work-in-progress thread.
Boost count Quote count.
#PhanpySocialDev

On the "second" Kahn--Kalai Conjecture
Quentin Dubroff, Jeff Kahn, Jinyoung Park
https://arxiv.org/abs/2508.14269 https://arxiv.org/pdf/2508.1426…

On the "second" Kahn--Kalai Conjecture
We make progress on a conjecture of Kahn and Kalai, the original (stronger but less general) version of what became known as the ``Kahn-Kalai Conjecture" (KKC; now a theorem of Park and Pham). This ``second" KKC concerns the threshold, $p_c(H)$, for $G_{n,p}$ to contain a copy of a given graph $H$, predicting $p_c(H) = O(p_{\mathbb E}(H)\log n)$, where $p_{\mathbb E}$ is an easy lower bound on $p_c$. What we actually show is $p_{\mathbb E}^*(H)=O(p_{\mathbb E}(H)\log ^2n)$, where $p_{\mathbb E}…

Jerry Jones gives 'bottom line' message on improving Cowboys defense https://www.sportingnews.com/us/nfl/dallas-cowboys/news/jerry-jones-gives-bottom-line-message-improving-cowboys-defense/1702…

Trump administration retreats on combating human trafficking and child exploitation;
Experts say decades of progress are under threat; Trump officials spew the usual BS.
https://www.theguardian.com/us-news/2025/sep/17/trump-human-trafficking-programs-…

Some programming languages manage to absorb change, but withstand progress.
-- Epigrams in Programming, ACM SIGPLAN Sept. 1982

This report was new to me 'Building a pro-worker AI innovation strategy'
'We know from experience that rapid technological advancement only delivers widespread social progress when working people are empowered.'
https://www.tuc.org.uk/research-an…

Judge blocks Trump's stop-work order on New England wind farm - a win for renewable energy progress. #climatechange #climatesolutions #climate

Judge deals Trump’s war on wind its first major setback
The temporary injunction comes amid the administration’s broader assault on renewables that threatens the electricity supply as demand skyrockets.

Fuck it, we ball

@… Do share screenshots, etc. if you’re up for it. I’d love to see your work in progress. 😄

Global Regulation and Excitation via Attention Tuning for Stereo Matching
Jiahao Li, Xinhong Chen, Zhengmin Jiang, Qian Zhou, Yung-Hui Li, Jianping Wang
https://arxiv.org/abs/2509.15891

Global Regulation and Excitation via Attention Tuning for Stereo Matching
Stereo matching achieves significant progress with iterative algorithms like RAFT-Stereo and IGEV-Stereo. However, these methods struggle in ill-posed regions with occlusions, textureless, or repetitive patterns, due to a lack of global context and geometric information for effective iterative refinement. To enable the existing iterative approaches to incorporate global context, we propose the Global Regulation and Excitation via Attention Tuning (GREAT) framework which encompasses three attent…

That moment when you have to move large amounts of data and realize that by using NFS instead of SMB to move the data, you can almost max out your physical network connection. SMB only provided around 60 MB/s...

$\mathrm{GL}_n$ large sieves and density estimates via positive semi-definiteness
Alexandru Pascadi, Jesse Thorner
https://arxiv.org/abs/2508.14888 https://

$\mathrm{GL}_n$ large sieves and density estimates via positive semi-definiteness
Let $\mathfrak{F}_n$ be the set of unitary cuspidal automorphic representations of $\mathrm{GL}_n$ over a number field $F$, and let $\mathcal{S}\subseteq\mathfrak{F}_n$ be a finite subset. Given $π_0\in\mathfrak{F}_{n_0}$, we establish large sieve inequalities for the families $\{L(s,π)\colon π\in\mathcal{S}\}$ and $\{L(s,π\timesπ_0)\colon π\in\mathcal{S}\}$ that, unlike previous results, are independent of progress towards the generalized Ramanujan conjecture and simultaneously handle th…

Compose Yourself: Average-Velocity Flow Matching for One-Step Speech Enhancement
Gang Yang, Yue Lei, Wenxin Tai, Jin Wu, Jia Chen, Ting Zhong, Fan Zhou
https://arxiv.org/abs/2509.15952

Compose Yourself: Average-Velocity Flow Matching for One-Step Speech Enhancement
Diffusion and flow matching (FM) models have achieved remarkable progress in speech enhancement (SE), yet their dependence on multi-step generation is computationally expensive and vulnerable to discretization errors. Recent advances in one-step generative modeling, particularly MeanFlow, provide a promising alternative by reformulating dynamics through average velocity fields. In this work, we present COSE, a one-step FM framework tailored for SE. To address the high training overhead of Jacob…

More than 200 lobbyists at UN’s plastic treaty talks will limit progress, campaigners warn https://www.theguardian.com/environment/2025/aug/07/more-than-200-lobbyists-at-uns-plastic-treaty-talks-will-limit…

A U-Statistic-based random forest approach for genetic interaction study
Ming Li, Ruo-Sin Peng, Changshuai Wei, Qing Lu
https://arxiv.org/abs/2508.14924 https://

A U-Statistic-based random forest approach for genetic interaction study
Variations in complex traits are influenced by multiple genetic variants, environmental risk factors, and their interactions. Though substantial progress has been made in identifying single genetic variants associated with complex traits, detecting the gene-gene and gene-environment interactions remains a great challenge. When a large number of genetic variants and environmental risk factors are involved, searching for interactions is limited to pair-wise interactions due to the exponentially i…

Raiders’ long ball connection remains a work in progress https://www.reviewjournal.com/sports/raiders/raiders-long-ball-connection-remains-a-work-in-progress-3422923/

WenetSpeech-Chuan: A Large-Scale Sichuanese Corpus with Rich Annotation for Dialectal Speech Processing
Yuhang Dai, Ziyu Zhang, Shuai Wang, Longhao Li, Zhao Guo, Tianlun Zuo, Shuiyuan Wang, Hongfei Xue, Chengyou Wang, Qing Wang, Xin Xu, Hui Bu, Jie Li, Jian Kang, Binbin Zhang, Lei Xie
https://arxiv.org/abs/2509.18004

WenetSpeech-Chuan: A Large-Scale Sichuanese Corpus with Rich Annotation for Dialectal Speech Processing
The scarcity of large-scale, open-source data for dialects severely hinders progress in speech technology, a challenge particularly acute for the widely spoken Sichuanese dialects of Chinese. To address this critical gap, we introduce WenetSpeech-Chuan, a 10,000-hour, richly annotated corpus constructed using our novel Chuan-Pipeline, a complete data processing framework for dialectal speech. To facilitate rigorous evaluation and demonstrate the corpus's effectiveness, we also release high-qual…

Making progress on this 3D printed handlebar clamp for the Beat Bike…
#diy #maker #3DPrinting

Trump-Zelensky summit was theater, not progress — Landsbergis: https://benborges.xyz/2025/08/19/trumpzelensky-summit-was-theater-not.html

Progress on "How To Rise and Keep Rising" continues. Though the songwriter/performer (Stan Stewart) wishes it would go faster.
#RecordingStudio #Songwriting

Is This What You Call Progress? #CreativeProcess
Stan Stewart - @muz4now

CoReVLA: A Dual-Stage End-to-End Autonomous Driving Framework for Long-Tail Scenarios via Collect-and-Refine
Shiyu Fang, Yiming Cui, Haoyang Liang, Chen Lv, Peng Hang, Jian Sun
https://arxiv.org/abs/2509.15968

CoReVLA: A Dual-Stage End-to-End Autonomous Driving Framework for Long-Tail Scenarios via Collect-and-Refine
Autonomous Driving (AD) systems have made notable progress, but their performance in long-tail, safety-critical scenarios remains limited. These rare cases contribute a disproportionate number of accidents. Vision-Language Action (VLA) models have strong reasoning abilities and offer a potential solution, but their effectiveness is limited by the lack of high-quality data and inefficient learning in such conditions. To address these challenges, we propose CoReVLA, a continual learning end-to-en…

Transfer learning optimization based on evolutionary selective fine tuning
Jacinto Colan, Ana Davila, Yasuhisa Hasegawa
https://arxiv.org/abs/2508.15367 https://

Transfer learning optimization based on evolutionary selective fine tuning
Deep learning has shown substantial progress in image analysis. However, the computational demands of large, fully trained models remain a consideration. Transfer learning offers a strategy for adapting pre-trained models to new tasks. Traditional fine-tuning often involves updating all model parameters, which can potentially lead to overfitting and higher computational costs. This paper introduces BioTune, an evolutionary adaptive fine-tuning technique that selectively fine-tunes layers to enh…

Unveiling Trust in Multimodal Large Language Models: Evaluation, Analysis, and Mitigation
Yichi Zhang, Yao Huang, Yifan Wang, Yitong Sun, Chang Liu, Zhe Zhao, Zhengwei Fang, Huanran Chen, Xiao Yang, Xingxing Wei, Hang Su, Yinpeng Dong, Jun Zhu
https://arxiv.org/abs/2508.15370

Unveiling Trust in Multimodal Large Language Models: Evaluation, Analysis, and Mitigation
The trustworthiness of Multimodal Large Language Models (MLLMs) remains an intense concern despite the significant progress in their capabilities. Existing evaluation and mitigation approaches often focus on narrow aspects and overlook risks introduced by the multimodality. To tackle these challenges, we propose MultiTrust-X, a comprehensive benchmark for evaluating, analyzing, and mitigating the trustworthiness issues of MLLMs. We define a three-dimensional framework, encompassing five trustwo…

49ers QB Brock Purdy happy with progress, but status remains 'day to day' https://www.nytimes.com/athletic/6642465/2025/09/18/49ers-qb-brock-purdy-mac-jones-health/

Mind and Motion Aligned: A Joint Evaluation IsaacSim Benchmark for Task Planning and Low-Level Policies in Mobile Manipulation
Nikita Kachaev, Andrei Spiridonov, Andrey Gorodetsky, Kirill Muravyev, Nikita Oskolkov, Aditya Narendra, Vlad Shakhuro, Dmitry Makarov, Aleksandr I. Panov, Polina Fedotova, Alexey K. Kovalev
https://arxiv.org/abs/2…

Mind and Motion Aligned: A Joint Evaluation IsaacSim Benchmark for Task Planning and Low-Level Policies in Mobile Manipulation
Benchmarks are crucial for evaluating progress in robotics and embodied AI. However, a significant gap exists between benchmarks designed for high-level language instruction following, which often assume perfect low-level execution, and those for low-level robot control, which rely on simple, one-step commands. This disconnect prevents a comprehensive evaluation of integrated systems where both task planning and physical execution are critical. To address this, we propose Kitchen-R, a novel ben…

Interpretable Audio Editing Evaluation via Chain-of-Thought Difference-Commonality Reasoning with Multimodal LLMs
Yuhang Jia, Xu Zhang, Yang Chen, Hui Wang, Enzhi Wang, Yong Qin
https://arxiv.org/abs/2509.16975

Interpretable Audio Editing Evaluation via Chain-of-Thought Difference-Commonality Reasoning with Multimodal LLMs
Automatic mean opinion score (MOS) prediction provides a more perceptual alternative to objective metrics, offering deeper insights into the evaluated models. With the rapid progress of multimodal large language models (MLLMs), their enhanced perceptual and reasoning abilities enable more comprehensive and interpretable audio quality assessment. In this work, we tackle the challenging task of audio editing evaluation and propose the first natural language-based automated evaluation framework bu…

CineScale: Free Lunch in High-Resolution Cinematic Visual Generation
Haonan Qiu, Ning Yu, Ziqi Huang, Paul Debevec, Ziwei Liu
https://arxiv.org/abs/2508.15774 https://

CineScale: Free Lunch in High-Resolution Cinematic Visual Generation
Visual diffusion models achieve remarkable progress, yet they are typically trained at limited resolutions due to the lack of high-resolution data and constrained computation resources, hampering their ability to generate high-fidelity images or videos at higher resolutions. Recent efforts have explored tuning-free strategies to exhibit the untapped potential higher-resolution visual generation of pre-trained models. However, these methods are still prone to producing low-quality visual content…

Raiders’ Progress Under Carroll Faces Crucial Challenge This Weekend https://www.si.com/nfl/raiders/lkas-vegas-deebo-samuel-jayden-daniels-pete-carroll-marcus-mariota

A little more progress on the Beat Bike… switch connected to controller with TRS cable.
#maker #diy #electronics

This week, the France-based ArianeGroup aerospace company announced that it had completed the integration of the
Themis vehicle,
a prototype rocket that will test various landing technologies, on a launch pad in Sweden.
Low-altitude hop tests,
a precursor for developing a rocket's first stage that can vertically land after an orbital launch,
could start late this year or early next.

After a very slow start, Europe’s reusable rocket program shows signs of life
Although Themis is making progress, the program is several years behind schedule.

DNA-DetectLLM: Unveiling AI-Generated Text via a DNA-Inspired Mutation-Repair Paradigm
Xiaowei Zhu, Yubing Ren, Fang Fang, Qingfeng Tan, Shi Wang, Yanan Cao
https://arxiv.org/abs/2509.15550

DNA-DetectLLM: Unveiling AI-Generated Text via a DNA-Inspired Mutation-Repair Paradigm
The rapid advancement of large language models (LLMs) has blurred the line between AI-generated and human-written text. This progress brings societal risks such as misinformation, authorship ambiguity, and intellectual property concerns, highlighting the urgent need for reliable AI-generated text detection methods. However, recent advances in generative language modeling have resulted in significant overlap between the feature distributions of human-written and AI-generated text, blurring class…

Thermal description of braneworld effective theories
Soham Bhattacharyya, Soumitra SenGupta
https://arxiv.org/abs/2508.14228 https://arxiv.org/pdf/2508.142…

Thermal description of braneworld effective theories
Low-energy effective theories provide the natural description of four-dimensional physics in higher-dimensional geometries, where the imprint of the bulk appears as parameters of the lower dimensional theory. Motivated by the recent progress in the first-order thermodynamic formulation of modified gravity theories, we investigate the thermodynamics of effective theories in braneworld scenarios and thereby the attractor mechanism towards general relativity in such theories. We consider the two-b…

#Python Friday #298: Fancy Progress Bars With Alive-Progress
https://pythonfriday.dev/2025/09/298-fancy-progress-bars-with-alive-progress/

#298: Fancy Progress Bars With Alive-Progress - Python Friday
None

StreamMem: Query-Agnostic KV Cache Memory for Streaming Video Understanding
Yanlai Yang, Zhuokai Zhao, Satya Narayan Shukla, Aashu Singh, Shlok Kumar Mishra, Lizhu Zhang, Mengye Ren
https://arxiv.org/abs/2508.15717

StreamMem: Query-Agnostic KV Cache Memory for Streaming Video Understanding
Multimodal large language models (MLLMs) have made significant progress in visual-language reasoning, but their ability to efficiently handle long videos remains limited. Despite recent advances in long-context MLLMs, storing and attending to the key-value (KV) cache for long visual contexts incurs substantial memory and computational overhead. Existing visual compression methods require either encoding the entire visual context before compression or having access to the questions in advance, w…

CeeDee Lamb injury update: Dallas Cowboys star makes progress at Wednesday practice https://www.sportingnews.com/us/nfl/dallas-cowboys/news/ceedee-lamb-injury-update-dallas-cowboys-progress-wednes…

EmoQ: Speech Emotion Recognition via Speech-Aware Q-Former and Large Language Model
Yiqing Yang, Man-Wai Mak
https://arxiv.org/abs/2509.15775 https://arxiv…

EmoQ: Speech Emotion Recognition via Speech-Aware Q-Former and Large Language Model
The performance of speech emotion recognition (SER) is limited by the insufficient emotion information in unimodal systems and the feature alignment difficulties in multimodal systems. Recently, multimodal large language models (MLLMs) have made progress in SER. However, MLLMs still suffer from hallucination and misclassification problems in complex emotion reasoning. To address these problems, we propose an MLLM-based framework called EmoQ, which generates query embeddings that fuse multimodal…

TMD-TTS: A Unified Tibetan Multi-Dialect Text-to-Speech Synthesis for \"U-Tsang, Amdo and Kham Speech Dataset Generation
Yutong Liu, Ziyue Zhang, Ban Ma-bao, Renzeng Duojie, Yuqing Cai, Yongbin Yu, Xiangxiang Wang, Fan Gao, Cheng Huang, Nyima Tashi
https://arxiv.org/abs/2509.18060

TMD-TTS: A Unified Tibetan Multi-Dialect Text-to-Speech Synthesis for Ü-Tsang, Amdo and Kham Speech Dataset Generation
Tibetan is a low-resource language with limited parallel speech corpora spanning its three major dialects (Ü-Tsang, Amdo, and Kham), limiting progress in speech modeling. To address this issue, we propose TMD-TTS, a unified Tibetan multi-dialect text-to-speech (TTS) framework that synthesizes parallel dialectal speech from explicit dialect labels. Our method features a dialect fusion module and a Dialect-Specialized Dynamic Routing Network (DSDR-Net) to capture fine-grained acoustic and lingui…

Raiders RB Ashton Jeanty flashes progress in joint practice with 49ers https://raiderswire.usatoday.com/story/sports/nfl/raiders/2025/08/15/raiders-rb-ashton-jeanty-flashes-progress-in-joint-pr…

GeoSVR: Taming Sparse Voxels for Geometrically Accurate Surface Reconstruction
Jiahe Li, Jiawei Zhang, Youmin Zhang, Xiao Bai, Jin Zheng, Xiaohan Yu, Lin Gu
https://arxiv.org/abs/2509.18090

GeoSVR: Taming Sparse Voxels for Geometrically Accurate Surface Reconstruction
Reconstructing accurate surfaces with radiance fields has achieved remarkable progress in recent years. However, prevailing approaches, primarily based on Gaussian Splatting, are increasingly constrained by representational bottlenecks. In this paper, we introduce GeoSVR, an explicit voxel-based framework that explores and extends the under-investigated potential of sparse voxels for achieving accurate, detailed, and complete surface reconstruction. As strengths, sparse voxels support preservin…

Anthropic's Jack Clark argues that, while he is optimistic about AI's progress, the industry must do a better job of listening to people's concerns about it (Jack Clark/Import AI)
https://importai.substack.com/p/import-ai-431-technological-optimism…

Import AI 431: Technological Optimism and Appropriate Fear
What do we do if AI progress keeps happening?

Speech-to-See: End-to-End Speech-Driven Open-Set Object Detection
Wenhuan Lu, Xinyue Song, Wenjun Ke, Zhizhi Yu, Wenhao Yang, Jianguo Wei
https://arxiv.org/abs/2509.16670 https:…

Speech-to-See: End-to-End Speech-Driven Open-Set Object Detection
Audio grounding, or speech-driven open-set object detection, aims to localize and identify objects directly from speech, enabling generalization beyond predefined categories. This task is crucial for applications like human-robot interaction where textual input is impractical. However, progress in this domain faces a fundamental bottleneck from the scarcity of large-scale, paired audio-image data, and is further constrained by previous methods that rely on indirect, text-mediated pipelines. In …

When and What: Diffusion-Grounded VideoLLM with Entity Aware Segmentation for Long Video Understanding
Pengcheng Fang, Yuxia Chen, Rui Guo
https://arxiv.org/abs/2508.15641 https…

When and What: Diffusion-Grounded VideoLLM with Entity Aware Segmentation for Long Video Understanding
Understanding videos requires more than answering open ended questions, it demands the ability to pinpoint when events occur and how entities interact across time. While recent Video LLMs have achieved remarkable progress in holistic reasoning, they remain coarse in temporal perception: timestamps are encoded only implicitly, frame level features are weak in capturing continuity, and language vision alignment often drifts from the entities of interest. In this paper, we present Grounded VideoDi…

StableGuard: Towards Unified Copyright Protection and Tamper Localization in Latent Diffusion Models
Haoxin Yang, Bangzhen Liu, Xuemiao Xu, Cheng Xu, Yuyang Yu, Zikai Huang, Yi Wang, Shengfeng He
https://arxiv.org/abs/2509.17993

StableGuard: Towards Unified Copyright Protection and Tamper Localization in Latent Diffusion Models
The advancement of diffusion models has enhanced the realism of AI-generated content but also raised concerns about misuse, necessitating robust copyright protection and tampering localization. Although recent methods have made progress toward unified solutions, their reliance on post hoc processing introduces considerable application inconvenience and compromises forensic reliability. We propose StableGuard, a novel framework that seamlessly integrates a binary watermark into the diffusion gen…

Recording Studio Changes and Progress – #recordingstudio https://muz4now.com/2025/recording-studio-changes-and-progress-recordingstudio

Recording Studio Changes and Progress - #recordingstudio
Stan Stewart - @muz4now

No More Marching: Learning Humanoid Locomotion for Short-Range SE(2) Targets
Pranay Dugar, Mohitvishnu S. Gadde, Jonah Siekmann, Yesh Godse, Aayam Shrestha, Alan Fern
https://arxiv.org/abs/2508.14098

No More Marching: Learning Humanoid Locomotion for Short-Range SE(2) Targets
Humanoids operating in real-world workspaces must frequently execute task-driven, short-range movements to SE(2) target poses. To be practical, these transitions must be fast, robust, and energy efficient. While learning-based locomotion has made significant progress, most existing methods optimize for velocity-tracking rather than direct pose reaching, resulting in inefficient, marching-style behavior when applied to short-range tasks. In this work, we develop a reinforcement learning approach…

SurveyGen-I: Consistent Scientific Survey Generation with Evolving Plans and Memory-Guided Writing
Jing Chen, Zhiheng Yang, Yixian Shen, Jie Liu, Adam Belloum, Chrysa Papagainni, Paola Grosso
https://arxiv.org/abs/2508.14317

SurveyGen-I: Consistent Scientific Survey Generation with Evolving Plans and Memory-Guided Writing
Survey papers play a critical role in scientific communication by consolidating progress across a field. Recent advances in Large Language Models (LLMs) offer a promising solution by automating key steps in the survey-generation pipeline, such as retrieval, structuring, and summarization. However, existing LLM-based approaches often struggle with maintaining coherence across long, multi-section surveys and providing comprehensive citation coverage. To address these limitations, we introduce Sur…

T-REX: Table -- Refute or Entail eXplainer
Tim Luka Horstmann, Baptiste Geisenberger, Mehwish Alam
https://arxiv.org/abs/2508.14055 https://arxiv.org/pdf/2…

T-REX: Table -- Refute or Entail eXplainer
Verifying textual claims against structured tabular data is a critical yet challenging task in Natural Language Processing with broad real-world impact. While recent advances in Large Language Models (LLMs) have enabled significant progress in table fact-checking, current solutions remain inaccessible to non-experts. We introduce T-REX (T-REX: Table -- Refute or Entail eXplainer), the first live, interactive tool for claim verification over multimodal, multilingual tables using state-of-the-art…

Virtual Community: An Open World for Humans, Robots, and Society
Qinhong Zhou, Hongxin Zhang, Xiangye Lin, Zheyuan Zhang, Yutian Chen, Wenjun Liu, Zunzhe Zhang, Sunli Chen, Lixing Fang, Qiushi Lyu, Xinyu Sun, Jincheng Yang, Zeyuan Wang, Bao Chi Dang, Zhehuan Chen, Daksha Ladia, Jiageng Liu, Chuang Gan
https://arxiv.org/abs/2508.14893

Virtual Community: An Open World for Humans, Robots, and Society
The rapid progress in AI and Robotics may lead to a profound societal transformation, as humans and robots begin to coexist within shared communities, introducing both opportunities and challenges. To explore this future, we present Virtual Community-an open-world platform for humans, robots, and society-built on a universal physics engine and grounded in real-world 3D scenes. With Virtual Community, we aim to study embodied social intelligence at scale: 1) How robots can intelligently cooperat…

Making Pose Representations More Expressive and Disentangled via Residual Vector Quantization
Sukhyun Jeong, Hong-Gi Shin, Yong-Hoon Choi
https://arxiv.org/abs/2508.14561 https:…

Making Pose Representations More Expressive and Disentangled via Residual Vector Quantization
Recent progress in text-to-motion has advanced both 3D human motion generation and text-based motion control. Controllable motion generation (CoMo), which enables intuitive control, typically relies on pose code representations, but discrete pose codes alone cannot capture fine-grained motion details, limiting expressiveness. To overcome this, we propose a method that augments pose code-based latent representations with continuous motion features using residual vector quantization (RVQ). This d…

PhysGM: Large Physical Gaussian Model for Feed-Forward 4D Synthesis
Chunji Lv, Zequn Chen, Donglin Di, Weinan Zhang, Hao Li, Wei Chen, Changsheng Li
https://arxiv.org/abs/2508.13911

PhysGM: Large Physical Gaussian Model for Feed-Forward 4D Synthesis
While physics-grounded 3D motion synthesis has seen significant progress, current methods face critical limitations. They typically rely on pre-reconstructed 3D Gaussian Splatting (3DGS) representations, while physics integration depends on either inflexible, manually defined physical attributes or unstable, optimization-heavy guidance from video models. To overcome these challenges, we introduce PhysGM, a feed-forward framework that jointly predicts a 3D Gaussian representation and its physica…

HumanPCR: Probing MLLM Capabilities in Diverse Human-Centric Scenes
Keliang Li, Hongze Shen, Hao Shi, Ruibing Hou, Hong Chang, Jie Huang, Chenghao Jia, Wen Wang, Yiling Wu, Dongmei Jiang, Shiguang Shan, Xilin Chen
https://arxiv.org/abs/2508.13692

HumanPCR: Probing MLLM Capabilities in Diverse Human-Centric Scenes
The aspiration for artificial general intelligence, fueled by the rapid progress of multimodal models, demands human-comparable performance across diverse environments. We propose HumanPCR, an evaluation suite for probing MLLMs' capacity about human-related visual contexts across three hierarchical levels: Perception, Comprehension, and Reasoning (denoted by Human-P, Human-C, and Human-R, respectively). Human-P and Human-C feature over 6,000 human-verified multiple choice questions, assessing m…