Tootfinder

🥨 Germany’s anti-diversity backlash isn’t fatigue – it’s strategy masquerading as neutrality | Fatma Aydemir
https://www.theguardian.com/commentisfree/2025/sep/30/germany-anti-diversity-backlash-trump-afd

Dear Leader has a very North Korean vibe going...
Trump Officials Demand George Mason’s President Apologize Over Diversity - The New York Times
https://www.nytimes.com/2025/08/22/us/george-mason-president-diversity-investigation.html

Similarity as Thermodynamic Work: Between Depth and Diversity -- from Information Distance to Ugly Duckling
Kentaro Imafuku
https://arxiv.org/abs/2509.16236 https://

Similarity as Thermodynamic Work: Between Depth and Diversity -- from Information Distance to Ugly Duckling
Defining similarity is a fundamental challenge in information science. Watanabe's Ugly Duckling Theorem highlights diversity, while algorithmic information theory emphasizes depth through Information Distance. We propose a statistical-mechanical framework that treats program length as energy, with a temperature parameter unifying these two aspects: in the low-temperature limit, similarity approaches Information Distance; in the high-temperature limit, it recovers the indiscriminability of the U…

DIVEBATCH: Accelerating Model Training Through Gradient-Diversity Aware Batch Size Adaptation
Yuen Chen, Yian Wang, Hari Sundaram
https://arxiv.org/abs/2509.16173 https://

DIVEBATCH: Accelerating Model Training Through Gradient-Diversity Aware Batch Size Adaptation
The goal of this paper is to accelerate the training of machine learning models, a critical challenge since the training of large-scale deep neural models can be computationally expensive. Stochastic gradient descent (SGD) and its variants are widely used to train deep neural networks. In contrast to traditional approaches that focus on tuning the learning rate, we propose a novel adaptive batch size SGD algorithm, DiveBatch, that dynamically adjusts the batch size. Adapting the batch size is c…

A method for improving multilingual quality and diversity of instruction fine-tuning datasets
Chunguang Zhao, Yilun Liu, Pufan Zeng, Yuanchang Luo, Shimin Tao, Minggui He, Weibin Meng, Song Xu, Ziang Chen, Chen Liu, Hongxia Ma, Li Zhang, Boxing Chen, Daimeng Wei
https://arxiv.org/abs/2509.15549

A method for improving multilingual quality and diversity of instruction fine-tuning datasets
Multilingual Instruction Fine-Tuning (IFT) is essential for enabling large language models (LLMs) to generalize effectively across diverse linguistic and cultural contexts. However, the scarcity of high-quality multilingual training data and corresponding building method remains a critical bottleneck. While data selection has shown promise in English settings, existing methods often fail to generalize across languages due to reliance on simplistic heuristics or language-specific assumptions. In…

See&Trek: Training-Free Spatial Prompting for Multimodal Large Language Model
Pengteng Li, Pinhao Song, Wuyang Li, Weiyu Guo, Huizai Yao, Yijie Xu, Dugang Liu, Hui Xiong
https://arxiv.org/abs/2509.16087

See&Trek: Training-Free Spatial Prompting for Multimodal Large Language Model
We introduce SEE&TREK, the first training-free prompting framework tailored to enhance the spatial understanding of Multimodal Large Language Models (MLLMS) under vision-only constraints. While prior efforts have incorporated modalities like depth or point clouds to improve spatial reasoning, purely visualspatial understanding remains underexplored. SEE&TREK addresses this gap by focusing on two core principles: increasing visual diversity and motion reconstruction. For visual diversity, we con…

Trump claimed that Joe Biden had “established toxic diversity, equity and inclusion ideology as a guiding principle of American AI development”.
“But the American people do not want woke Marxist lunacy in the AI models,” Trump said
Trump told assembled industry leaders that he wants them to “change the name” of artificial intelligence
and that they should not be forced to pay the authors of articles or books they use to train their large language models

Diversity of Structured Domains via k-Kemeny Scores
Piotr Faliszewski, Krzysztof Sornat, Stanis{\l}aw Szufa, Tomasz W\k{a}s
https://arxiv.org/abs/2509.15812 https://

Diversity of Structured Domains via k-Kemeny Scores
In the k-Kemeny problem, we are given an ordinal election, i.e., a collection of votes ranking the candidates from best to worst, and we seek the smallest number of swaps of adjacent candidates that ensure that the election has at most k different rankings. We study this problem for a number of structured domains, including the single-peaked, single-crossing, group-separable, and Euclidean ones. We obtain two kinds of results: (1) We show that k-Kemeny remains intractable under most of these do…

M&M33: MUSE and M33 I. Unveiling the Diversity of HII Regions in M33 with MUSE
A. Feltre, F. Belfiore, G. Cresci, E. Corbelli, N. Tomi\v{c}i\'c, F. Mannucci, A. Marconi, E. Bertola, C. Bracci, M. Ceci, M. Curti, Q. D'Amato, M. Ginolfi, E. Koch, I. Lamperti, L. Magrini, C. Marconcini, A. Plat, M. Scialpi, G. Tozzi, L. Ulivi, G. Venturi, M. V. Zanchettin, A. Chakraborty, A. Amiri

M&M33: MUSE and M33 I. Unveiling the Diversity of HII Regions in M33 with MUSE
We present new VLT/MUSE mosaic observations of a 3 $\times$ 8 arcmin$^2$ area along the southern major axis of the nearby galaxy M33 at a distance of 840 kpc from the Milky Way. These data provide an unprecedented view of the galaxy interstellar medium (ISM), and allow us to resolve ionised nebulae at a spatial scale of $\approx$5 pc. We identify and catalogue 124 HII regions, down to H$α$ luminosities of $\approx 5\times$10$^{35}$ erg s$^{-1}$, one order of magnitude fainter than previous sur…

A Unified and Predictive Measure of Functional Diversity
Adji Bousso Dieng, Amey Pasarkar
https://arxiv.org/abs/2509.16133 https://arxiv.org/pdf/2509.16133…

A Unified and Predictive Measure of Functional Diversity
Despite the critical role of functional diversity (FD) in understanding ecological systems and processes, its robust quantification remains a significant challenge. A long-held view in the field is that it is not possible to capture its three facets -- functional richness, functional divergence, and functional evenness -- in a single index. This perspective has prompted recent proposals for FD measurement to use three separate indices, one for each aspect. Here, we challenge this paradigm by de…

Kuramoto Mean Field Game with Intrinsic Frequencies
Rene Carmona, Quentin Cormier, Mete Soner
https://arxiv.org/abs/2509.18000 https://arxiv.org/pdf/2509.1…

Kuramoto Mean Field Game with Intrinsic Frequencies
This paper studies a mean field game formulation of the classical Kuramoto model for synchronization. Our model captures the diversity within the population by considering random intrinsic frequencies, which allows us to study the impact of this heterogeneity on synchronization patterns and stability. Our findings contribute insights into the interplay between intrinsic frequency diversity and synchronization dynamics, offering a more realistic understanding of complex systems. The proposed fra…

PuzzleClone: An SMT-Powered Framework for Synthesizing Verifiable Data
Kai Xiong, Yanwei Huang, Rongjunchen Zhang, Kun Chen, Haipang Wu
https://arxiv.org/abs/2508.15180 https://…

PuzzleClone: An SMT-Powered Framework for Synthesizing Verifiable Data
High-quality mathematical and logical datasets with verifiable answers are essential for strengthening the reasoning capabilities of large language models (LLMs). While recent data augmentation techniques have facilitated the creation of large-scale benchmarks, existing LLM-generated datasets often suffer from limited reliability, diversity, and scalability. To address these challenges, we introduce PuzzleClone, a formal framework for synthesizing verifiable data at scale using Satisfiability M…

Democratizing News Recommenders: Modeling Multiple Perspectives for News Candidate Generation with VQ-VAE
Hardy, Sebastian Pad\'o, Amelie W\"uhrl, Tanise Ceron
https://arxiv.org/abs/2508.13978

Democratizing News Recommenders: Modeling Multiple Perspectives for News Candidate Generation with VQ-VAE
Current News Recommender Systems based on past clicks are designed for engagement, but come at the cost of limiting diversity in the suggested content. While diversity-aware algorithms exist, they suffer from two major limitations. First, they fail to account for normative diversity, which requires fair access to a broad range of perspectives. Second, they typically apply diversity late in the system's pipeline, after a lot of content has already been filtered out. Both limitations confine thei…

Think Landing a Job Is Hard? Try Having 'DEI' on Your Resume (Saijel Kishan/Bloomberg)
https://www.bloomberg.com/news/features/2025-10-20/dei-jobs-vanish-as-diversity-workers-struggle-to-land-roles
http://www.memeorandum.com/251020/p104#a251020p104

Crosslisted article(s) found for quant-ph. https://arxiv.org/list/quant-ph/new
[1/2]:
- Similarity as Thermodynamic Work: Between Depth and Diversity -- from Information Distance to Ugl...
Kentaro Imafuku

MotionTrans: Human VR Data Enable Motion-Level Learning for Robotic Manipulation Policies
Chengbo Yuan, Rui Zhou, Mengzhen Liu, Yingdong Hu, Shengjie Wang, Li Yi, Chuan Wen, Shanghang Zhang, Yang Gao
https://arxiv.org/abs/2509.17759

MotionTrans: Human VR Data Enable Motion-Level Learning for Robotic Manipulation Policies
Scaling real robot data is a key bottleneck in imitation learning, leading to the use of auxiliary data for policy training. While other aspects of robotic manipulation such as image or language understanding may be learned from internet-based datasets, acquiring motion knowledge remains challenging. Human data, with its rich diversity of manipulation behaviors, offers a valuable resource for this purpose. While previous works show that using human data can bring benefits, such as improving rob…

Federal Gunmen Shoot Endangered Mexican Gray Wolf Pup, Target Second Wolf - Center for Biological Diversity
https://biologicaldiversity.org/w/news/press-releases/federal-gunmen-shoot-endangered-mexican-gray-wolf-pup-target-second-wolf-2025-08-21/

Trajectory Encryption Cooperative Salvo Guidance
Lohitvel Gopikannan, Shashi Ranjan Kumar, Abhinav Sinha
https://arxiv.org/abs/2509.17341 https://arxiv.org…

Trajectory Encryption Cooperative Salvo Guidance
This paper introduces the concept of trajectory encryption in cooperative simultaneous target interception, wherein heterogeneity in guidance principles across a team of unmanned autonomous systems is leveraged as a strategic design feature. By employing a mix of heterogeneous time-to-go formulations leading to a cooperative guidance strategy, the swarm of vehicles is able to generate diverse trajectory families. This diversity expands the feasible solution space for simultaneous target interce…

Kalman Filtering-Assisted Node Deployment for Distributed OTFS-ISAC: A Geometry-Aware Design for the Joint Sensing and Communication
Jyotsna Rani, Kuntal Deka, Ganesh Prasad, Zilong Liu
https://arxiv.org/abs/2509.16700

Kalman Filtering-Assisted Node Deployment for Distributed OTFS-ISAC: A Geometry-Aware Design for the Joint Sensing and Communication
Integrated sensing and communication (ISAC) is a key enabler for next-generation wireless networks, offering spectrum efficiency and reduced hardware complexity. While monostatic ISAC has been well studied, its limited spatial diversity reduces reliability in high-mobility scenarios. Distributed ISAC alleviates this via cooperative nodes, but conventional OFDM-based designs remain vulnerable to Doppler shifts and multipath fading. Orthogonal time frequency space (OTFS) modulation has recently e…

Diffusion-driven pattern formation in an opinion dynamical network model
Tim Mauch, Thilo Gross
https://arxiv.org/abs/2508.15377 https://arxiv.org/pdf/2508…

Diffusion-driven pattern formation in an opinion dynamical network model
The spatial organization of individuals and their interactions in communities are important factors known to preserve diversity in many complex systems. Inspired by metapopulation models from ecology, we study opinion formation using a network-based approach in which nodes represent communities of interacting agents holding one of two competing opinions, and links represent avenues of migration. Agents adapt to the dominant opinion within a community or migrate toward communities with similar v…

A rutile-based homologous series Na(PtO$_2$)$_{2\it{n} 1}$ discovered by computationally assisted high-pressure synthesis
Yasuhito Kobayashi, Hidefumi Takahashi, Shunsuke Kitou, Akitoshi Nakano, Hajime Sagayama, Yuichi Yamasaki, Shintaro Ishiwata
https://arxiv.org/abs/2508.15223

A rutile-based homologous series Na(PtO$_2$)$_{2\it{n}+1}$ discovered by computationally assisted high-pressure synthesis
Layered transition metal oxides typified by the Ruddlesden-Popper phase have been extensively studied for its applications in high-temperature superconductivity, catalysis, and battery technologies. Despite the remarkable structural diversity and catalytic functionality of platinum oxides, the exploration of layered polymorphs has remained significantly constrained mainly due to the high inertness of platinum. Here, we discover a new homologous series of layered ternary oxides, Na(PtO$_2$)$_{2\…

Diversity-enhanced Collaborative Mamba for Semi-supervised Medical Image Segmentation
Shumeng Li, Jian Zhang, Lei Qi, Luping Zhou, Yinghuan Shi, Yang Gao
https://arxiv.org/abs/2508.13712

Diversity-enhanced Collaborative Mamba for Semi-supervised Medical Image Segmentation
Acquiring high-quality annotated data for medical image segmentation is tedious and costly. Semi-supervised segmentation techniques alleviate this burden by leveraging unlabeled data to generate pseudo labels. Recently, advanced state space models, represented by Mamba, have shown efficient handling of long-range dependencies. This drives us to explore their potential in semi-supervised medical image segmentation. In this paper, we propose a novel Diversity-enhanced Collaborative Mamba framewor…

ICYMI yesterday: I've been writing about the diversity of tools for contributing to #OpenStreetMap and how this diversity plays a role in creating and maintaining a healthy commons.
https://tzovar.as/tool-diversity/

Constructive Conflict-Driven Multi-Agent Reinforcement Learning for Strategic Diversity
Yuxiang Mai, Qiyue Yin, Wancheng Ni, Pei Xu, Kaiqi Huang
https://arxiv.org/abs/2509.14276

Constructive Conflict-Driven Multi-Agent Reinforcement Learning for Strategic Diversity
In recent years, diversity has emerged as a useful mechanism to enhance the efficiency of multi-agent reinforcement learning (MARL). However, existing methods predominantly focus on designing policies based on individual agent characteristics, often neglecting the interplay and mutual influence among agents during policy formation. To address this gap, we propose Competitive Diversity through Constructive Conflict (CoDiCon), a novel approach that incorporates competitive incentives into coopera…

Moderate deviation principle for plug-in estimators of diversity indices on countable alphabets
Zhenhong Yu, Yu Miao
https://arxiv.org/abs/2508.12382 https://

Moderate deviation principle for plug-in estimators of diversity indices on countable alphabets
In the present paper, we consider the moderate deviation principle for the plug-in estimators of a large class of diversity indices on countable alphabets, where the distribution may change with the sample size. Our results cover some of the most commonly used indices, including Tsallis entropy, Reńyi entropy and Hill diversity number.

Identifying rocky planets and water worlds among sub-Neptune-sized exoplanets with the Habitable Worlds Observatory
Renyu Hu, Michiel Min, Max Millar-Blanchaer, Jacob Lustig-Yaeger, Tyler Robinson, Jennifer Burt, Athena Coustenis, Mario Damiano, Chuanfei Dong, Courtney Dressing, Luca Fossati, Stephen Kane, Soumil Kelkar, Tim Lichtenberg, Jean-Baptiste Ruffio, Dibyendu Sur, Armen Tokadjian, Martin Turbet

Identifying rocky planets and water worlds among sub-Neptune-sized exoplanets with the Habitable Worlds Observatory
Astronomers are debating whether the plentiful "sub-Neptune" exoplanets -- worlds a bit larger than Earth but smaller than Neptune -- are predominantly rocky planets, water-rich "ocean worlds," or gas-enshrouded mini-Neptunes. This question is crucial because such sub-Neptune-sized planets are among the most common in our galaxy, yet we have no analog in our own solar system, making them a key to understanding planet formation and diversity. It also directly impacts the search for habitable wor…

DivLogicEval: A Framework for Benchmarking Logical Reasoning Evaluation in Large Language Models
Tsz Ting Chung, Lemao Liu, Mo Yu, Dit-Yan Yeung
https://arxiv.org/abs/2509.15587

DivLogicEval: A Framework for Benchmarking Logical Reasoning Evaluation in Large Language Models
Logic reasoning in natural language has been recognized as an important measure of human intelligence for Large Language Models (LLMs). Popular benchmarks may entangle multiple reasoning skills and thus provide unfaithful evaluations on the logic reasoning skill. Meanwhile, existing logic reasoning benchmarks are limited in language diversity and their distributions are deviated from the distribution of an ideal logic reasoning benchmark, which may lead to biased evaluation results. This paper …

Don't miss today's Metacurity for the critical infosec developments you should know, including
--DOGE killed $324 million in grants for cybersecurity diversity, global partners
--US is the top investor in global spyware,
--Kenyan authorities accused of installing spyware on filmmakers' phones,
--GOP senators press Zuckerberg on WhatsApp whistleblower's claims,
--Wyden accuses Microsoft of negligence in Ascension attack,
--CISA says CVE shoul…

DOGE killed $324 million in grants for cybersecurity diversity, global partners
US is the top investor in global spyware, Kenyan authorities accused of installing spyware on filmmakers' phones, GOP senators press Zuckerberg on WhatsApp whistleblower's claims, Wyden accuses Microsoft of negligence in Ascension attack, CISA says CVE should remain public, much more

UN Peacekeeping Force in Lebanon Spends US Taxpayer Money on 'Gender Diversity' Training and Therapeutic Yoga Instruction, Drawing Scrutiny From Trump Admin (Adam Kredo/The Washington Free Beacon)
https://freebeacon.com/national-security/un-peacekeeping-force-in-lebanon-spends-us-taxpayer-money-on-gender-diversity-training-and-therapeutic-yoga-instruction-drawing-scrutiny-from-trump-admin/
http://www.memeorandum.com/250818/p3#a250818p3

Maximum diversity, weighting and invariants of time series
Byungchang So
https://arxiv.org/abs/2509.11146 https://arxiv.org/pdf/2509.11146

Maximum diversity, weighting and invariants of time series
Magnitude, obtained as a special case of Euler characteristic of enriched category, represents a sense of the size of metric spaces and is related to classical notions such as cardinality, dimension, and volume. While the studies have explained the meaning of magnitude from various perspectives, continuity also gives a valuable view of magnitude. Based on established results about continuity of magnitude and maximum diversity, this article focuses on continuity of weighting, a distribution whos…

https://www.newscientist.com/article/mg26735551-500-enchanting-photos-of-bizarre-mushrooms-showcase-fungi-diversity/

Enchanting photos of 'bizarre' mushrooms showcase fungi diversity
From squat toadstools to web-like mushrooms, images from Funga Obscura celebrate some of the most striking fungi on our planet

"Snow leopard populations threatened by climate change and low genetic diversity"
#SnowLeopard #Leopard #Animals #Climate

Snow leopard habitats could be at risk from climate change
Because there aren’t many snow leopards left, they are classified as “vulnerable” on the IUCN Red List.

Crosslisted article(s) found for cs.CY. https://arxiv.org/list/cs.CY/new
[1/1]:
- Benchmarking Sociolinguistic Diversity in Swahili NLP: A Taxonomy-Guided Approach
Kezia Oketch, John P. Lalor, Ahmed Abbasi

3D Cardiac Anatomy Generation Using Mesh Latent Diffusion Models
Jolanta Mozyrska, Marcel Beetz, Luke Melas-Kyriazi, Vicente Grau, Abhirup Banerjee, Alfonso Bueno-Orovio
https://arxiv.org/abs/2508.14122

3D Cardiac Anatomy Generation Using Mesh Latent Diffusion Models
Diffusion models have recently gained immense interest for their generative capabilities, specifically the high quality and diversity of the synthesized data. However, examples of their applications in 3D medical imaging are still scarce, especially in cardiology. Generating diverse realistic cardiac anatomies is crucial for applications such as in silico trials, electromechanical computer simulations, or data augmentations for machine learning models. In this work, we investigate the applicati…

The Impact of Team Diversity in Agile Development Education
Marco Torchiano, Riccardo Coppola, Antonio Vetro', Xhoi Musaj
https://arxiv.org/abs/2509.08389 https://

The Impact of Team Diversity in Agile Development Education
Software Engineering is mostly a male-dominated sector, where gender diversity is a key feature for improving equality of opportunities, productivity, and innovation. Other diversity aspects, including but not limited to nationality and ethnicity, are often understudied.In this work we aim to assess the impact of team diversity, focusing mainly on gender and nationality, in the context of an agile software development project-based course. We analyzed 51 teams over three academic years, measuri…

Reading Between the Lines: A Study of Thematic Bias in Book Recommender Systems
Nityaa Kalra, Savvina Daniil
https://arxiv.org/abs/2508.15643 https://arxiv…

Reading Between the Lines: A Study of Thematic Bias in Book Recommender Systems
Recommender systems help users discover new content, but can also reinforce existing biases, leading to unfair exposure and reduced diversity. This paper introduces and investigates thematic bias in book recommendations, defined as a disproportionate favouring or neglect of certain book themes. We adopt a multi-stage bias evaluation framework using the Book-Crossing dataset to evaluate thematic bias in recommendations and its impact on different user groups. Our findings show that thematic bi…

Bird Twin: Research Group Leader (f/m/x) for Developing Models of Bird Diversity and Policy-relevant Applications in Germany at UFZ, Germany
#ecoevojobs #ecologyjobs #xp

Die ePetition 183357 an den Bundestag aus dem Bereich Migrationspolitik mit dem Titel
Einführung eines bundesweiten Visa-Lotterie-Programms nach Vorbild der Diversity Visa Lottery der Vereinigten Staaten
kann bis zum Mittwoch 01. Oktober 2025 01:00 UTC mitgezeichnet werden und lautet
Mit der Pet…

Die ePetition 183357 an den Bundestag aus dem Bereich Migrationspolitik mit dem Titel
Einführung eines bundesweiten Visa-Lotterie-Programms nach Vorbild der Diversity Visa Lottery der Vereinigten Staaten
kann bis zum Mittwoch 01. Oktober 2025 01:00 UTC mitgezeichnet werden und lautet
Mit der Pet…

Sound Separation and Classification with Object and Semantic Guidance
Younghoo Kwon, Jung-Woo Choi
https://arxiv.org/abs/2509.15899 https://arxiv.org/pdf/2…

Sound Separation and Classification with Object and Semantic Guidance
The spatial semantic segmentation task focuses on separating and classifying sound objects from multichannel signals. To achieve two different goals, conventional methods fine-tune a large classification model cascaded with the separation model and inject classified labels as separation clues for the next iteration step. However, such integration is not ideal, in that fine-tuning over a smaller dataset loses the diversity of large classification models, features from the source separation model…

Parameterized Algorithms for Diversity of Networks with Ecological Dependencies
Mark Jones, Jannik Schestag
https://arxiv.org/abs/2510.09512 https://arxiv.…

Parameterized Algorithms for Diversity of Networks with Ecological Dependencies
For a phylogenetic tree, the phylogenetic diversity of a set A of taxa is the total weight of edges on paths to A. Finding small sets of maximal diversity is crucial for conservation planning, as it indicates where limited resources can be invested most efficiently. In recent years, efficient algorithms have been developed to find sets of taxa that maximize phylogenetic diversity either in a phylogenetic network or in a phylogenetic tree subject to ecological constraints, such as a food web. Ho…

Empirical Evidences for the Effects of Feature Diversity in Open Set Recognition and Continual Learning
Jiawen Xu, Odej Kao
https://arxiv.org/abs/2508.13005 https://

Empirical Evidences for the Effects of Feature Diversity in Open Set Recognition and Continual Learning
Open set recognition (OSR) and continual learning are two critical challenges in machine learning, focusing respectively on detecting novel classes at inference time and updating models to incorporate the new classes. While many recent approaches have addressed these problems, particularly OSR, by heuristically promoting feature diversity, few studies have directly examined the role that feature diversity plays in tackling them. In this work, we provide empirical evidence that enhancing feature…

Replaced article(s) found for astro-ph.SR. https://arxiv.org/list/astro-ph.SR/new
[1/1]:
- Explosions of pulsating red supergiants: a natural pathway for the diversity of Type II-P/L super...
V. A. Bronner, E. Laplace, F. R. N. Schneider, Ph. Podsiadlowski

Migration is as old as time:
https://theconversation.com/two-seventh-century-people-found-with-west-african-ancestry-a-story-of-diversity-and-integration-in-early-anglo-saxon-socie…

Two seventh-century people found with west African ancestry – a story of diversity and integration in early Anglo-Saxon society
We should not be surprised that there are west Africans in early medieval Britain, the clues were there.

DiCriTest: Testing Scenario Generation for Decision-Making Agents Considering Diversity and Criticality
Qitong Chu, Yufeng Yue, Danya Yao, Huaxin Pei
https://arxiv.org/abs/2508.11514

DiCriTest: Testing Scenario Generation for Decision-Making Agents Considering Diversity and Criticality
The growing deployment of decision-making agents in dynamic environments increases the demand for safety verification. While critical testing scenario generation has emerged as an appealing verification methodology, effectively balancing diversity and criticality remains a key challenge for existing methods, particularly due to local optima entrapment in high-dimensional scenario spaces. To address this limitation, we propose a dual-space guided testing framework that coordinates scenario param…

Quantitative metrics for trait and identity distributions
Leah Hoogstra, Katherine Slyman, Bjorn Sandstede
https://arxiv.org/abs/2509.14237 https://arxiv.o…

Quantitative metrics for trait and identity distributions
Understanding the role of demographic diversity in group settings requires effective quantitative metrics. Intersectional feminist theory has highlighted that demographic identities can intersect in complex ways, but most metrics used to study these traits are one-dimensional. In their paper "Diversity, identity, and data" (2025), Topaz et al. introduced two novel metrics that capture multiple aspects of demographic identities among group members: "intersecting diversity" and "shared identity".…

All political violence is bad; violence is never a good answer.
From report AG and potus want to hide: "…the number of far-right attacks continues to outpace all other types of terrorism and domestic violent extremism."
https://www.scribd.com/document/9186184…

What NIJ Research Tells Us About Domestic Terrorism | PDF | Extremism | Crimes
NIJ-funded research has enhanced understanding of domestic terrorism, particularly the rise of far-right extremist violence in the U.S., which has outpaced other forms of terrorism. The studies reveal that radicalization processes vary by group and crime type, and highlight the importance of community-based prevention strategies. Key findings include the diversity of extremist beliefs and behaviors, the role of military experience in radicalization, and the need for targeted interventions to pr…

Learning to vary: Teaching LMs to reproduce human linguistic variability in next-word prediction
Tobias Groot, Salo Lacunes, Evgenia Ilia
https://arxiv.org/abs/2509.17794 https:…

Learning to vary: Teaching LMs to reproduce human linguistic variability in next-word prediction
Natural language generation (NLG) tasks are often subject to inherent variability; \emph{e.g.} predicting the next word given a context has multiple valid responses, evident when asking multiple humans to complete the task. While having language models (LMs) that are aligned pluralistically, so that they are able to reproduce well the inherent diversity in perspectives of an entire population of interest is clearly beneficial, \citet{ilia2024predict} show that LMs do not reproduce this type of …

Diversity in planetary architectures from pebble accretion: Water delivery to the habitable zone with pebble snow
Sean McCloat, Gijs Mulders, Sherry Fieber-Beyer
https://arxiv.org/abs/2509.14101

Diversity in planetary architectures from pebble accretion: Water delivery to the habitable zone with pebble snow
"Pebble snow" describes a planet formation mechanism where icy pebbles in the outer disk reach inner planet embryos as the water ice line evolves inward. We model the effects pebble snow has on sculpting planetary system architectures by developing "The PPOLs Model". The model is capable of growing any number of protoplanet seed masses by pebble accretion simultaneously and accounts for differences in rocky and icy pebble composition, the filtering of pebbles by other protoplanets, the pebble i…

Weekend #Plankton Factoid 🦠🦐
You've likely watched a police procedural where the lab states the drowning was suspicious because of algae. The shells of diatoms have long been used in forensic #limnology because they are made of glass, so preserve very well.

Kaepernick, Lynch join hockey diversity event https://www.espn.com/olympics/hockey/story/_/id/45869078/colin-kaepernick-marshawn-lynch-join-hockey-diversity-group-host-event

CAST: Counterfactual Labels Improve Instruction Following in Vision-Language-Action Models
Catherine Glossop, William Chen, Arjun Bhorkar, Dhruv Shah, Sergey Levine
https://arxiv.org/abs/2508.13446

CAST: Counterfactual Labels Improve Instruction Following in Vision-Language-Action Models
Generalist robots should be able to understand and follow user instructions, but current vision-language-action (VLA) models struggle with following fine-grained commands despite providing a powerful architecture for mapping open-vocabulary natural language instructions to robot actions. One cause for this is a lack of semantic diversity and language grounding in existing robot datasets and, specifically, a lack of fine-grained task diversity for similar observations. To address this, we presen…

On The Road - To Xi’An/ Beings 👁️‍🗨️
在路上 - 去西安/ 灵 👁️‍🗨️
📷 Pentax MX
🎞️Kodak Double-X 5222
#filmphotography #Photography #blackandwhite

The far right is surging in the United States,
driven in part by white nationalists exploiting economic anxieties
and a populace increasingly frustrated with the political status quo.
Now, as the Trump administration rolls back diversity, equity and inclusion policies,
cracks down on immigration and offers pardons to white supremacists,
some see an opening.
In creating their community, the founders of "Return to the Land" are challenging anti-d…

Arkansas Housing Development Restricted to White Residents Sparks Legal Concerns
Housing rights experts say a community restricted to white residents is illegal, but the creators believe they could win a potential challenge in court in the current political climate.

Bayesian estimators of diversity indexes on exchangeable random partitions
Servet Martinez
https://arxiv.org/abs/2509.12115 https://arxiv.org/pdf/2509.1211…

Bayesian estimators of diversity indexes on exchangeable random partitions
Bayesian diversity estimators are martingales converging almost surely and in mean with common limit and local behavior with plug in estimators.

Partial Secrecy Analysis in Wireless Systems: Diversity-Enhanced PLS over Generalized Fading Channels
Henry Carvajal Mora, Nathaly Orozco, Fernando Almeida Garc\'ia, Jos\'e Vega-S\'anchez, Felipe Grijalva, Edgar Benitez Olivo
https://arxiv.org/abs/2509.12359

Partial Secrecy Analysis in Wireless Systems: Diversity-Enhanced PLS over Generalized Fading Channels
Securing information in future mobile networks is challenging, especially for devices with limited computational resources. Physical layer security (PLS) offers a viable solution by leveraging wireless channel randomness. When full secrecy is unattainable, the partial secrecy regime provides a realistic alternative. This work analyzes partial secrecy performance under the generalized multicluster fluctuating two-ray (MFTR) fading model, which subsumes many classical fading cases. We study a sys…

Analysis: journalism's DEI efforts in the US have declined, fueled in part by the Trump administration's quashing of diversity initiatives (Hanaa' Tameez/Nieman Lab)
https://www.niemanlab.org/2025/09/from-reckoning-to-retreat-news…

From reckoning to retreat: Journalism’s DEI efforts are in decline
Diversity-related newsroom jobs haven't totally disappeared — but they also haven't stuck.

#idw Keeping pace with #ClimateChange: Genetic exchange enables rapid adaptation in songbirds
Leibniz-Institut zur Analyse des Biodiversitätswandels
Exchange of genetic diversity between species accelerates evolutionary adaptation Climate change is rapidly altering our environment – and posing m…

Keeping pace with climate change: Genetic exchange enables rapid adaptation in songbirds

LUNDIsim: model meshes for flow simulation and scientific data compression benchmarks
Laurent Duval, Fr\'ed\'eric Payan, Christophe Preux, Lauriane Bouard
https://arxiv.org/abs/2508.13636

LUNDIsim: model meshes for flow simulation and scientific data compression benchmarks
The volume of scientific data produced for and by numerical simulation workflows is increasing at an incredible rate. This raises concerns either in computability, interpretability, and sustainability. This is especially noticeable in earth science (geology, meteorology, oceanography, and astronomy), notably with climate studies. We highlight five main evaluation issues: efficiency, discrepancy, diversity, interpretability, availability. Among remedies, lossless and lossy compression techn…

Towards Robust Visual Continual Learning with Multi-Prototype Supervision
Xiwei Liu, Yulong Li, Yichen Li, Xinlin Zhuang, Haolin Yang, Huifa Li, Imran Razzak
https://arxiv.org/abs/2509.16011

Towards Robust Visual Continual Learning with Multi-Prototype Supervision
Language-guided supervision, which utilizes a frozen semantic target from a Pretrained Language Model (PLM), has emerged as a promising paradigm for visual Continual Learning (CL). However, relying on a single target introduces two critical limitations: 1) semantic ambiguity, where a polysemous category name results in conflicting visual representations, and 2) intra-class visual diversity, where a single prototype fails to capture the rich variety of visual appearances within a class. To this …

A modified RIME algorithm with covariance learning and diversity enhancement for numerical optimization
Shangqing Shi, Luoxiao Zhang, Yuchen Yin, Xiong Yang, Hoileong Lee
https://arxiv.org/abs/2509.09529

A modified RIME algorithm with covariance learning and diversity enhancement for numerical optimization
Metaheuristics are widely applied for their ability to provide more efficient solutions. The RIME algorithm is a recently proposed physical-based metaheuristic algorithm with certain advantages. However, it suffers from rapid loss of population diversity during optimization and is prone to fall into local optima, leading to unbalanced exploitation and exploration. To address the shortcomings of RIME, this paper proposes a modified RIME with covariance learning and diversity enhancement (MRIME-C…

Dual-Phase Playtime-guided Recommendation: Interest Intensity Exploration and Multimodal Random Walks
Jingmao Zhang, Zhiting Zhao, Yunqi Lin, Jianghong Ma, Tianjun Wei, Haijun Zhang, Xiaofeng Zhang
https://arxiv.org/abs/2508.14058

Dual-Phase Playtime-guided Recommendation: Interest Intensity Exploration and Multimodal Random Walks
The explosive growth of the video game industry has created an urgent need for recommendation systems that can scale with expanding catalogs and maintain user engagement. While prior work has explored accuracy and diversity in recommendations, existing models underutilize playtime, a rich behavioral signal unique to gaming platforms, and overlook the potential of multimodal information to enhance diversity. In this paper, we propose DP2Rec, a novel Dual-Phase Playtime-guided Recommendation mode…

Harvard hiring investigation could upend employment practices for institutions well beyond academia (Aidan Ryan/The Boston Globe)
https://www.bostonglobe.com/2025/08/18/metro/harvard-trump-hiring-investigation-diversity/
http://www.memeorandum.com/250819/p60#a250819p60

ATLAS: Decoupling Skeletal and Shape Parameters for Expressive Parametric Human Modeling
Jinhyung Park, Javier Romero, Shunsuke Saito, Fabian Prada, Takaaki Shiratori, Yichen Xu, Federica Bogo, Shoou-I Yu, Kris Kitani, Rawal Khirodkar
https://arxiv.org/abs/2508.15767

ATLAS: Decoupling Skeletal and Shape Parameters for Expressive Parametric Human Modeling
Parametric body models offer expressive 3D representation of humans across a wide range of poses, shapes, and facial expressions, typically derived by learning a basis over registered 3D meshes. However, existing human mesh modeling approaches struggle to capture detailed variations across diverse body poses and shapes, largely due to limited training data diversity and restrictive modeling assumptions. Moreover, the common paradigm first optimizes the external body surface using a linear basis…

Following our mapping party for OpenStreetMap's birthday, I've been thinking more about the diversity of OSM tools and how they help create and maintain a commons.
#OpenStreetMap

Effective decoupling of mutations and the resulting loss of biodiversity caused by environmental change
Ruixi Huang, David Waxman
https://arxiv.org/abs/2509.17913 https://

Effective decoupling of mutations and the resulting loss of biodiversity caused by environmental change
Many biological populations exhibit diversity in their strategy for survival and reproduction in a given environment, and microbes are an example. We explore the fate of different strategies under sustained environmental change by considering a mathematical model for a large population of asexual organisms. Fitness is a bimodal function of a quantitative trait, with two local optima, separated by a local minimum, i.e., a mixture of stabilising and disruptive selection. The optima represent two …

And another related position:
BirdFuture: Research Group Leader (f/m/x) for Developing Models of Bird Diversity and Policy-relevant Applications in Europe
#ecologyjobs #ecoevojobs #xp

Quantum MIMO Diversity over Discrete-Variable Crosstalk Channels
Shehbaz Tariq, Junaid ur Rehman, Symeon Chatzinotas
https://arxiv.org/abs/2508.07344 https://

Quantum MIMO Diversity over Discrete-Variable Crosstalk Channels
Quantum communication plays a pivotal role in enabling distributed quantum computing and sensing. Diversity strategies can be used to increase the communication reliability (in the sense of output fidelity with respect to the input quantum state) when multiple communication channels are available. The current paper proposes a diversity strategy for quantum discrete variable (DV) multiple-input-multiple-output (MIMO) channels, utilizing approximate cloning to distribute information across multip…

OSCAR: Orthogonal Stochastic Control for Alignment-Respecting Diversity in Flow Matching
Jingxuan Wu, Zhenglin Wan, Xingrui Yu, Yuzhe Yang, Bo An, Ivor Tsang
https://arxiv.org/abs/2510.09060

OSCAR: Orthogonal Stochastic Control for Alignment-Respecting Diversity in Flow Matching
Flow-based text-to-image models follow deterministic trajectories, forcing users to repeatedly sample to discover diverse modes, which is a costly and inefficient process. We present a training-free, inference-time control mechanism that makes the flow itself diversity-aware. Our method simultaneously encourages lateral spread among trajectories via a feature-space objective and reintroduces uncertainty through a time-scheduled stochastic perturbation. Crucially, this perturbation is projected …

Dwarf diversity in $\Lambda$CDM with baryons
Akaxia Cruz, Alyson Brooks, Mariangela Lisanti, Annika H. G. Peter, Robel Geda, Thomas Quinn, Michael Tremmel, Ferah Munshi, Ben Keller, James Wadsley
https://arxiv.org/abs/2510.11800

Dwarf diversity in $Λ$CDM with baryons
Observed rotation curves of dwarf galaxies exhibit significant diversity at fixed halo mass, challenging galaxy formation within the Cold Dark Matter (CDM) model. Previous cosmological galaxy formation simulations with baryonic physics fail to reproduce the full diversity of rotation curves, suggesting either that there is a flaw in baryonic feedback models, or that an alternative to CDM must be invoked. In this work, we use the Marvelous Massive Dwarf zoom-in simulations, a suite of high-resol…

D-RDW: Diversity-Driven Random Walks for News Recommender Systems
Runze Li, Lucien Heitz, Oana Inel, Abraham Bernstein
https://arxiv.org/abs/2508.13035 https://

D-RDW: Diversity-Driven Random Walks for News Recommender Systems
This paper introduces Diversity-Driven RandomWalks (D-RDW), a lightweight algorithm and re-ranking technique that generates diverse news recommendations. D-RDW is a societal recommender, which combines the diversification capabilities of the traditional random walk algorithms with customizable target distributions of news article properties. In doing so, our model provides a transparent approach for editors to incorporate norms and values into the recommendation process. D-RDW shows enhanced pe…

Explosions of pulsating red supergiants: a natural pathway for the diversity of Type II-P/L supernovae
V. A. Bronner, E. Laplace, F. R. N. Schneider, Ph. Podsiadlowski
https://arxiv.org/abs/2508.11077 …

Explosions of pulsating red supergiants: a natural pathway for the diversity of Type II-P/L supernovae
Red supergiants (RSGs), which are progenitors of hydrogen-rich Type II supernovae (SNe), have been known to pulsate from both observations and theory. The pulsations can be present at core collapse and affect the resulting SN. However, SN light curve models of such RSGs commonly use hydrostatic progenitor models and ignore pulsations. Here, we model the final stages of a 15 solar-mass RSG and self-consistently follow the hydrodynamical evolution. We find the growth of large amplitude radial pul…

Informfully Recommenders -- Reproducibility Framework for Diversity-aware Intra-session Recommendations
Lucien Heitz, Runze Li, Oana Inel, Abraham Bernstein
https://arxiv.org/abs/2508.13019

Informfully Recommenders -- Reproducibility Framework for Diversity-aware Intra-session Recommendations
Norm-aware recommender systems have gained increased attention, especially for diversity optimization. The recommender systems community has well-established experimentation pipelines that support reproducible evaluations by facilitating models' benchmarking and comparisons against state-of-the-art methods. However, to the best of our knowledge, there is currently no reproducibility framework to support thorough norm-driven experimentation at the pre-processing, in-processing, post-processing, …

The U.S. Department of Education has pulled funding for programs in eight states
aimed at supporting students who have both hearing and vision loss,
a move that could affect some of the country’s most vulnerable students.
The programs are considered vital in those states but represent only a little over $1 million a year in federal money.
Nonetheless, they got caught in the Trump administration’s attacks on diversity, equity and inclusion,
with an Education Dep…

Programs for Students With Hearing and Vision Loss Harmed by Trump’s Anti-Diversity Push
Citing concerns about DEI, the U.S. Department of Education has halted funding for programs that support students with combined hearing and vision loss in eight states. “How low can you go?” one advocate asked. “How can you do this to children?”

The Italian federation of newspaper publishers submits a complaint to Italy's communication watchdog calling for an investigation into Google's AI Overviews (Angela Giuffrida/The Guardian)
https://www.theguardian.com/technology/202

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…

Diversity First, Quality Later: A Two-Stage Assumption for Language Model Alignment
Zetian Sun, Dongfang Li, Baotian Hu
https://arxiv.org/abs/2508.10530 https://

Diversity First, Quality Later: A Two-Stage Assumption for Language Model Alignment
The alignment of language models (LMs) with human preferences is critical for building reliable AI systems. The problem is typically framed as optimizing an LM policy to maximize the expected reward that reflects human preferences. Recently, Direct Preference Optimization (DPO) was proposed as a LM alignment method that directly optimize the policy from static preference data, and further improved by incorporating on-policy sampling (i.e., preference candidates generated during the training loo…

🍄 Turning biodiversity upside down: Conservation maps miss fungal hotspots by focusing on plants
https://phys.org/news/2025-07-biodiversity-upside-fungal-hotspots-focusing.html

Turning biodiversity upside down: Conservation maps miss fungal hotspots by focusing on plants
For decades, scientists and conservationists have been using aboveground plant biodiversity as a metric for conserving ecosystems. Now, a new study finds that there is a major mismatch between aboveground plant diversity and Earth's underground fungal biodiversity.

Simulation of Impact-induced seismic shaking on asteroid (25143) Itokawa to address its resurfacing process
Sunho Jin, Masateru Ishiguro
https://arxiv.org/abs/2508.13727 https:/…

Simulation of Impact-induced seismic shaking on asteroid (25143) Itokawa to address its resurfacing process
The surface of asteroid (25143) Itokawa shows both fresh and mature terrains, despite its short space weathering timescale of approximately 1000 years, as inferred from recent studies. Seismic shaking triggered by the impact that formed the 8-meter Kamoi crater has been proposed as a possible explanation for the diversity. This study aims to examine whether the seismic shaking induced by the impact could account for the observed spatial variations in space weathering and further constrain the i…

Warning that Trump scrapping diversity orders could hurt global economic growth | The Independent
https://www.independent.co.uk/news/world/americas/trump-diversity-economic-growth-women-mariella-frostrup-b2839581.html

Beyond Pass@1: Self-Play with Variational Problem Synthesis Sustains RLVR
Xiao Liang, Zhongzhi Li, Yeyun Gong, Yelong Shen, Ying Nian Wu, Zhijiang Guo, Weizhu Chen
https://arxiv.org/abs/2508.14029

Beyond Pass@1: Self-Play with Variational Problem Synthesis Sustains RLVR
Reinforcement Learning with Verifiable Rewards (RLVR) has recently emerged as a key paradigm for post-training Large Language Models (LLMs), particularly for complex reasoning tasks. However, vanilla RLVR training has been shown to improve Pass@1 performance at the expense of policy entropy, leading to reduced generation diversity and limiting the Pass@k performance, which typically represents the upper bound of LLM reasoning capability. In this paper, we systematically analyze the policy's gen…

Toward Embodiment Equivariant Vision-Language-Action Policy
Anzhe Chen, Yifei Yang, Zhenjie Zhu, Kechun Xu, Zhongxiang Zhou, Rong Xiong, Yue Wang
https://arxiv.org/abs/2509.14630

Toward Embodiment Equivariant Vision-Language-Action Policy
Vision-language-action policies learn manipulation skills across tasks, environments and embodiments through large-scale pre-training. However, their ability to generalize to novel robot configurations remains limited. Most approaches emphasize model size, dataset scale and diversity while paying less attention to the design of action spaces. This leads to the configuration generalization problem, which requires costly adaptation. We address this challenge by formulating cross-embodiment pre-tr…

Feature Request Analysis and Processing: Tasks, Techniques, and Trends
Feifei Niu, Chuanyi Li, Haosheng Zuo, Jionghan Wu, Xin Xia
https://arxiv.org/abs/2508.12436 https://

Feature Request Analysis and Processing: Tasks, Techniques, and Trends
Feature requests are proposed by users to request new features or enhancements of existing features of software products, which represent users' wishes and demands. Satisfying users' demands can benefit the product from both competitiveness and user satisfaction. Feature requests have seen a rise in interest in the past few years and the amount of research has been growing. However, the diversity in the research topics suggests the need for their collective analysis to identify the challenges a…

Revisiting the systematics of Brevipalpus flat mites (Tenuipalpidae): phylogeny, species groups and cryptic diversity
Renata Santos de Mendon\c{c}a (PNPD/CAPES, UnB, CENARGEN), Francisco Ferragut (UPV, IAM), Isis Carolina S. de Oliveira (UnB, CENARGEN), Aline Daniele Tassi (ESALQ, UF), Felipe Fileni (UMR CBGP), Ronald Ochoa (UMR CBGP), Denise Navia (UMR CBGP)
h…

Revisiting the systematics of Brevipalpus flat mites (Tenuipalpidae): phylogeny, species groups and cryptic diversity
Phytophagous mites in the genus Brevipalpus (Tenuipalpidae) can be major pests, causing direct damage to their host plants or vectoring viruses. However, a phylogeny-based classification to understand their evolution and predict their bioecological aspects is lacking. Accurate species identification is crucial for studying pathosystem interactions, implementing quarantine measures, and developing control strategies. This study revisited the classification of Brevipalpus based on phylogenetic re…

Trump’s administration simply will not stop setting up snitch lines,
urging federal staff to rat on each other for the crime of being anti-Trump
or in favor of the virtues of diversity, equity, and inclusion.
https://www.rollingstone.com/pol…

Trump’s Government Is a Den of Snitches, ‘Freaks,’ and Paranoid Tyrants
The Department of Health and Human Services is the latest agency to ask government employees to snitch about diversity practices.

Chunks as Arms: Multi-Armed Bandit-Guided Sampling for Long-Context LLM Preference Optimization
Shaohua Duan, Xinze Li, Zhenghao Liu, Xiaoyuan Yi, Yukun Yan, Shuo Wang, Yu Gu, Ge Yu, Maosong Sun
https://arxiv.org/abs/2508.13993

Chunks as Arms: Multi-Armed Bandit-Guided Sampling for Long-Context LLM Preference Optimization
Long-context modeling is critical for a wide range of real-world tasks, including long-context question answering, summarization, and complex reasoning tasks. Recent studies have explored fine-tuning Large Language Models (LLMs) with synthetic data to enhance their long-context capabilities. However, the effectiveness of such approaches is often limited by the low diversity and factual inconsistencies in the generated data. To address these challenges, we propose LongMab-PO, a novel framework t…

ROVR-Open-Dataset: A Large-Scale Depth Dataset for Autonomous Driving
Xianda Guo, Ruijun Zhang, Yiqun Duan, Ruilin Wang, Keyuan Zhou, Wenzhao Zheng, Wenke Huang, Gangwei Xu, Mike Horton, Yuan Si, Hao Zhao, Long Chen
https://arxiv.org/abs/2508.13977

ROVR-Open-Dataset: A Large-Scale Depth Dataset for Autonomous Driving
Depth estimation is a fundamental task for 3D scene understanding in autonomous driving, robotics, and augmented reality. Existing depth datasets, such as KITTI, nuScenes, and DDAD, have advanced the field but suffer from limitations in diversity and scalability. As benchmark performance on these datasets approaches saturation, there is an increasing need for a new generation of large-scale, diverse, and cost-efficient datasets to support the era of foundation models and multi-modal learning. T…

Optimizing for Persuasion Improves LLM Generalization: Evidence from Quality-Diversity Evolution of Debate Strategies
Aksel Joonas Reedi, Corentin L\'eger, Julien Pourcel, Loris Gaven, Perrine Charriau, Guillaume Pourcel
https://arxiv.org/abs/2510.05909

Optimizing for Persuasion Improves LLM Generalization: Evidence from Quality-Diversity Evolution of Debate Strategies
Large Language Models (LLMs) optimized to output truthful answers often overfit, producing brittle reasoning that fails to generalize. While persuasion-based optimization has shown promise in debate settings, it has not been systematically compared against mainstream truth-based approaches. We introduce DebateQD, a minimal Quality-Diversity (QD) evolutionary algorithm that evolves diverse debate strategies across different categories (rationality, authority, emotional appeal, etc.) through tour…

Self-Guided Action Diffusion
Rhea Malhotra, Yuejiang Liu, Chelsea Finn
https://arxiv.org/abs/2508.12189 https://arxiv.org/pdf/2508.12189

Self-Guided Action Diffusion
Recent works have shown the promise of inference-time search over action samples for improving generative robot policies. In particular, optimizing cross-chunk coherence via bidirectional decoding has proven effective in boosting the consistency and reactivity of diffusion policies. However, this approach remains computationally expensive as the diversity of sampled actions grows. In this paper, we introduce self-guided action diffusion, a more efficient variant of bidirectional decoding tailor…

Unsupervised Urban Tree Biodiversity Mapping from Street-Level Imagery Using Spatially-Aware Visual Clustering
Diaa Addeen Abuhani, Marco Seccaroni, Martina Mazzarello, Imran Zualkernan, Fabio Duarte, Carlo Ratti
https://arxiv.org/abs/2508.13814

Unsupervised Urban Tree Biodiversity Mapping from Street-Level Imagery Using Spatially-Aware Visual Clustering
Urban tree biodiversity is critical for climate resilience, ecological stability, and livability in cities, yet most municipalities lack detailed knowledge of their canopies. Field-based inventories provide reliable estimates of Shannon and Simpson diversity but are costly and time-consuming, while supervised AI methods require labeled data that often fail to generalize across regions. We introduce an unsupervised clustering framework that integrates visual embeddings from street-level imagery …

Enhancing Diversity in Large Language Models via Determinantal Point Processes
Yilei Chen, Souradip Chakraborty, Lorenz Wolf, Ioannis Ch. Paschalidis, Aldo Pacchiano
https://arxiv.org/abs/2509.04784

Enhancing Diversity in Large Language Models via Determinantal Point Processes
Supervised fine-tuning and reinforcement learning are two popular methods for post-training large language models (LLMs). While improving the model's performance on downstream tasks, they often reduce the model's output diversity, leading to narrow, canonical responses. Existing methods to enhance diversity are limited, either by operating at inference time or by focusing on lexical differences. We propose a novel training method named DQO based on determinantal point processes (DPPs) to jointl…

Prompt Optimization Across Multiple Agents for Representing Diverse Human Populations
Manh Hung Nguyen, Sebastian Tschiatschek, Adish Singla
https://arxiv.org/abs/2510.07064 htt…

Prompt Optimization Across Multiple Agents for Representing Diverse Human Populations
The difficulty and expense of obtaining large-scale human responses make Large Language Models (LLMs) an attractive alternative and a promising proxy for human behavior. However, prior work shows that LLMs often produce homogeneous outputs that fail to capture the rich diversity of human perspectives and behaviors. Thus, rather than trying to capture this diversity with a single LLM agent, we propose a novel framework to construct a set of agents that collectively capture the diversity of a giv…

Mind the Gap: Conformative Decoding to Improve Output Diversity of Instruction-Tuned Large Language Models
Max Peeperkorn, Tom Kouwenhoven, Dan Brown, Anna Jordanous
https://arxiv.org/abs/2507.20956

Mind the Gap: Conformative Decoding to Improve Output Diversity of Instruction-Tuned Large Language Models
Instruction-tuning large language models (LLMs) reduces the diversity of their outputs, which has implications for many tasks, particularly for creative tasks. This paper investigates the ``diversity gap'' for a writing prompt narrative generation task. This gap emerges as measured by current diversity metrics for various open-weight and open-source LLMs. The results show significant decreases in diversity due to instruction-tuning. We explore the diversity loss at each fine-tuning stage for th…

ID-Card Synthetic Generation: Toward a Simulated Bona fide Dataset
Qingwen Zeng, Juan E. Tapia, Izan Garcia, Juan M. Espin, Christoph Busch
https://arxiv.org/abs/2508.13078 http…

ID-Card Synthetic Generation: Toward a Simulated Bona fide Dataset
Nowadays, the development of a Presentation Attack Detection (PAD) system for ID cards presents a challenge due to the lack of images available to train a robust PAD system and the increase in diversity of possible attack instrument species. Today, most algorithms focus on generating attack samples and do not take into account the limited number of bona fide images. This work is one of the first to propose a method for mimicking bona fide images by generating synthetic versions of them using St…

MuDRiC: Multi-Dialect Reasoning for Arabic Commonsense Validation
Kareem Elozeiri, Mervat Abassy, Preslav Nakov, Yuxia Wang
https://arxiv.org/abs/2508.13130 https://

MuDRiC: Multi-Dialect Reasoning for Arabic Commonsense Validation
Commonsense validation evaluates whether a sentence aligns with everyday human understanding, a critical capability for developing robust natural language understanding systems. While substantial progress has been made in English, the task remains underexplored in Arabic, particularly given its rich linguistic diversity. Existing Arabic resources have primarily focused on Modern Standard Arabic (MSA), leaving regional dialects underrepresented despite their prevalence in spoken contexts. To bri…

SPATIALGEN: Layout-guided 3D Indoor Scene Generation
Chuan Fang, Heng Li, Yixun Liang, Jia Zheng, Yongsen Mao, Yuan Liu, Rui Tang, Zihan Zhou, Ping Tan
https://arxiv.org/abs/2509.14981

SPATIALGEN: Layout-guided 3D Indoor Scene Generation
Creating high-fidelity 3D models of indoor environments is essential for applications in design, virtual reality, and robotics. However, manual 3D modeling remains time-consuming and labor-intensive. While recent advances in generative AI have enabled automated scene synthesis, existing methods often face challenges in balancing visual quality, diversity, semantic consistency, and user control. A major bottleneck is the lack of a large-scale, high-quality dataset tailored to this task. To addre…

SINAI at eRisk@CLEF 2022: Approaching Early Detection of Gambling and Eating Disorders with Natural Language Processing
Alba Maria Marmol-Romero, Salud Maria Jimenez-Zafra, Flor Miriam Plaza-del-Arco, M. Dolores Molina-Gonzalez, Maria-Teresa Martin-Valdivia, Arturo Montejo-Raez
https://arxiv.org/abs/2509.14806

SINAI at eRisk@CLEF 2022: Approaching Early Detection of Gambling and Eating Disorders with Natural Language Processing
This paper describes the participation of the SINAI team in the eRisk@CLEF lab. Specifically, two of the proposed tasks have been addressed: i) Task 1 on the early detection of signs of pathological gambling, and ii) Task 3 on measuring the severity of the signs of eating disorders. The approach presented in Task 1 is based on the use of sentence embeddings from Transformers with features related to volumetry, lexical diversity, complexity metrics, and emotion-related scores, while the approach…

Jointly Reinforcing Diversity and Quality in Language Model Generations
Tianjian Li, Yiming Zhang, Ping Yu, Swarnadeep Saha, Daniel Khashabi, Jason Weston, Jack Lanchantin, Tianlu Wang
https://arxiv.org/abs/2509.02534

Jointly Reinforcing Diversity and Quality in Language Model Generations
Post-training of Large Language Models (LMs) often prioritizes accuracy and helpfulness at the expense of diversity. This creates a tension: while post-training improves response quality, it also sharpens output distributions and reduces the range of ideas, limiting the usefulness of LMs in creative and exploratory tasks such as brainstorming, storytelling, or problem solving. We address this challenge with Diversity-Aware Reinforcement Learning (DARLING), a framework that jointly optimizes for…

A survey of diversity quantification in natural language processing: The why, what, where and how
Louis Est\`eve, Marie-Catherine de Marneffe, Nurit Melnik, Agata Savary, Olha Kanishcheva
https://arxiv.org/abs/2507.20858

A survey of diversity quantification in natural language processing: The why, what, where and how
The concept of diversity has received increased consideration in Natural Language Processing (NLP) in recent years. This is due to various motivations like promoting and inclusion, approximating human linguistic behavior, and increasing systems' performance. Diversity has however often been addressed in an ad hoc manner in NLP, and with few explicit links to other domains where this notion is better theorized. We survey articles in the ACL Anthology from the past 6 years, with "diversity" or "d…

TinyTim: A Family of Language Models for Divergent Generation
Christopher J. Agostino
https://arxiv.org/abs/2508.11607 https://arxiv.org/pdf/2508.11607

TinyTim: A Family of Language Models for Divergent Generation
This work introduces TinyTim, a family of large language models fine-tuned on James Joyce's `Finnegans Wake'. Through quantitative evaluation against baseline models, we demonstrate that TinyTim V1 produces a statistically distinct generative profile characterized by high lexical diversity and low semantic coherence. These findings are interpreted through theories of creativity and complex problem-solving, arguing that such specialized models can function as divergent knowledge sources within m…