Explore the Frontier of Global Academia

01.

arXiv (CS.LG) 2026-06-12 DOI: arXiv:2606.12763

Adaptive Weighted Averaging

Authors:

Aditya Bhaskara↗Ashok Cutkosky↗Ravi Kumar↗Manish Purohit↗

arXiv:2606.12763v1 Announce Type: new Abstract: We study the problem of selecting the largest among $n$ unknown values $x_1,\dots,x_n$ given only a single unbiased estimate $y_i$ for each $x_i$. We design strategies that are simultaneously admissible (not uniformly dominated by any other strategy) and also never worse than a given baseline such as uniform random selection. We provide an application to stochastic optimization, where we obtain online-to-batch conversion bounds with a desirable "no-compromise" guarantee: they are never worse than standard random iterate selection, and yet can be significantly better in benign settings.

Read & Discuss → View Source →

02.

arXiv (CS.CV) 2026-06-17 DOI: arXiv:2606.17953

MLLMs Get It Right, Then Get It Wrong: Tracing and Correcting Late-Layer Textual Bias

Authors:

Xingming Li↗Ao Cheng↗Qiyao Sun↗Xixiang He↗Xuanyu Ji↗Runke Huang↗Qingyong Hu↗

When vision contradicts text, multimodal large language models (MLLMs) consistently favor text, even when images provide clear evidence otherwise. This bias poses risks for applications requiring visual grounding, yet its cause remains unclear. In this paper, we uncover a surprising finding: models often get it right initially, forming correct vision-based predictions in their intermediate layers, before changing their minds and favoring text in the final output. We call this "late-layer textual override". The visual information is encoded, it simply does not survive to the output. More intriguingly, we find that how predictions change reveals whether they're correct: 85% of failures shift toward text, while 89% of successes shift toward vision. This directional signature enables a simple but powerful intervention: when we detect a confident visual prediction being suppressed, we restore it. We propose CALRD (Conflict-Aware Layer Reference Decoding), a training-free method that recovers overridden predictions at inference time. Experiments across five MLLMs of varying architectures demonstrate up to 9.4% absolute improvements on conflict benchmarks while largely preserving standard performance, without training or external knowledge. It recovers what the model already knew but failed to preserve.

Read & Discuss → View Source →

03.

Nature (Science) 2026-06-22 DOI: HASH:ea1c0e135d50c98ce6d52e2e1e3648f0

Isotopic evidence for a cold and distant origin of 3I/ATLAS

Authors:

Martin Cordiner↗

Interstellar objects provide the only directly observable samples of icy planetesimals formed around other stars, and can therefore provide insight into the diversity of physical and chemical conditions occurring during exoplanet formation1−3. Here we report isotopic measurements of the interstellar comet 3I/ATLAS, which reveal an elemental composition unlike any Solar System body. The water in 3I/ATLAS is enriched in deuterium, at a level of D/H = (0.98 ± 0.06)%, which is more than an order of magnitude higher than in known comets, while its range of 12C/13C ratios (141–191 for CO2 and 123–172 for CO) exceeds typical values found in the Solar System, as well as nearby interstellar clouds and protoplanetary disks. Such extreme isotopic signatures indicate formation at temperatures  ≲ 30 K in a relatively metal-poor environment. When interpreted with respect to models for Galactic chemical evolution, the carbon isotopic composition implies that 3I/ATLAS may have accreted as long ago as 12 billion years, following a period of intense, early star formation. 3I/ATLAS thus represents a preserved fragment of an ancient planetary system.

Read & Discuss → View Source →

04.

arXiv (CS.CL) 2026-06-11 DOI: arXiv:2606.11520

ISE: An Execution-Grounded Recipe for Multi-Turn OS-Agent Trajectories

Authors:

Siyuan Luo↗Nairong Zheng↗Lin Zhou↗Tiankuo Yao↗Shengyou Yuan↗Haojia Yu↗Cong Pang↗Jiapeng Luo↗Lewei Lu↗

Training capable OS agents requires data that simultaneously captures structured user intents, multi-turn task delegation, and grounded tool execution–properties absent from existing datasets. We propose ISE (Intent -> Simulate -> Execute), a three-stage synthesis paradigm that addresses these gaps jointly. Stage 1 constructs roughly 50000 structured intents via a 4D framework (Persona x Domain x Task x Complexity); after deduplication the pool contains 43956 unique intents and attains a Vendi Score of 61.57 over the entire pool on mpnet-base-v2 embeddings (cosine kernel, q=1). Stage 2 drives multi-turn user-agent interaction through a role-locked user simulator that grounds each user turn in actual execution outcomes, producing 23132 complete trajectories averaging 8.12 user turns and 68.24 total dialogue turns. Stage 3 runs every tool call inside a live, isolated OS workspace, generating authentic failure-recovery dynamics instead of simulated responses. Fine-tuning on ISETrace improves ClawEval pass@1 from 19.3 to 37.7 using Qwen3-8B on agent tool-use tasks with a standard protocol. This result outperforms zero-shot GPT-4o and the larger Qwen3-32B base model which is four times bigger. An ablation on Stage 2 proves multi-turn simulation brings a large portion of the performance gain. We release all source code and dataset at https://github.com/Valiere01/ISE-Trace.

Read & Discuss → View Source →

05.

arXiv (CS.LG) 2026-06-11 DOI: arXiv:2601.14792

Robustness of Mixtures of Experts to Feature Noise

Authors:

Dong Sun↗Rahul Nittala↗Rebekka Burkholz↗

arXiv:2601.14792v2 Announce Type: replace Abstract: Despite their practical success, it remains unclear why Mixture of Experts (MoE) models can outperform dense networks beyond sheer parameter scaling. We study an iso-parameter regime where inputs exhibit latent modular structure but are corrupted by feature noise, a proxy for noisy internal activations. We show that sparse expert activation acts as a noise filter: compared to a dense estimator, MoEs achieve lower generalization error under feature noise, improved robustness to perturbations, and faster convergence speed. Empirical results on synthetic data and real-world language tasks corroborate the theoretical insights, demonstrating consistent robustness and efficiency gains from sparse modular computation.

Read & Discuss → View Source →

06.

arXiv (CS.LG) 2026-06-12 DOI: arXiv:2606.13191

The Geometry of Phase Transitions in Generative Dynamics via Projection Caustics

Authors:

Ryosuke Sakamoto↗Kotaro Sakamoto↗

arXiv:2606.13191v1 Announce Type: new Abstract: Continuous-state generative samplers, including diffusion and flow-matching models, evolve through continuous reverse-time dynamics, yet their samples often undergo abrupt qualitative changes: trajectories commit to modes, semantic alternatives collapse, and small perturbations in narrow time windows can produce large downstream effects. This paper develops a geometric account of such phase-transition-like behaviour. We view denoising as gradient descent on a free energy landscape and show that sharp transitions arise near projection caustics, where the nearest-point projection onto the data support ceases to be unique. Motivated by this perspective, we introduce the Critical Boundary Detector (CBD), as practical diagnostics for score-direction instability. Across toy models, standard diffusion models, and latent text-to-image diffusion models, CBD localises mode commitment, predicts intervention-sensitive windows, and supports targeted control in geometrically sensitive regions. Our results connect geometry of data and dynamics of diffusion generation.

Read & Discuss → View Source →

07.

arXiv (CS.AI) 2026-06-18 DOI: arXiv:2606.19319

Data Intelligence Agents: Interpreting, Modeling, and Querying Enterprise Data via Autonomous Coding Agents

Authors:

Anoushka Vyas↗Aarushi Dhanuka↗Sina Khoshfetrat Pakazad↗Henrik Ohlsson↗

arXiv:2606.19319v1 Announce Type: cross Abstract: Production data integration is bottlenecked by repeated, lossy handoffs between data owners, engineers, and analysts who must collaboratively discover, structure, and query enterprise data. We present Data Intelligence Agents (DIA), a system of three agents (Data Interpreter, Schema Creator, and Query Generator) that compresses this workflow by treating autonomous coding agents (ACAs) as a first-class abstraction: rather than emitting text, the agents generate, execute, validate, and repair concrete artifacts, draw on a shared memory for experience reuse, and surface each for review by domain experts. DIA is deployed in production for enterprise customers. We study the Query Generator in depth and evaluate it in fully autonomous mode across seven SQL benchmarks spanning four task categories and four dialects. It matches or surpasses the best published results on all seven, demonstrating that an architecture grounded in execution, built on ACAs and a shared memory, generalizes across the data intelligence workload with adaptation confined to natural-language instructions.

Read & Discuss → View Source →

08.

arXiv (CS.LG) 2026-06-11 DOI: arXiv:2506.08473

AsFT: Anchoring Safety During LLM Fine-Tuning Within Narrow Safety Basin

Authors:

Shuo Yang↗Qihui Zhang↗Yuyang Liu↗Xiaojun Jia↗Kunpeng Ning↗Jiayu Yao↗Jigang Wang↗Hailiang Dai↗Yibing Song↗Li Yuan↗

arXiv:2506.08473v4 Announce Type: replace Abstract: Fine-tuning large language models (LLMs) improves performance but introduces critical safety vulnerabilities: even minimal harmful data can severely compromise safety measures. We observe that perturbations orthogonal to the alignment direction - defined by weight differences between aligned (safe) and unaligned models - rapidly compromise model safety. In contrast, updates along the alignment direction largely preserve it, revealing the parameter space as a "narrow safety basin". To address this, we propose AsFT (Anchoring Safety in Fine-Tuning) to maintain safety by explicitly constraining update directions during fine-tuning. By penalizing updates orthogonal to the alignment direction, AsFT effectively constrains the model within the "narrow safety basin," thus preserving its inherent safety. Extensive experiments on multiple datasets and models show that AsFT reduces harmful behaviors by up to 7.60%, improves task performance by 3.44%, and consistently outperforms existing methods across multiple tasks.

Read & Discuss → View Source →

09.

medRxiv (Medicine) 2026-06-12 DOI: HASH:217aa3549787460a5cc14ac360ee61ff

Genome-wide association and multi-omics functional screens reveal the genetic architecture of foveal development

Authors:

Hunt↗Patil↗Syed↗Yoon↗H.-J↗Yang↗Rodwell↗Tu↗Maconachie↗G. D↗Coley↗Lirio↗…

Foveal hypoplasia causes visual impairment across congenital eye disorders, yet the genetic programmes governing foveal development remain poorly characterised and no tractable model exists for foveal disease. In the first genome-wide association study of foveal hypoplasia, we identified 42 sentinel variants mapping to 54 effector genes supported by >= 2 criteria from a variant-to-gene framework incorporating developmental multi-omics. Disruption of six effector genes using mutant lines and CRISPR knockouts in the zebrafish high acuity zone recapitulates structural, functional, and ultrastructural hallmarks of foveal hypoplasia, establishing the first vertebrate disease model. Integration with human foetal single-cell and spatial transcriptomics reveals two temporal waves of effector gene expression and identifies Muller glia as critical mediators of foveal patterning. Phenome-wide analyses reveal foveal variants are pleiotropic with refractive, lenticular, and metabolic traits, connecting foveal development to anterior segment and systemic disease biology. These findings should inform mechanistic studies of macular disease.

Read & Discuss → View Source →

10.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2511.14007

Can Artificial Intelligence Accelerate Technological Progress? Researchers' Perspectives on AI in Manufacturing and Materials Science

Authors:

John P. Nelson↗Olajide Olugbade↗Philip Shapira↗Justin B. Biddle↗

arXiv:2511.14007v3 Announce Type: replace-cross Abstract: Artificial intelligence (AI) raises expectations of substantial increases in rates of technological progress, but such anticipations are often not connected to detailed ground-level studies of AI use in innovation processes. Accordingly, it remains unclear how and to what extent AI can accelerate innovation. To help to fill this gap, we explore and assess results from 32 interviews with U.S.-based academic manufacturing and materials sciences researchers experienced with AI and machine learning (ML) techniques. We found that AI was primarily used for modeling of materials and manufacturing processes, facilitating cheaper and more rapid search of design spaces for materials and manufacturing processes alike. Benefits included cost, time, and computation savings in technology development. However, AI/ML tools were unreliable outside design spaces for which dense data were already available; they required skilled and judicious application in tandem with older research techniques; and concerns were raised about the potential to detrimentally circumvent opportunities for disruptive theoretical advancement. Based on these results, we suggest there is reason for optimism about acceleration in sustaining innovations through the use of AI/ML; but that support for conventional empirical, computational, and theoretical research is required to maintain the likelihood of further disruptive advances in manufacturing and materials.

Read & Discuss → View Source →

11.

medRxiv (Medicine) 2026-06-11 DOI: HASH:1562585bf27424431b9d1ee0793939b3

Population-scale detection of methylation outliers from long-read genome sequencing

Authors:

Jensen↗T. D↗Kaur↗Bonner↗D. E↗Nguyen↗Reuter↗C. M↗Undiagnosed Diseases Network↗Genomics Research to Elucidate the Genetics of Rare Diseases Consortium↗Ashley↗E. A↗…

Background: Aberrant DNA methylation can mediate the functional effects of rare genetic variation and contribute to imprinting disorders, repeat expansion diseases, and other pathogenic regulatory mechanisms. Long-read sequencing technologies now enable genome-wide detection of CpG methylation alongside genetic variation from a single assay. However, methods for systematic identification and interpretation of methylation outliers from long-read sequencing data remain limited. Methods: We developed METAFORA, a computational workflow for detecting methylation outlier regions from PacBio and Oxford Nanopore long-read sequencing data. METAFORA constructs population-level methylation references, segments the genome into correlated CpG blocks, infers technical and biological sources of variation through hidden factor estimation, models uncertainty due to variable depth sequencing, and computes covariate-adjusted methylation outlier scores for individual samples. We applied METAFORA across large long-read sequencing cohorts and integrated methylation outliers with multi-omic data. METAFORA is implemented as a snakemake workflow available at https://github.com/tjense25/METAFORA. Results: METAFORA identified methylation outlier regions associated with rare structural variants, tandem repeat expansions, and imprinting abnormalities. We found outlier regions were enriched for molecular outliers across transcriptomic and chromatin accessibility datasets, supporting their functional relevance in gene regulation. In a representative case, METAFORA identified an imprinting defect affecting the GNAS locus associated with an STX16 deletion. Conclusions: METAFORA enables scalable detection and interpretation of methylation outliers from long-read sequencing data and provides a framework for integrating epigenetic outliers with genomic and multi-omic analyses. These approaches may improve interpretation of rare regulatory variation and support discovery of clinically relevant epigenetic abnormalities in genomic medicine.

Read & Discuss → View Source →

12.

arXiv (CS.LG) 2026-06-17 DOI: arXiv:2601.22495

Gradual Fine-Tuning for Flow Matching Models

Authors:

Gudrun Thorkelsdottir↗Arindam Banerjee↗

arXiv:2601.22495v2 Announce Type: replace Abstract: Fine-tuning flow matching models is a central challenge in settings with limited data, evolving distributions, or computational constraints. While recent work has produced significant advances, particularly in the area of reward-based fine-tuning, current methods fail to demonstrate both theoretical correctness as well as strong empirical results in terms of stability, efficiency, and diversity preservation. In this work, we propose Gradual Fine-Tuning (GFT), a simple yet principled annealing-based framework for fine-tuning flow generative models when only samples from the target distribution are available. For stochastic flows, GFT defines a temperature-controlled sequence of intermediate objectives that smoothly interpolate between the pretrained and target drifts, provably approaching the true target as the temperature approaches zero. We analytically demonstrate that sample generation after GFT can be made substantially more efficient with the use of arbitrary (e.g., optimal transport) couplings, as well as by utilizing few-step inference methods. Empirically, GFT significantly improves convergence stability, while maintaining or improving generation quality, training speed, and generation diversity compared to other fine-tuning methods. Our results position GFT as a simple yet theoretically grounded and practically effective alternative for scalable adaptation of flow matching models under distribution shift.

Read & Discuss → View Source →

13.

arXiv (CS.CL) 2026-06-11 DOI: arXiv:2606.12411

Context-Driven Incremental Compression for Multi-Turn Dialogue Generation

Authors:

Yeongseo Jung↗Jaehyeok Kim↗Eunseo Jung↗Jiachuan Wang↗Yongqi Zhang↗Ka Chun Cheung↗Simon See↗Lei Chen↗

Modern conversational agents condition on an ever-growing dialogue history at each turn, incurring redundant attention and encoding costs that grow with conversation length. Naive truncation or summarization degrades fidelity, while existing context compressors lack cross-turn memory sharing or revision, causing information loss and compounding errors in long dialogues. We revisit the context compression under conversational dynamics and empirically present its fragility. To improve both efficiency and robustness, we introduce Context-Driven Incremental Compression (C-DIC), which treats a conversation as interleaved contextual threads and stores revisable per-thread compression states in a single, compact dialogue memory. At each turn, a lightweight retrieve, revise, and write-back loop shares information across turns and updates stale memories, stabilizing long-horizon behavior. In addition, we adapt truncated backpropagation-through-time (TBPTT) to our multi-turn setting, learning cross-turn dependencies without full-history backpropagation. Extensive experiments on long-form dialogue benchmarks demonstrate superior performance and efficiency of C-DIC; notably, C-DIC shows stable inference latency and perplexity over hundreds of dialogue turns, supporting a scalable path to high-quality dialogue modeling.

Read & Discuss → View Source →

14.

medRxiv (Medicine) 2026-06-18 DOI: HASH:80e3fdadb41d206824a0b1d66e443a1d

Instantaneous-Frequency EEG Microstate Dynamics Stratify Motor Subtypes in Parkinson's Disease

Authors:

Nobukawa↗Watanabe↗

Parkinson's disease (PD) is clinically heterogeneous, yet objective electrophysiological markers of its postural-instability/gait-difficulty (PIGD) and tremor-dominant (TD) motor subtypes are lacking. We tested whether the temporal dynamics of instantaneous-frequency (IF) microstates in resting-state electroencephalography (EEG) distinguish these subtypes from each other and from healthy controls (HC). In a publicly available cohort (OpenNeuro ds007526) comprising 28 HC and 97 PD patients classified as PIGD (n=50) or TD (n=47), the spatial distribution of the IF was reduced by principal component analysis and modeled with a Gaussian hidden Markov model, yielding three recurrent microstates. Per-participant mean dwell time, occupancy, and state-transition probabilities were compared across the three groups and, within PD, correlated with clinical scores. We found that the dynamics of one microstate varied systematically across groups: its dwell time, occupancy, and self-transition probability increased monotonically from HC through TD to PIGD, while outgoing transitions decreased, so that the state became an increasingly persistent attractor. For dwell time, all three pairwise contrasts survived correction (HC versus PIGD, Hedges' g=1.06; HC versus TD, g=0.59; PIGD versus TD, g=0.40). None of the dynamic indices was associated with clinical severity, disease duration, or medication dose within PD. IF-microstate dynamics thus stratify the PD motor subtypes along a graded continuum without tracking continuous disease severity. The approach offers a candidate objective EEG marker for motor-subtype stratification, complementing spectral characterizations of PD.

Read & Discuss → View Source →

15.

arXiv (CS.CL) 2026-06-11 DOI: arXiv:2601.22025

When Generic Prompt Improvements Hurt: Evaluation-Driven Iteration for LLM Applications

Authors:

Daniel Commey↗

Evaluating Large Language Model (LLM) applications differs from conventional software testing because outputs are probabilistic, semantically variable, and sensitive to prompt and model changes. This technical report proposes the Minimum Viable Evaluation Suite (MVES), an audit-oriented structure for application-level LLM evaluation. MVES links application categories to failure modes, metrics, required artifacts, and validation evidence across general LLM applications, retrieval-augmented systems, and agentic workflows. We pair the framework with a reproducible local evaluation harness covering structured extraction, RAG citation/content-compliance, and instruction-following checks. Using Ollama with Llama 3 8B Instruct and Qwen 2.5 7B Instruct, we evaluate five prompt conditions over expanded 30-case-per-suite ablations. The results show that, in the tested local conditions, generic prompt additions do not produce monotonic improvements: stronger output-contract prompts improve strict extraction for both models, while RAG citation/content-compliance declines under some generic-rule conditions. The largest observed decline occurs for Qwen 2.5 on RAG when generic rules are appended to the user prompt, from 26/30 to 9/30. These findings support evaluation-driven prompt iteration: prompt changes should be treated as potential regression risks and tested against task-specific suites before deployment. The accompanying repository contains the test suites, prompt variants, evaluation harness, raw result logs, and scripts needed to reproduce the reported local ablations.

Read & Discuss → View Source →

16.

arXiv (CS.CL) 2026-06-12 DOI: arXiv:2606.07515

How reliable are LLMs when it comes to playing dice?

Authors:

Luca Avena↗Gianmarco Bet↗Bernardo Busoni↗

We investigate the probabilistic reasoning capabilities of large language models through a controlled benchmarking study on discrete probability problems. We constructed two datasets, respectively a set of standard exercises and a set of counterintuitive exercises, designed to trigger heuristic reasoning, and evaluated 8 state-of-the-art models, each tested with and without Chain-of-Thought prompting. Models achieve an average accuracy of 0.96 on standard problems but only 0.59 on counterintuitive ones. We further provide empirical evidence of token bias: performance drops by over 20% when canonical formulations are replaced by disguised variants. Embedding misleading suggestions in the prompt reduces performance by up to 34%, with no model proving immune. Taken together, the reported findings suggest that current LLMs are not yet genuine probabilistic reasoners, despite their success in advanced mathematical problems.

Read & Discuss → View Source →

17.

arXiv (CS.CV) 2026-06-11 DOI: arXiv:2606.11719

Ouroboros-Spatial: Closing the Data-Model Loop for Spatial Reasoning

Authors:

Enhan Zhao↗Wei Wu↗Yuanrui Zhang↗Xueliang Zhao↗Di He↗

Spatial reasoning remains a persistent challenge for multimodal large language models (MLLMs). Existing approaches largely rely on large-scale, statically curated datasets, where all training samples are treated uniformly regardless of the model's evolving capabilities. This static paradigm is inherently data-inefficient: training capacity is often spent on samples that are either trivial or overly difficult for the model at its current stage. To address this limitation, we propose Ouroboros-Spatial, a self-evolving training framework in which the model plays dual roles as a proposer and a solver. In each iteration, a frozen proposer generates spatial question-answer (QA) pairs from 3D scene metadata and raw video frames, together with executable code for deriving reliable ground truth. A learnable solver is then fine-tuned on the accepted samples, and its per-sample prediction confidence is used as a difficulty signal. This signal is fed back to the proposer in the next iteration, guiding it to generate questions better matched to the solver's current capabilities. Through this closed-loop design, the training distribution co-evolves with model ability, reducing redundant trivial examples while filtering out ambiguous or uninformative samples with limited learning value. Across six spatial reasoning benchmarks, Ouroboros-Spatial substantially improves Qwen3-VL-4B and Qwen3-VL-8B while using an order of magnitude fewer training examples than recent large-scale curated datasets. On VSI-Bench, it yields absolute gains of 9.9 and 6.8 points for the 4B and 8B models, respectively, enabling both to outperform a wide range of strong open-source and proprietary baselines.

Read & Discuss → View Source →

18.

arXiv (CS.CV) 2026-06-16 DOI: arXiv:2606.14773

Double-Helix Vision (DH-V2): A Geometry-Based Visual Sampler for Bandwidth-Constrained Perception

Authors:

Jinwen Wen↗

We present Double-Helix Vision (DH), a geometry-based visual sampler that compresses 2D images into compact 1D signals using paired golden-ratio-inspired spiral trajectories. Rather than processing every pixel uniformly, DH employs two phase-shifted helices (Alpha and Beta, offset by 180 degrees) to sample the image with biologically-inspired foveation: high density at the center, sparse coverage at the periphery. At 4K resolution, DH achieves a 1,433x compression ratio (99.93% reduction) while preserving the geometric structure of the scene. The full perception pipeline – including spatial mapping, temporal collision detection, and intra-frame structural disparity estimation – runs in 0.52 ms at 1080p on CPU-only hardware, with no neural network dependencies. On CIFAR-10 at extreme sampling budgets (K=128 points per helix), DH achieves a +6.03% accuracy gain over uniform random sampling. A JSON-serializable Robotics API is provided, delivering sub-millisecond spatial perception reports in 2.7 KB packets. Code and benchmarks are available under the MIT License.

Read & Discuss → View Source →

19.

arXiv (CS.AI) 2026-06-12 DOI: arXiv:2412.08610

Competition and Diversity in Generative AI

Authors:

Manish Raghavan↗

arXiv:2412.08610v3 Announce Type: replace-cross Abstract: Recent evidence, both in the lab and in the wild, suggests that the use of generative artificial intelligence reduces the diversity of content produced. The use of the same or similar AI models appears to lead to more homogeneous behavior. Our work begins with the observation that there is a force pushing in the opposite direction: competition. When producers compete with one another (e.g., for customers or attention), they are incentivized to create novel or unique content. We explore the impact competition has on both content diversity and overall social welfare. Through a formal game-theoretic model, we show that competitive markets select for diverse AI models, mitigating monoculture. We further show that a generative AI model that performs well in isolation (i.e., according to a benchmark) may fail to provide value in a competitive market. Our results highlight the importance of evaluating generative AI models across the breadth of their output distributions, particularly when they will be deployed in competitive environments. We validate our results empirically by using language models to play Scattergories, a word game in which players are rewarded for answers that are both correct and unique. Overall, our results suggest that homogenization due to generative AI is unlikely to persist in competitive markets, and instead, competition in downstream markets may drive diversification in AI model development.

Read & Discuss → View Source →

20.

arXiv (CS.CL) 2026-06-15 DOI: arXiv:2606.14460

A Computational Audit of Demographic Association Encoding in ClinicalBERT Language Predictions

Authors:

Kehinde Temitayo Soetan↗

Transformer-based clinical language models are increasingly integrated into high-stakes clinical decision support pipelines, yet the computational mechanisms through which demographic associations encoded in medical documentation propagate into model probability distributions remain empirically underspecified. We present a systematic computational audit of representational bias in ClinicalBERT (Alsentzer et al., 2019), a BERT-based model pretrained on MIMIC-III discharge summaries, employing two complementary probing methodologies: Log Probability Bias Analysis (LPBA), which quantifies demographic descriptor-induced shifts in masked token probability distributions across behavioral and evaluative semantic categories, and Masked Language Model-based analysis (MLM), which probes internal representational structure for demographic agency attribution encoding across 98 real clinical sentence templates and eight intersectional race-gender combinations. Corpus frequency analysis operationalizes the distinction between statistical disparity and bias amplification by benchmarking model outputs against empirical term frequencies in the MIMIC-III training corpus. Of 32 statistically significant findings, 65.6% contradict observed corpus distributions, rising to 80% for Black patients and 87.5% for agency attribution under MLM probing, providing direct empirical evidence that representational bias in ClinicalBERT operates predominantly through model-internal amplification rather than training data inheritance. Keywords: natural language processing, clinical documentation, algorithmic auditing, representational bias, health equity 1

Read & Discuss → View Source →

21.

arXiv (CS.LG) 2026-06-17 DOI: arXiv:2606.09770

Discovering Functionally Selective Brain Regions with a Deep Topographic Multimodal Model

Authors:

Badr AlKhamissi↗Johannes Mehrer↗Lara Marinov↗Ahmed Abdelaal↗Abdulkadir Gokce↗Martin Schrimpf↗

arXiv:2606.09770v2 Announce Type: replace-cross Abstract: Nearby neurons in cortex share similar response profiles, producing systematic spatial organization across sensory and cognitive systems. Recent topographic models reproduce aspects of this structure but remain unimodal and spatially constrain each layer separately, yielding fragmented maps that capture neither the contiguity of cortical processing streams nor their integration across modalities. We introduce Topo-Omni, a topographic multimodal model in which visual, auditory, and language/cognitive processing share a single contiguous in-silico sheet. Built by fine-tuning a pretrained foundation model with a spatial smoothness objective, this architecture develops clusters across modalities that are consistent with human neuroimaging, from sensory to cognitive systems. Driving or suppressing a cluster selectively biases or impairs perception, paralleling human intervention studies. Finally, we use our model to screen for novel clusters in-silico and discover new natural landscape and animal networks which we validate in human data. A single spatial principle thus organizes representations across modalities and processing stages, yielding testable hypotheses about cortical organization.

Read & Discuss → View Source →

22.

arXiv (CS.CV) 2026-06-12 DOI: arXiv:2606.13061

LaME: Learning to Think in Latent Space for Multimodal Embedding via Information Bottleneck

Authors:

Peixi Wu↗Biao Yang↗Feipeng Ma↗Bosong Chai↗Bo Lin↗Wei Yuan↗Fan Yang↗Tingting Gao↗Hebei Li↗Xiaoyan Sun↗

Reasoning-driven universal multimodal embedding has advanced rapidly by introducing Chain-of-Thought (CoT) reasoning into the embedding pipeline. Despite the strong performance across both general and complex tasks, this paradigm suffers from two core limitations: (i) autoregressive CoT reasoning incurs high computational cost, making it impractical for low-latency retrieval; and (ii) embedding performance is heavily coupled with CoT annotation quality, making large-scale training unreliable. These raise fundamental questions: Is textual CoT the optimal form of reasoning for embedding, and can effective embedding reasoning be accomplished in latent space? To this end, we propose LaME (Latent Reasoning Multimodal Embedding), which formulates embedding-oriented latent reasoning as a weakly supervised information bottleneck. LaME employs K learnable reason tokens as a fixed-capacity bottleneck, completing all reasoning within a single forward pass. The two weak supervision signals structurally decouple contrastive from autoregressive objectives and eliminate dependence on CoT annotations, while a two-stage training pipeline ensures stable convergence. Experiments on MMEB-v2 and MRMR show that LaME achieves competitive performance, surpassing some explicit CoT-based models, while delivering 60x faster inference than explicit CoT methods and 2x faster than latent baselines with throughput comparable to discriminative embedding models. Code will be released.

Read & Discuss → View Source →

23.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2606.16475

AI systems out-persuade expert humans

Authors:

Kobi Hackenburg↗Caroline Wagner↗Luke Hewitt↗Ben M. Tappin↗Ed Saunders↗Hannah Rose Kirk↗Helen Margetts↗Christopher Summerfield↗

arXiv:2606.16475v1 Announce Type: cross Abstract: Many societal decisions are settled by contests of persuasion. Conversational AI is a powerful new entrant in these contests, but whether it can out-persuade skilled and highly incentivized humans has remained unclear. Here, in a series of four preregistered experiments (n = 18,978 conversations from 6,923 people), we pitted AI systems against a range of human persuaders, including laypeople, winners of a separately preregistered four-round online persuasion tournament, professional canvassers, and world championship debaters. We found that AI systems were reliably more persuasive than expert humans, even when expert humans chose their issues, researched in advance, underwent hours of live, structured practice, and were incentivized with {\pounds}1,000 cash bonuses. In a follow-up study, AI's advantage persisted after experts received a coaching tool that let them practice against the AI that beat them, review their performance history, and see what AI would have said at key moments. We found converging evidence that AI's advantage stemmed from rapidly deploying larger quantities of information: after coaching, expert humans could tie an AI constrained to respond at human speeds and with human-length messages. In a final study, we show that AI's advantage extends to consequential real-world behavior: AI was nearly 3x more effective than professional canvassers from a UK fundraising firm at raising real-money donations to Save the Children. Together, these results establish that frontier AI systems out-persuade expert humans in conversation, with significant implications for political communication.

Read & Discuss → View Source →

24.

arXiv (CS.LG) 2026-06-12 DOI: arXiv:2606.13657

Dense Supervision, Sparse Updates: On the Sparsity and Geometry of On-Policy Distillation

Authors:

Guo Yu↗Wenlin Liu↗Yulan Hu↗Hao-Xuan Ma↗Jun-Peng Jiang↗Han-Jia Ye↗

arXiv:2606.13657v1 Announce Type: new Abstract: On-policy distillation (\textsc{OPD}) has recently become a prominent post-training recipe as it combines two desirable ingredients: on-policy student trajectories and dense teacher supervision, yet how this hybrid changes a model's parameters remains unclear. Across several language and vision-language model pairs and use cases, our analysis yields two main findings. On sparsity, \textsc{OPD}-style updates are small and coordinate-sparse. They are distributed across layers and are usually FFN-heavy. This sparse structure is operationally useful: training only the discovered subnetwork recovers nearly the same performance as full \textsc{OPD}. However, the sparsity-inducing SGD optimizer underperforms AdamW in our optimizer ablation, likely because dense teacher supervision preserves heterogeneous coordinate-wise gradient scales where AdamW's adaptive scaling remains useful. On geometry, the updates are numerically full-rank but spectrally concentrated; they lie mostly away from the principal singular subspaces of the source weights and fall disproportionately on coordinates where the source weights are close to zero. These findings suggest that dense teacher supervision does not turn \textsc{OPD} into ordinary dense parameter rewriting; instead, \textsc{OPD} retains important geometric signatures of on-policy post-training.

Read & Discuss → View Source →

25.

arXiv (CS.LG) 2026-06-19 DOI: arXiv:2606.19624

MassSpecGym in the Wild: Uncovering and Correcting Evaluation Pitfalls in AI-Driven Molecule Discovery

Authors:

Hongxuan Liu↗Roman Bushuiev↗Ivy Lightheart↗Mrunali Manjrekar↗Anton Bushuiev↗Magdalena Lederbauer↗Filip Jozefov↗Yinkai Wang↗Soha Hassoun↗Josef Sivic↗James Taylor↗Runzhong Wang↗…

arXiv:2606.19624v1 Announce Type: new Abstract: Reliable benchmarking is critical for developing machine learning models for tandem mass spectrometry (MS/MS) based molecule discovery. Subtle issues in experimental design and model evaluation procedures can degrade the trustworthiness of such benchmarks and lead to erroneous conclusions. We conduct a thorough review of model evaluation issues in the recent MS/MS machine learning literature, using the standard MassSpecGym benchmark suite as a case study to illustrate the impact of these issues. We find evaluation issues in at least 17 of 26 papers reporting MassSpecGym benchmark results in the first year of its adoption. We isolate three classes of failures: (i) data leakage, (ii) shortcut learning, and (iii) implementation bugs and metric divergence. Through extensive experimentation and code replication, we quantify the impact of these issues and show how they corrupt the evaluation standards MassSpecGym was designed to enforce. We distill our findings into recommendations generalizable to MS/MS challenges, benchmarks, and custom evaluation setups. We also release MassSpecGym v1.5, an implementation of our recommendations in the MassSpecGym benchmarking suite which addresses the failure modes identified in this audit. MassSpecGym v1.5 is publicly available at https://github.com/pluskal-lab/MassSpecGym.

Read & Discuss → View Source →