Arthropod monitoring at scale begins with metabarcoding of bulk samples: trap collections of hundreds to thousands of specimens processed as one unit, extraction of DNA from the bulked specimens, then sequencing of the DNA from all specimens together. Metabarcoding reveals which taxa such a sample contains, but due to factors such as differing DNA amplification rates and body sizes, its read counts do not neatly correspond to how abundant the different taxa are relative to one another. This lack of relative abundance limits the data's utility for the multitude of ecological analyses that depend on it. We propose BIOTRAM: a neural network that estimates per-taxon specimen counts by dividing the observed read counts by a learned read yield per specimen, which it factors into the DNA each specimen contributes and how efficiently that DNA is amplified. On a paired dataset of 1,188 bottles (800 k specimens) processed both by metabarcoding and by comprehensive individual barcoding for ground-truthing, BIOTRAM reduces the Jensen-Shannon divergence between the estimated and the true composition from 0.3586 for raw read proportions (the usual proxy for abundance) to 0.1200. Trained on the same objective and inputs as four generic deep architectures, all with tuned loss weights, it reaches a count error 3.2% below that of the strongest of them and the lowest composition divergence. It also generalizes to out-of-domain data better, beating all baselines on bottles from unseen regions, later collection dates and unseen sequencing batches, and transferring to data from an unseen laboratory. Structuring the mapping from reads to counts around the steps of the experimental pipeline thus yields more accurate abundance estimates than leaving that mapping unconstrained.
Point cloud denoising aims to recover clean geometry from noisy 3D observations while preserving both fine surface details and the underlying spatial distribution of the points. Many learning-based methods adopt a two-stage pipeline that first extracts point-wise features from the noisy input and subsequently predicts point-wise displacements via simple regressions. However, these approaches often lack robust feature guidance and distribution-aware geometric refinement, causing them to fail at maintaining optimal point uniformity and geometric quality. To address these limitations, we propose PointNDF, a denoising framework that combines patch-level geometric context with local displacement prediction. Specifically, a Point Transformer V3 (PTv3) encoder aggregates multiscale geometric information into a global patch descriptor. Rather than directly regressing an unconstrained displacement vector, a Neural Displacement Field (NDF) fuses this global patch descriptor with per-point neighborhood features. It then predicts each displacement through bounded-vector and scale factor branches, thereby achieving a superior, more uniform point distribution. Three cascaded NDF stages propagate local features and progressively refine the point positions. Experiments on PU-Net and ModelNet10 demonstrate competitive denoising accuracy and favorable inference efficiency. The source code is publicly available at https://github.com/peridous/PointNDF.
Low-textured sketch images are widely used in scientific applications, including wildlife conservation, archaeological illustration, and forensic composites. Learning from and retrieving such images is challenging because they lack detailed surface textures and visual variations commonly exploited by modern deep learning models. This paper proposes Augmentation with Reinforcement Transformation (ART) to fine-tune pretrained models to learn effective representations for accurate sketch image retrieval. Our key observation is that sketches are particularly sensitive to image transformations, such as rotation, flipping, zooming, and stretching. While some transformations preserve their structural integrity, others may introduce distortions that hinder representation learning. Instead of randomly choosing transformations to construct fine-tuning views, ART formulates augmentation selection as a multi-armed bandit (MAB) problem, where transformations are treated as arms and their effectiveness is continuously evaluated through rewards. This enables ART to adaptively construct reward-guided view banks before self-supervised fine-tuning; the subsequent representation loss does not feed back to ART. On Florida manatee sketches provided by Mote Marine Laboratory, ART achieves 71.40% average Top-1 accuracy for transformed-scar retrieval, compared with 68.83% for random augmentation selection, and 55.84% for location-aware sketch retrieval, compared with 18.18% for frozen CLIP.
Contrastive pretraining has advanced image-text understanding, yet image, video, and audio encoders are still trained independently, with cross-modal alignment realized mainly through post-hoc binding to a frozen anchor space. We present Omni-Encoder, a general multimodal encoder that processes image, video, audio, and audio-visual inputs within a single SigLIP-2 Vision Transformer with fully shared parameters. Unlike anchor-centric binding or per-modality adapters, all modalities are optimized jointly end-to-end, and the framework is organized from input to training. A modality-native input stage first maps each signal into the shared embedding space, including a 1D-convolutional audio tokenizer that converts mel-spectrograms into tokens aligned with visual patches. A multimodal rotary position embedding parameterized by absolute timestamps then places visual frames and audio segments in a unified spatiotemporal coordinate system. Finally, alternating-modality training interleaves image, video, audio, and temporally aligned audio-visual batches and accumulates their gradients into one update, which we find central to stable joint optimization. Omni-Encoder achieves competitive results on 16 benchmarks across all four modalities with one shared parameter set, and joint training improves each modality over its separately trained counterpart. Code and models will be publicly released.
The hand localization problem has been a longstanding focus due to its many applications. The task involves modeling the hand as a singular point and determining its position within a defined coordinate system. However, due to data modality limitations, existing hand localization technologies face several challenges. For example, vision-based localization raises privacy concerns, while wearable-based methods compromise user comfort. In this paper, we introduce mmHand, a new device-free, privacy-preserving dynamic hand localization system with pixel-level accuracy, using a single commodity mmWave device. We first propose a mmImage generation tool to fully extract spatial information from raw mmWave data and introduce a novel 2D image-format representation of mmWave data. Next, we design a framework that provides a new quality evaluation method and pixel space labeling for the mmWave data. Finally, we present a cross-modality spatial feature-enhanced model with high spatial feature extraction capabilities, which can accurately localize hand positions at the pixel level in the mmWave radar U-V pixel coordinate system. We evaluate the system with experiments on 12 subjects in three scenarios, and the results across four metrics demonstrate the effectiveness of our hand localization system.
In Bangladesh, much localized misinformation spreads as photocards: single-image news summaries that imitate the branding of well-known news organizations. Because the misleading message lives in the pixels rather than in machine-readable text, text-based fact-checking tools cannot see it. We recast photocard fake-news detection as visual image forgery detection. We build a dataset of 969 authentic and 1,077 fabricated Bangla photocards scraped from public Facebook pages: authentic cards from the verified pages of seventeen national television broadcasters, fabricated ones from pseudo-broadcaster pages, anonymous profiles, and public groups. Sixteen photometric and morphological transformations per image grow the corpus to 32,736 samples. A fully connected ANN reaches only about 52% accuracy, its loss stuck at ln(2) ~ 0.693, showing that flattening the image destroys the spatial cues forgery detection needs. A compact, fully batch-normalized four-block CNN with 489,954 parameters, about 1,644x smaller than the ANN, is evaluated with leakage-free stratified group five-fold cross-validation, which keeps every augmented version of a card in one fold. Under this protocol the CNN reaches 87.45% +/- 0.53% pooled accuracy from scratch and 88.75% +/- 1.55% when its classifier head is warm-started from the ANN. An ImageNet-pretrained YOLOv8n-cls backbone (1.44M parameters) fine-tuned on the same folds reaches 97.36% +/- 0.42%, marking the headroom above the compact model. We report per-class precision, recall, F1, and pooled confusion matrices, diagnose and fix a one-class collapse caused by an unnormalized classifier head, and give a manual error analysis and bias-variance diagnosis showing that the compact CNNs under-fit.
Colony counting is commonly used to evaluate microbial populations in food safety testing and microbiological studies. Despite its wide application, manual counting is time-consuming and operator-dependent, and the final count often lacks a record of the objects included in the measurement. To address these limitations, this study presents AgentCount, an open-source agentic workflow for colony counting and result interpretation from agar plate images. Plate photographs and plating metadata are processed through seven agents for image quality control, plate localisation, colony detection, counting, CFU calculation, validation, and reporting. Colony detection is performed using Segment Anything Model 3 (SAM 3) with multiple text prompts and morphology-based filtering. After that, replicate statistics are calculated and a large language model (LLM)-based agent is used to generate a results narrative. Intermediate outputs, including quality scores, segmentation masks, detections, and warnings, are retained to support review of the reported values. The workflow also extends to skill-guided analysis of archived microbial population data. In a retrospective comparison with two previously published studies, we benchmarked 241 published endpoints, including all 216 mean +- SD values of the meat-analogue pathogen tables; on the 168 endpoints with a complete n=6 replicate source, 164 (97.6%) agreed within 0.01 log10 units. Overall, AgentCount demonstrates the promising potential of agentic workflows for applications in applied microbiology.
Generative AI is currently fragmented, with separate subscriptions required for text generation, image synthesis, and code assistance, leading to high costs and workflow disruptions. AI Express is a SaaS platform that consolidates these capabilities into a unified pay-as-you-go service. The platform provides a range of AI tools, including a Core Code Reviewer that evaluates GitHub repositories, a Text-to-Website generator that converts text into fully functional websites, script generation, grammar checking, data analysis, and watermark removal, all accessible through a single interface without requiring technical expertise.
Small Language Models (SLMs) are increasingly deployed on consumer-grade hardware, yet their ability to preserve information across progressively longer contexts remains insufficiently understood. Existing benchmarks primarily evaluate retrieval-oriented tasks, providing limited insight into whether successful retrieval reflects comprehensive long-context memory preservation. To address this limitation, this paper introduces Simple Retrieval-Reconstruction Memory (SRRM), a lightweight and fully reproducible benchmark that jointly evaluates Targeted Retrieval and Global Information Reconstruction. This study also proposes the Memory Preservation Ratio (MPR), a benchmark-level metric that quantifies the relationship between retrieval and reconstruction performance. SRRM was evaluated using a synthetic dataset on three Qwen2.5 models (0.5B, 1.5B, and 3B parameters) across context loads ranging from 10 to 100 factual statements. Experimental results show that reconstruction performance deteriorated substantially faster than retrieval accuracy as contextual information increased, indicating that retrieval alone is insufficient to characterize long-context memory preservation. Among the evaluated models, Qwen2.5-1.5B achieved the highest retrieval accuracy (86.7%), reconstruction performance (45.7%), and MPR (0.53), outperforming the larger Qwen2.5-3B model (72.2%, 18.5%, and 0.26, respectively). These findings demonstrate that increasing parameter count does not necessarily improve long-context memory preservation. Overall, SRRM provides a reproducible and extensible benchmark for systematically evaluating long-context memory while revealing complementary memory behaviors that remain hidden under retrieval-only evaluation frameworks.
Automated detection of machine-generated text is applied where the verdict carries a cost for the author, yet origin is a property of the production process, not an observable property of the text. The conditions under which a text is produced push it in the same direction in which a generative model is presumed to push it. This study measures the contribution of these conditions while origin is held fixed. The Russian-language corpus of 1882 documents comprises a machine part, generated by four generation channels (each backed by its own model family) across 45 tasks in three task modes, and an archival human part annotated for source regimentation level before the texts were read. The primary contrast is computed within the machine corpus: both halves of a pair are generated by the same model for the same task and differ only in task wording. Machine-likeness is measured by four operationalisations: an interpretable index with weights fixed before data collection, a trained classifier, a zero-shot metric on an open model, a judge model. The main result is disagreement between procedures: changing the task mode shifted the scores of all four, but three gave a negative shift, the judge a positive one, and none of the four intervals covers zero. The comparison plan and the specifications of procedures 2-4 were fixed after the result of procedure 1, before procedures 2-4 ran; the disagreement survived correction of a corpus defect and of the nested validation. A baseline on the source identifier alone reaches a median AUROC of 1.0000 on the thirteen group splits where it is defined, and removing emphasis markers flipped a confident machine verdict to human without changing the full text by a single character. The scores are properties of a specific measurement system and corpus: they reflect data collection, repetition, formatting, and preprocessing decisions as well as linguistic style.
Generalisability is a central question for deep neural networks, including the cross-language generalisation of speaker embeddings. This study examined whether deep neural speaker embeddings generalise across languages and how such generalisation relates to human perception and acoustic structure. Using Cantonese--English bilingual speech presented in within- and cross-language conditions, we derived similarity from 18 state-of-the-art models and compared it with human ratings and acoustic features using linear mixed models and representational similarity analysis. Embeddings exhibited cross-language generalisation that broadly paralleled human behaviour, reflecting accurate identity discrimination and sensitivity to language switching. This generalisation relied on largely shared acoustic cues with language-sensitive weighting, mirroring human patterns. Together, these findings provide converging evidence for human--machine alignment in cross-language voice similarity processing.
Cognitive Behavioral Therapy (CBT) demands more than empathic validation, requiring instead a structured formulation of the interplay among situations, automatic thoughts, emotions, and behaviors. Therapists formalize this interplay through a Cognitive Conceptualization Diagram, where maintaining longitudinal coherence necessitates continuous evidential adjudication to separate tentative hypotheses from established findings. Current dialogue systems track conversational history via retrieval or static profiles but lack the representational capacity to encode epistemic status. Consequently, provisional interpretations are often prematurely reified as established facts, inadvertently biasing downstream interventions. Addressing this limitation, CCDWiki is introduced as a plug-and-play advisor conceptualizing longitudinal therapy as evidence-grounded hypothesis adjudication. The approach encodes each clinical hypothesis as a mutable entry bound to corroborating and contradicting evidence. Across sessions, accumulating data strengthens supported entries, preserves provisional ones, and retracts contradicted assumptions. The resulting formulation distills into concise guidance for unmodified therapeutic language models. Experiments demonstrate substantial improvements in both conceptualization and intervention quality without requiring backbone retraining.
Misinformation spreads faster than professional fact-checkers can manually verify it and write articles explaining their verdicts. This creates a need to automate the production of fact-checking articles. This paper details work done by the DS@GT ARC team for CLEF 2026 CheckThat! Lab Task 3 Fact-Checking Article Generation. We seek to generate a full fact-checking article from a claim, its original verdict, and a set of scraped source documents. Our team built a four-stage pipeline that cleans noisy evidence, retrieves and clusters relevant sources, generates the article by conditioning \texttt{Llama-3.1-8B-Instruct} on the original fact-checker verdict, and recovers inline citations through deterministic post-processing. We achieved a mean score of 0.428 and ranked 3rd out of 9 teams for the CLEF 2026 CheckThat! Lab Task 3, compared to a baseline mean score of 0.272. Our code is available on GitHub at https://github.com/dsgt-arc/checkthat-2026-task3.
Legislative hearings are distinct communication events with their own human recognizable structure and logic, yet they have been analyzed as distinct phenomena beyond their transcripts. Understanding legislative hearings at a deeper level is a major step in analyzing the work and power relationships within democratic bodies. In this work, we present a novel end-to-end pipeline for parsing rhetorical structures from legislative committee hearings with the goal of improving legislative discourse analysis and democratic accountability. We also propose a rhetorical structure grammar and find that 55.21% of California state bill discussions in our dataset can be parsed with this grammar. We evaluate our pipeline with two utterance section classifiers on a random subset of over 2,000 annotated utterances corresponding to 100 hearings. We find that a logistic regression-based classifier with grammar-based output masking and utterance tag smoothing outperforms more complex models, achieving an F1 score of 52.8% against our ground truth discourse section labels.
Visual autoregressive generation spans two dominant paradigms: next-scale prediction for images and video, and next-frame prediction for video. Both decode block-by-block rather than token-by-token, yielding KV caches whose statistics diverge from those of language models. At scale, KV memory exceeds the weights and limits large-scale deployment caused by a large amount of visual tokens. Our analysis of these caches reveals three findings. First, a small set of massive-value channels carries the functional load: ablating these outlier channels collapses generation, whereas ablating a matched set of inlier channels leaves quality intact. Second, the outliers organize along two axes, feature and block, with magnitudes persistent within each cell and shifting across cells. Third, this structure arises from two independent mechanisms: projection bias and RoPE-induced scattering. Guided by these findings, we propose VAR-Q, a tuning-free KV-cache quantization framework that groups along the same two axes. The generation loop provides block boundaries for free, removing the need for outlier detection or calibration. Paired with bit-packing kernels for runtime memory reduction, VAR-Q delivers low-bit quantization across nine models spanning both paradigms, cutting KV memory by up to 78.5% with negligible quality degradation and enabling 6x larger inference batches.
This paper presents GSCV++, a lightweight pipeline for 3D {G}aussian {S}platting (GS) sequences {C}ompression with standard {V}ideo codecs. To meet the requirements of low-complexity and hardware compatibility from the industry, GSCV++ jointly improves preprocessing, 3D-to-2D mapping, and practical video compression configuration of GS compression. First, for preprocessing, energy-adaptive inter-frame spherical harmonic (SH) alternative current (AC) dimensionality reduction (EA-SHDR) is proposed to produces a compact and stable temporal SH AC feature space. It can reduce the data volume of following mapping and practical compression, as well as less complexity while eliminating redundant information. Second, for 3D-to-2D mapping, prior-based Inter-MiniPLAS (P-MiniPLAS) is designed to generate smooth 2D feature maps through prior-based weighting factor inference and small scale remapping. Compared with vanilla Parallel Linear Assignment Sorting (PLAS) and Morton scan, P-MiniPLAS ensures the generated 2D maps are more suitable for the video codec while maintaining a low level of computational complexity. Third, for practical compression, content-aware generalized compression (CA-GC) is developed to use a non-uniform bit-depth split for coordinate map generation, and a coding unit size selection is introduced for efficient compression complexity control, which fully exploits the performance of video codecs without involving normative changes. Experiments demonstrate that GSCV++ reports over 20\% in intra- and 60\% in inter-prediction rate-distortion gains compared with state-of-the-art (SOTA) methods. GSCV++ also achieves faster 2D map generation, encoding, and decoding than other SOTA methods using the same type of video codecs. Ablation studies verify the effectiveness and robustness of the proposed modules and provide insights for subsequent research.
Naive on-policy RL is often bottlenecked by the capabilities of the base model --- insufficient coverage can result in an inability to learn from certain rewards. At the same time, rewards in modern post-training systems often come from rich textual sources, e.g. judge models with a rubric of criteria. Can we utilize such structures to provide a rich directional signal that enables improving on otherwise difficult to optimize rewards? In this work, we examine a framework we refer to as targeted guidance that learns from per-turn textual feedback via an on-policy self-distillation objective. Our focus is not only on directly improving hard-to-optimize behaviors, but on how to do so throughout the training process without degrading baseline RL performance. Over a range of settings across an agentic multi-turn software engineering environment, we find success by combining targeted self-distillation with a per-criteria RL reward, and by limiting feedback to turns where the policy specifically fails. We further examine the design choices that lead to stable entropy and reduce oscillatory behavior throughout training.
Composed Image Retrieval (CIR) aims to retrieve a target image given a reference image and a modification text. Although recent approaches leveraging Multimodal Large Language Models (MLLMs) have shown significant progress, we argue that the MLLM's compositional understanding remains underutilized. This stems from directly mapping composed queries into a retrieval embedding via contrastive supervision alone, without explicitly resolving the intended visual modifications. In this work, we introduce Factorized MLLM Embeddings (FactEmbed), which decouples compositional query comprehension from building discriminative embeddings. Rather than directly projecting the composed query into a single embedding without internal reasoning, FactEmbed employs a set of factorized latents that simulate the intended visual modifications via an intermediate target imagination objective. This process encourages the latents to ground into target semantics before forming discriminative representations for retrieval. Subsequently, to propagate these factorized representations throughout the model for retrieval, we optimize a factor-level contrastive loss while distilling the decomposed representations into a deeper attention layer of the MLLM. Finally, for efficient inference, we retain the [EOS] token to establish a global-level embedding on top of these factorized latents, while we exploit the mean-pooled factorized latents to rerank a short candidate list at negligible cost, as both are produced by the same forward pass. Extensive evaluations demonstrate that FactEmbed outperforms prior works across CIR benchmarks.
We study PAC learning when each example comes with a set of at most $\ell$ correct labels and a prediction is correct if it belongs to this set. Training may reveal the full set, only whether a proposed label is correct (bandit feedback), or one correct label chosen by a demonstrator (demonstrations). Our main finding is that demonstrations can be much harder than full sets, and even than bandit feedback, both in which classes can be learned and in how many examples are needed. For finite label spaces, a generalized Natarajan dimension characterizes learnability from full sets and from bandit feedback, in both the realizable and the agnostic setting. From demonstrations, however, a class is realizably learnable if and only if the intersections of at most $\ell+1$ of its hypotheses are learnable from full sets. Already with three labels, this condition can fail for a class learnable from a single full-set example or even a single bandit answer. When the condition holds, we show that $\widetilde O(\varepsilon^{-\ell})$ demonstrations suffice, and the exponent $\ell$ cannot be improved in general, even for classes learnable from $\widetilde O(1/\varepsilon)$ full sets or bandit answers. For countable label spaces and $\ell \geq 2$, our packed dimension, which asks for many disjoint groups of at most $\ell+1$ hypotheses with no common label, characterizes full-set learnability, and demonstrations still reduce to intersections. Agnostic learning from demonstrations, already for finite label spaces, is not determined by the dimensions of the intersection class that characterize realizable learning. Finally, we show that the uniform bound $\ell$ on the number of correct labels is essential. Without this bound, it is impossible to characterize learnability by any dimension determined by finite subclasses.
High-fidelity photovoltaic (PV) module mapping requires complete instance recovery and accurate delineation. Vision foundation models offer zero-shot segmentation, but converting incomplete and inconsistent predictions across views into a complete, geometrically accurate map of individual modules remains challenging. We propose the Multi-View PV Module Mapper (MV-PVMapper), a training-free framework coupling vision foundation models with unmanned aerial vehicle (UAV) photogrammetry. First, Segment Anything Model 3 (SAM 3) generates candidates from original images using text prompts. Their contours are then transferred into object space through per-module slope correction to limit distortion from surface-model noise, and verified against representative module dimensions to guide cross-view instance selection. Finally, accepted instances return to all covering images as box prompts for SAM~3, supplementing text prompts with spatial cues for iterative segmentation, verification and fusion. On five-direction surveys of three operational rooftop PV plants at approximately 1 cm nadir ground sampling distance, two feedback iterations recover 7,710 of 7,711 reference modules with no false positives at an intersection-over-union (IoU) matching threshold of 0.5. Macro-averaged area precision and recall reach 99.00 % and 98.52 %, respectively. Averaged across sites, the aggregated Jaccard index reaches 97.55 %, compared with 60.73 % and 41.24 % for orthomosaic segmentation and multi-view pixel-voting baselines, respectively; average precision at the stricter IoU threshold of 0.95 reaches 95.67 %. Ablation studies show that module-size constraints are critical for instance separation, while slope correction and feedback to all covering views improve boundary accuracy. These results are achieved without task-specific image annotation or segmentation-model weight updates.