Brief

Researchers have developed a new method called VerifySteer to control the strictness of generative verifiers in step-wise verification processes. This technique identifies a hidden signal within the verification paragraph's hidden state that indicates the verifier's tendency to accept or reject a step. By selectively steering this signal, VerifySteer can modulate verifier strictness without requiring fine-tuning, offering a way to balance error detection and correctness certification. AI

Researchers have developed STAR-IOD, a new framework designed to improve incremental object detection in remote sensing imagery. This method addresses challenges like intra-class scale variations and missing annotations, which hinder knowledge transfer and preservation in existing detectors. STAR-IOD utilizes a Subspace-decoupled Topology Distillation module for structural knowledge transfer and a Clustering-driven Pseudo-label Generator to accurately distinguish targets from background noise. The framework also introduces two new datasets, DIOR-IOD and DOTA-IOD, and demonstrates superior performance over state-of-the-art approaches. AI

Researchers have introduced two novel open-source iris recognition algorithms, TripletIris and ArcIris, designed to lower participation barriers for the IREX X program. The paper details Python and IREX-compliant C++ implementations, enabling broader assessment of open-source solutions. Additionally, it provides open-source tools for iris segmentation and circle estimation, facilitating the development and integration of new recognition methods. AI

Researchers have developed a new metric called conditional scale entropy (CSE) to analyze how decoder-only language models process metaphors. CSE measures the breadth of computational engagement across different frequency scales within a transformer's layers. Studies using CSE revealed that metaphorical tokens consistently activate a wider range of computational scales compared to literal tokens in models ranging from 124 million to 20 billion parameters, including architectures like GPT-2, LLaMA-2, and GPT-oss. AI

Researchers have developed a new hyperdimensional computing architecture called PyVaCoAl/VaCoAl, which is built around the XOR-and-shift operation over Galois Fields. This architecture aims to fulfill Gary Marcus's three core requirements for cognitive architectures: operations over variables, recursively structured representations, and a distinction between individuals and kinds. The system demonstrates reversible variable binding, non-commutative compositional bundling for distinguishing sentence structures, and address-space separation, potentially offering a functional neural substrate that more closely aligns with Marcus's specifications than previous approaches. AI

Researchers have developed AutoScale, a novel closed-loop system designed to optimize the mixture of real and synthetic data for training autonomous driving models. This system dynamically adjusts the data mixture based on performance feedback, addressing the challenges of scene bias and inefficient data utilization in current co-training methods. AutoScale employs Graph Regularized AutoEncoder for scene representation and Cluster-aware Gradient Ascent for reweighting, demonstrating improved performance with fewer synthetic samples under budget constraints. AI

Researchers have developed Draw2Think, a new framework that enhances geometric reasoning in vision-language models by interacting with the GeoGebra constraint engine. This system uses a Propose-Draw-Verify loop to externalize hypotheses onto an executable canvas, ensuring geometric accuracy and allowing for auditable checks on both model construction and engine measurements. Draw2Think significantly improves the accuracy of geometric problem-solving and rendering scores on various benchmarks. AI

Researchers have developed LangTail, a new framework designed to improve unsupervised 3D point cloud segmentation by addressing the issue of long-tail ambiguity. This problem occurs when minor object classes are overlooked in favor of dominant ones during the segmentation process. LangTail integrates semantic knowledge from language models to create a more balanced understanding of categories, which is then used to guide the segmentation, leading to better identification of underrepresented classes. Experiments show significant improvements in mean Intersection over Union (mIoU) scores on benchmark datasets. AI

Researchers have developed a novel reference monitor designed to detect and prevent covert channels used by compromised Large Language Model (LLM) agents to leak data. The system employs a multi-stage text processing pipeline and media scrambling techniques for audio and images to eliminate hidden data transmission. It uses cryptographic attestations to distinguish legitimate media from data disguised as media, and measures residual capacity to ensure covert channels are destroyed or bounded. AI

Gregor Stocks, a software engineer, has launched the Library of Leng, a searchable database dedicated to preserving articles about the game Magic: The Gathering. The project aims to combat internet churn by archiving old usenet posts, website content, and publisher announcements that are often lost over time. Stocks developed custom tools to parse the varied and often unformatted data from the early internet, and the response from the Magic community and authors has been overwhelmingly positive. AI

Researchers have developed DiffGF, a novel framework designed to restore corrupted Landsat 7 satellite imagery from Antarctica. This method utilizes a diffusion-based approach in latent and pixel spaces, eliminating the need for external reference data, which is often unavailable or unreliable for the rapidly changing Antarctic landscape. A new dataset, SLCANT, was created to train and evaluate DiffGF, demonstrating its effectiveness in high-fidelity image restoration and its utility in downstream applications like crevasse segmentation. AI

Researchers have developed Sketch2MinSurf, a novel framework for generating editable 3D minimal surfaces from hand-drawn sketches. This approach combines vision-language guidance with geometric optimization, addressing the challenges of non-Euclidean surface representation and topological consistency. The system utilizes a spatial-topological encoding and a specialized loss function to ensure both accurate reconstruction and coherent topology, producing artifact-free, editable manifolds suitable for design workflows. AI

The Fifth Shared Task on Multilingual Coreference Resolution, held at the CODI-CRAC 2026 workshop, focused on systems that can identify mentions and cluster coreferential chains, particularly those spanning long distances across text. This year's task incorporated five new datasets and two additional languages, utilizing the CorefUD v1.4 collection which spans 19 languages. While traditional systems still outperformed, the ten participating systems, including four LLM-based approaches, showed significant promise for future advancements in the field. AI

Researchers have developed Deep Attention Reweighting (DAR), a novel post-hoc method to improve the generalization and fairness of Convolutional Neural Networks (CNNs). DAR addresses the issue of CNNs exploiting spurious correlations in datasets by using an attention-based aggregation module to selectively suppress irrelevant features. This module replaces the standard Global Average Pooling layer and is retrained alongside the classification head, outperforming existing Deep Feature Reweighting techniques. AI

Researchers have developed a novel Amplitude-Width-Area (AWA) pattern representation to analyze partial discharge (PD) pulses under switching-voltage excitation. This method maps PD pulses into visual patterns using amplitude, width, and area, enabling the distinction of six different PD source conditions. Convolutional Neural Network (CNN) models, specifically InceptionV3 and ResNet-18, achieved over 96% accuracy in classifying these sources, significantly outperforming a Random Forest baseline. AI

Researchers have introduced a new metric, $d_{\text{NTP}}$, to evaluate the effectiveness of task vectors in large language models by measuring the discrepancy in next-token probabilities between task vector-based and in-context learning inference. This metric serves as a proxy for performance, correlating negatively with downstream accuracy. Based on this, they developed the Linear Task Vector (LTV) method, which uses a closed-form linear mapping to minimize $d_{\text{NTP}}$, outperforming existing baselines by an average of 9.2% in accuracy across various benchmarks and LLMs while reducing inference latency. The study also demonstrated that task vectors extracted from larger models can improve smaller models' performance by 6.4%, indicating potential for cross-model scale transferability. AI

Researchers have developed a new system called CROWD IO to enable the efficient inference of large deep neural networks on resource-constrained Android devices. The system addresses the challenge of limited RAM on mobile phones by distributing memory pressure across multiple devices. CROWD IO employs several mechanisms, including deferred partition loading and compressed tensor transport, to manage memory usage and reduce batch latency. AI

Researchers have developed LASH, a novel framework designed to enhance the jailbreaking of large language models. LASH adaptively combines outputs from multiple existing attack methods, treating them as seed prompts. This approach leverages the complementary strengths of different attack families to improve success rates against various models and harm categories. In evaluations on the JailbreakBench dataset, LASH achieved high attack success rates with significantly fewer queries compared to state-of-the-art baselines. AI

Researchers have developed MTR-Suite, a new framework designed to improve the evaluation and creation of conversational retrieval benchmarks. This suite includes MTR-Eval, an LLM-based tool for identifying alignment gaps in existing benchmarks, and MTR-Pipeline, a multi-agent system that generates high-fidelity dialogues at a significantly reduced cost. The framework also introduces MTR-Bench, a comprehensive benchmark that simulates real-world conversational challenges like topic switching and verbosity, offering enhanced discriminative power for retrieval-augmented generation systems. AI

Researchers have developed OcclusionFormer, a new framework designed to improve image generation models by explicitly handling object occlusion. This is achieved by introducing a Z-order priority system and utilizing volume rendering to composite instances. The framework is supported by a new dataset, SA-Z, which includes detailed occlusion ordering and pixel-level annotations to train and evaluate the model's ability to manage overlapping objects. AI

Researchers have introduced TASTE, a new dataset designed to improve AI-generated graphic design by incorporating multi-dimensional preferences from professional designers. Unlike previous datasets that used single-verdict comparisons, TASTE captures evaluations across criteria like typography, color, and layout. The dataset reveals that current text-to-image models and existing evaluation metrics do not significantly outperform random chance in aligning with designer preferences, highlighting a gap in AI's understanding of design aesthetics. AI

Researchers have developed a new method called Early High-Frequency Injection (EIHF) to improve out-of-distribution (OOD) detection in computer vision models. EIHF works by injecting high-frequency information into the input data before it's processed by the first convolution layer, without altering the training objective. This approach enhances the model's ability to distinguish between in-distribution and out-of-distribution data, particularly for geometry-sensitive tasks, by reshaping feature geometry and reducing overlap in scores. Experiments on CIFAR-100 and ImageNet-100 datasets showed promising results, including improved false positive rates and area under the receiver operating characteristic curve. AI

Researchers have developed a new method called GAMR (Geometric-Aware Manifold Regularization) to improve deep neural network performance when trained on datasets with noisy labels. Unlike existing methods that passively filter data, GAMR actively synthesizes virtual outlier samples to create distinct boundaries between data manifolds. This geometric approach enhances the separation between correctly labeled and mislabeled data, leading to more robust feature representations. The technique has shown state-of-the-art results on benchmarks like CIFAR-10, particularly under challenging noise conditions, and also improves out-of-distribution detection capabilities. AI

Researchers have developed a new active learning technique called physics-based acquisition to improve the efficiency of training neural operators. This method uses the partial differential equation residual to intelligently select the most informative data samples for training. Experiments on the 1D Burgers and 2D Navier-Stokes equations demonstrate that this approach significantly reduces data requirements compared to random sampling and matches state-of-the-art data efficiency while incorporating physics into the model's understanding. AI

Researchers have developed a new method called Holistic Reliability Propagation (HRP) to improve learning with noisy labels in multimedia classification. HRP decouples the reliability of external annotations from model predictions, estimating separate weights for each. This approach uses bilevel meta-learning to produce two scalars, alpha for given labels and beta for pseudo-labels, which are then routed to different objectives. HRP has demonstrated improved accuracy over existing methods, particularly at high noise rates. AI

Researchers have developed E-ReCON, a novel compute-in-memory (CIM) macro designed for efficient AI inference on edge devices. This macro utilizes a compact ReRAM bitcell capable of performing multiplication for both conventional neural networks and spiking neural networks. The design incorporates an interleaved adder tree to reduce transistor count and power consumption, achieving high energy efficiency and low latency. AI

Researchers have introduced SCRIBE, a new diagnostic framework designed to improve automatic speech recognition (ASR) for Indic languages. Unlike traditional Word Error Rate (WER) metrics, SCRIBE categorizes errors into lexical, punctuation, numeral, and domain-entity types, offering a more nuanced evaluation. This framework, along with open-weight rich transcription models for Hindi, Malayalam, and Kannada, aims to make ASR correction more cost-effective and accurate, especially for agglutinative languages. AI

A new evaluation framework has been developed to assess the capabilities of large language models (LLMs) in analyzing social media data. This framework, comprising 470 curated questions, was applied to Twitter datasets for tasks like sentiment analysis and hate speech detection. The study found that LLM performance significantly degrades with increasing input scale, especially beyond 500 instances and for numerical tasks, highlighting architectural limitations for quantitative analysis of large text collections. AI

A new research paper highlights how symmetries in network inputs can mislead representational similarity analyses (RSMs). These symmetries can make different network configurations appear functionally equivalent, yet produce distinct RSMs that reflect different representational geometries. The study demonstrates this issue in networks trained on image data, where latent symmetries can lead to sparse, drifting codes and consequently, drifting RSMs. The findings underscore the difficulties in comparing nonlinear neural codes when functionally equivalent representations are not simply rotational. AI

Researchers have developed SymbolicLight V1, a novel spiking language model designed to achieve high activation sparsity while maintaining language quality. This model integrates binary Leaky Integrate-and-Fire spike dynamics with a continuous residual stream, featuring a unique Dual-Path SparseTCAM module that uses an aggregation path for long-range memory and a spike-gated local attention path for short-range precision. A 194M-parameter version trained on a Chinese-English corpus achieved over 89% activation sparsity, showing competitive performance against GPT-2 models. AI

Researchers have developed a new method for triangular inversion, a crucial operation in linear attention mechanisms used by advanced models like Qwen3.5/3.6 and Kimi Linear. This technique significantly improves the speed and numerical stability of this sub-routine, which is often a performance bottleneck. Experiments show up to a 4.3x speed-up on NPUs compared to existing implementations, leading to overall layer performance gains without sacrificing accuracy. AI

Researchers have developed SAVER, a novel framework designed to improve multimodal information extraction from social media posts. This system selectively uses visual evidence only when necessary, preventing computational waste and the amplification of misleading visual cues. SAVER employs a Conformal Groundability Gate to determine the relevance of images and a submodular selector to choose the most pertinent subset for analysis, ultimately enhancing accuracy while reducing processing load and latency. AI

Researchers have developed a new cryptographic protocol called Heartbeat-Bound Hierarchical Credentials (HBHC) to address the safety gap in autonomous AI agent swarms. This protocol binds credential validity to periodic liveness proofs from parent agents, enabling rapid revocation without requiring network connectivity to a central authority. Experiments with GPT-4o-mini agent swarms demonstrated a significant reduction in the 'zombie agent' window, with zero post-revocation tool calls observed even under prompt injection attacks. AI

New jobless claims in the US decreased to 209,000 for the week ending May 16, falling below analyst expectations. This decline indicates a continued trend of low lay-offs, contributing to a stable but somewhat stagnant labor market. Despite a low unemployment rate of 4.3%, the market is characterized by a 'low-hire, low-fire' dynamic, making it challenging for those out of work to find new positions. AI

Researchers have developed FedKDNAS, a novel federated learning framework that optimizes model selection and knowledge distillation for heterogeneous client devices. This approach allows each client to autonomously choose a lightweight model tailored to its specific accuracy and resource constraints. The framework then uses a hybrid objective for training, incorporating both supervised learning and knowledge distillation, and shares only predictions on a public reference set. Evaluations show FedKDNAS significantly improves accuracy under non-IID conditions, reduces CPU usage, and drastically cuts communication overhead compared to existing baselines. AI

Researchers have developed TextReg, a new regularization framework designed to address prompt distributional overfitting in large language models. This method aims to improve how prompts generalize to new data by controlling representation in text-space optimization. TextReg combines several techniques, including dual-evidence gradient purification and semantic edit regularization, to achieve better out-of-distribution performance. AI

Researchers have developed a new framework to analyze the distributional robustness of deep neural networks, a key challenge for real-world AI deployment. The framework models interactions between layer weights and activations using Bernoulli distributions, with class separation serving as a proxy for robustness. Experiments on CIFAR-10 and ImageNet demonstrate that the proposed metrics can differentiate between networks that have memorized training data and those that have not, and show that distributional shifts reduce separation. AI

Researchers have introduced Deformba, a novel vision state space model designed to overcome limitations in applying SSMs to visual tasks. Deformba addresses the challenges of fixed scanning methods and the difficulty in fusing distinct information streams by employing adaptive state fusion. This approach dynamically enhances spatial structural information while preserving the linear complexity of SSMs and enabling multi-modal fusion. AI

Researchers have developed Hyper-V2X, a novel framework utilizing hypernetworks to estimate both epistemic and aleatoric uncertainties in cooperative semantic segmentation for autonomous driving. This approach conditions a Bayesian hypernetwork on fused multi-agent features from V2X communication to generate weight distributions for stochastic Bird's-Eye-View segmentation. The method is architecture-agnostic and demonstrated on the OPV2V benchmark to provide accurate uncertainty estimates with minimal computational overhead, enhancing overall perception reliability. AI

Researchers have developed Declarative Data Services (DDS), a new architecture designed to improve how AI agents discover and compose data systems. Traditional agentic discovery methods struggle with the complexity and heterogeneity of data backends. DDS addresses this by using a layered contract system that breaks down the search into smaller, manageable sub-searches, enabling more consistent convergence on functional data stacks. AI

Researchers have developed a formal framework for cumulative mechanistic science in neural networks, treating circuit interpretation as inductive theory construction. This approach uses Causal Functional Signatures (CFS) and architectural signatures learned via inductive logic programming (ILP) to make mechanistic claims explicit and comparable. The system demonstrates improved structural separation compared to baseline methods and supports transferability across different model scales and architectures. AI

Researchers have developed DIVE, a new method for compressing high-dimensional embeddings from large language models to reduce storage and computational costs in vector search systems. Unlike previous methods that overfit with scarce labeled data, DIVE uses a self-limiting triplet loss to bound perturbations and a contrastive loss to provide dense self-supervised gradients. This approach reportedly outperforms existing compression adapters across multiple datasets and compression ratios, with an open-source implementation available. AI

Researchers have developed a new method called Deep UCSL for identifying distinct subgroups within patient populations by contrasting them with healthy controls. This approach uses a deep feature extractor to learn a representation space that isolates disease-specific factors, ignoring common variations shared with healthy individuals. The method optimizes a novel loss function through an Expectation-Maximization strategy and has shown quantitative improvements in subgroup quality on both synthetic and real medical imaging datasets. AI

Researchers have developed TimeSRL, a novel two-stage framework that leverages Large Language Models (LLMs) for generalizable time-series behavioral modeling. This approach first abstracts raw data into natural language semantic concepts, then predicts outcomes solely from these abstractions, aiming for better cross-dataset generalization. Optimized using Reinforcement Learning from Verifiable Rewards, TimeSRL demonstrates state-of-the-art performance in mental health prediction, significantly outperforming existing methods in cross-cohort generalization and transfer learning. AI

Researchers have developed a novel two-phase retrieval system designed to improve corporate credit underwriting by addressing the limitations of standard RAG pipelines. This new workflow separates candidate retrieval from utility ranking, using an adaptive controller and an LLM-as-a-Judge to prioritize passages based on analytical usefulness rather than just semantic similarity. Deployed on-premise for data governance, the system has been shown to drastically reduce document review times for analysts, from hours to minutes, by preserving structural fidelity across various document types. AI

Researchers have introduced DriveMA, a new approach for driving vision-language-action models that replaces complex natural language reasoning with simpler, one-step meta-actions. This method addresses bottlenecks in annotation, model complexity, and inference latency associated with traditional reasoning-centric interfaces. DriveMA achieves new state-of-the-art results on the Waymo End-to-End Driving Challenge, demonstrating the effectiveness of its action-centric supervised training and reinforcement learning framework. AI

Researchers have developed a new framework called Just EEG Transformer (JET) for generating high-fidelity electroencephalogram (EEG) data. Unlike previous methods that use discrete denoising objectives, JET models EEG as continuous temporal sequences, better capturing the inherent dynamics and spectral structure of neural activity. This approach allows JET to preserve long-range temporal dependencies and generate more realistic signals, achieving over 40% reduction in TS-FID compared to existing baselines across multiple benchmarks. AI

Researchers have introduced MONET, a new open dataset designed to facilitate text-to-image model training. The dataset comprises approximately 104.9 million image-text pairs, meticulously curated through stages of filtering, deduplication, and re-captioning. MONET aims to lower the barriers for large-scale, reproducible research in text-to-image generation by providing a high-quality, enriched corpus. AI

A new research paper compares the effectiveness of Vision Transformers (ViTs) and Convolutional Neural Networks (CNNs) for land use scene classification using remote sensing imagery. The study evaluated AlexNet and ViT on the UC Merced Land Use and EuroSAT datasets, analyzing metrics like accuracy, precision, recall, and F1-score. Results indicate that CNNs are more robust with limited data and strong local textures, while ViTs excel at capturing global spatial relationships with sufficient training data, though they require more computational resources. AI

Researchers have developed G2D, a novel three-stage pipeline that combines a short online reinforcement learning (RL) warm-up with offline fine-tuning for language models. This approach aims to mitigate the computational expense of continuous online rollouts required by methods like GRPO. By constructing a static preference dataset after a brief GRPO phase and then using DPO for offline training, G2D has shown to match or exceed the performance of GRPO at a significantly reduced compute cost. AI