Brief

A new paper on arXiv proposes guidelines for using text data to assess the socio-economic impacts of climate change. The research addresses the fragmentation and methodological complexity in the field, offering recommendations for defining impacts, handling biases, and selecting modeling strategies. The goal is to support the creation of more accurate datasets for disaster risk management and attribution studies. AI

Researchers have introduced Spatial Gram Alignment (SGA), a new framework designed to improve ultra-high-resolution image synthesis using large-scale pre-trained Latent Diffusion Models (LDMs). Traditional methods struggle with extreme resolutions due to a conflict between learnability and fidelity, where direct feature distillation can degrade generation quality. SGA addresses this by aligning self-similarities of generative features with foundation model priors, preserving microscopic pixel-level fidelity while ensuring macroscopic structural coherence. AI

Researchers have developed a new two-stage framework for subject-driven text-to-image generation that first predicts a structural map (like a Canny edge map) and then renders the final image using both appearance and structure. This approach aims to better preserve high-frequency details such as logos, patterns, and text, which are often degraded in existing methods. To enhance text handling, they also created a large dataset of 100,000 image pairs with textual consistency, and evaluations using GPT-4.1 showed significant improvements over baseline methods. AI

A recent study re-evaluated the effectiveness of Transformer model modifications, finding that most still do not yield significant improvements when scaled to 1-3 billion parameters. Researchers tested 20 modifications introduced after 2021, using downstream evaluation metrics and controlling for variables like data, compute, and training recipes. The findings largely echo a 2021 study, with only a couple of modifications showing benefits, and one of those proving unstable at the larger scale. The research emphasizes the need for rigorous reporting, downstream evaluation, and cross-scale stability testing for architecture comparisons. AI

Researchers have introduced ELSA, a novel architecture designed to enhance the efficiency of neuromorphic computing using spiking neural networks (SNNs). ELSA enables true elastic inference by processing data in a fine-grained, token-wise pipeline, allowing for immediate forwarding of results and reduced latency. The architecture incorporates optimizations like a bundled address event representation protocol and mini-batch spiking Gustavson-product to minimize memory access and communication traffic. Experiments demonstrate that ELSA significantly outperforms existing accelerators in both speed and energy efficiency compared to both quantized artificial neural networks and other SNN accelerators. AI

Researchers have developed a novel method for algorithm selection in continuous black-box optimization that utilizes contour plots instead of traditional numerical features. A Convolutional Neural Network (CNN) analyzes these contour visualizations of probed landscapes to predict the performance of different solvers. This image-based approach demonstrated significant improvements over the single best solver (SBS) on the BBOB 2009 benchmark and showed competitiveness with existing feature-based methods. AI

Researchers have developed Tunable MAGMAX, a new framework for continual learning that allows for preference-aware model merging. This method enables control over task-specific performance in merged models, adapting them to different deployment needs and user preferences. By using a preference vector and leveraging target environment data, the system can automatically construct optimal vectors without manual input. Experiments show Tunable MAGMAX effectively manages task-wise performance and adapts merged models to various environments, outperforming or matching baseline methods. AI

Researchers have developed a new diagnostic dataset and protocol called TRACE-Edit to evaluate how well semantic information is preserved when Vision-Language Models (VLMs) are used for video editing. Their findings indicate that the alignment process between VLMs and Diffusion Transformer models (DiTs) can significantly degrade fine-grained structural details, challenging the assumption of lossless semantic transfer. This research identifies the VLM-to-DiT alignment as a critical bottleneck and provides a foundation for developing improved multi-modal alignment architectures. AI

Researchers have introduced a new framework called interaction locality to measure how information flows within AI models during spatial reasoning tasks. This framework analyzes whether computations remain confined to nearby areas or semantic segments, or if they cross these boundaries. The study applied this to models like HRM, TRM, and MTU3D, finding that high-level states in recursive models tend to write information locally, accumulating into broader structures, while embodied models concentrate causal spatial structure at module boundaries. AI

Researchers have introduced AttriStory, a new benchmark and method for improving fine-grained attribute realization in visual storytelling generated by diffusion models. The system addresses the challenge of ensuring specific attributes like clothing color and textures are accurately depicted across narrative scenes. AttriStory utilizes a plug-and-play latent optimization module and a novel AttriLoss objective to guide the diffusion model during the early stages of image generation, enhancing attribute control without altering existing story generation pipelines. AI

Researchers have developed a new active learning framework called Cumulative Active Meta-Learning (CAML) to improve the robustness of machine learning models against spurious correlations. CAML treats each active learning round as a meta-learning task, using queried samples to refine the model's inductive bias rather than just updating its likelihood. This cumulative approach captures sequential dependencies between learning rounds, leading to significant accuracy improvements for minority groups on various benchmarks. AI

A new roadmap paper highlights the limitations of causal machine learning (ML) in health research, despite its growing use with large observational clinical datasets. The authors emphasize the need for careful assessment of validity assumptions and responsible application by both clinical experts and ML practitioners. Without these precautions, causal ML approaches risk producing biased or misleading results, potentially impacting clinical research and patient care. AI

Researchers have developed a new framework called REPA-P to improve the accuracy and robustness of physics-informed diffusion models. This method aligns intermediate model representations with physical states during training by using lightweight projection heads that are removed during inference, thus adding no computational overhead. Experiments across four different physics tasks demonstrated that REPA-P can accelerate convergence, reduce physics residuals, and enhance out-of-distribution performance. AI

Researchers have developed a new framework for infrared small-target detection using point supervision, addressing challenges of unstable pseudo-labels and sample imbalance. Their approach utilizes a physics-induced annotation strategy based on heat diffusion to generate reliable pseudo-masks from single-point labels. A bi-level dual-update framework optimizes detector weights, sample weights, and diffusion parameters, enhancing supervision and adapting to sample distribution. AI

Researchers have introduced ShapeBench, a new open-source benchmark designed to standardize evaluations in aerodynamic shape optimization. This benchmark includes 103 tasks across eight shape categories, featuring validated surrogates for rapid testing and optional high-fidelity CFD pipelines for verification. ShapeBench aims to enable fair comparisons between various optimization methods, including classical, general-purpose, and LLM-driven approaches, by using a consistent budget metric and highlighting the variance in optimizer performance across different tasks. AI

Researchers have developed VBFDD-Agent, a novel system designed for detecting and diagnosing faults in electric vehicle batteries. This agent utilizes a descriptive text modeling approach, transforming raw battery data into natural language descriptions to create a specialized corpus. By integrating this corpus with maintenance manuals and large language model reasoning, VBFDD-Agent provides structured diagnostic results and actionable maintenance recommendations, enhancing human-AI collaboration in battery health management. AI

Researchers have identified a critical flaw in using large language models (LLMs) to simulate human behavior for experimental studies. Because LLMs are trained on observational data, interventions can inadvertently alter the simulated users' underlying attributes, leading to "user drift." This drift can distort the estimated effects of interventions, making the experimental results unreliable. The study proposes methods to diagnose this confounding using negative control outcomes and mitigate it by adjusting LLM personas with relevant confounders. AI

Researchers have developed SpineContextResUNet, a new 3D Residual U-Net architecture designed for efficient segmentation of spinal CT scans. This model addresses the high computational demands of existing methods by using a lightweight Context Block with parallel multi-dilated convolutions, avoiding the need for resource-intensive Transformers or RNNs. SpineContextResUNet achieves high accuracy on public benchmarks and demonstrates viable inference performance on commodity hardware, making it suitable for point-of-care diagnostics and edge devices. AI

A new paper analyzes the effectiveness of Gated Linear Units (GLU) in large language models, finding that they improve training speed by reshaping the neural tangent kernel (NTK) spectrum. Researchers observed that GLU structures lead to a smaller condition number and faster convergence, a phenomenon sometimes resulting in loss-crossing between GLU and non-GLU models. However, the study also indicated that GLU's benefit is primarily in optimization acceleration rather than reducing the generalization gap. AI

Researchers have developed a new method called Conflict-Aware Additive Guidance ($g^ ext{car}$) to improve the control and fidelity of generative models, particularly when dealing with multiple, potentially conflicting, constraints. This technique addresses issues where combining constraints can lead to deviations from the natural data distribution. $g^ ext{car}$ dynamically detects and resolves these gradient conflicts, demonstrating effectiveness across various applications including image editing and decision-making for planning and control, while maintaining efficient computation. AI

Researchers have developed PACD-Net, a novel self-supervised framework designed to estimate glycemic control metrics from sparse self-monitoring of blood glucose (SMBG) data. This approach uses pseudo-SMBG samples as teacher signals and contrastive learning to ensure consistent representations across different sampling patterns. The model, which employs a hybrid Swin Transformer-CNN backbone, demonstrates superior accuracy and stability compared to existing methods for estimating Time Above Range, Time in Range, and Time Below Range from real-world SMBG data, particularly under extremely sparse conditions. AI

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

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