AI News Archive: September 2, 2026 — Part 18
Sourced from 500+ daily AI sources, scored by relevance.
- Debias-SparseGPT: Bias-Aware Pruning for Large Language Models
Model compression techniques such as pruning and quantization facilitate the efficient deployment and acceleration of Large Language Models (LLMs). However, recent studies show that weight sparsification methods, such as SparseGPT, can amplify existing biases in models, with outputs varying signific...
- How LLMs Build Fictional Worlds: Setting and Narrative Space in AI-Generated Creative Storytelling
In this paper, we analyze how Large Language Models (LLMs) employ worldbuilding strategies, focusing on setting as one measurable dimension of storyworld construction. We compare 1,000 AI-generated stories per model in English and German with human-authored fiction from Project Gutenberg. Building o...
- Learning to Fuse LLMs with Ontology Rankers for Rare-Disease Diagnosis
Ontology rankers remain useful for rare-disease diagnosis because each candidate can be traced to matched patient phenotypes. Large language models (LLMs) can generate differential diagnoses from the same patient description, but their predictions lack an equally clear evidence trail. Rather than as...
- Improving Health Literacy through Lay Summarization of Radiological Reports: An Evaluation of BioNER and Retrieval-Augmented Generation
Radiology reports are written primarily for clinicians, and their specialized terminology often makes them difficult for patients to interpret. As a result, many patients turn to publicly available Large Language Models (LLMs) to help explain their reports, despite well-documented risks of factual i...
- SALA: Semantic-Aware Logical Alignment for Complex Reasoning in In-Context Learning
Effective in-context learning (ICL) for complex reasoning relies on selecting the right demonstrations. Traditional retrieval methods based on surface similarity fail to capture the underlying problem-solving logic. Recent logic-based methods address this by matching predefined reasoning steps, but ...
- SCX Router: Streaming Zero-Shot Model Selection with a Decoder-KV Classifier and a Real-World Task Ontology
The rapid proliferation of large language models (LLMs) and the growing diversity of their applications presents a unique optimization opportunity: selecting the right model for the task, while optimizing for speed, cost, and quality at a per-task level. However, inference endpoints can vary widely ...
- Entangled Representations Amplify Collateral Damage in Unlearning
A long-held intuition in interpretability research is that representational entanglement, the sharing of structure between knowledge domains in a neural network, makes unlearning harder. While the intuition is widespread, it has never been directly tested in a controlled experiment. We present a way...
- CoMerge: Conflict-Driven Preference Optimization for Multi-Task Model Merging
Model merging provides an efficient paradigm for constructing multi-task large language models (LLMs) without full model retraining, yet it remains challenged by parameter interference. While existing methods aim to preserve the capabilities of individual expert models and mitigate interference, the...
- DiscoSign: Discourse-Aware Text to Sign Language Gloss Translation
Sign language processing systems have traditionally operated at the sentence level, ignoring critical discourse phenomena fundamental to sign language comprehension. We introduce DiscoSign, a computational approach for discourse-aware text to sign language gloss translation grounded in linguistic re...
- HyperStyler: Low-resource Authorship Style Transfer via Context-aware Style Navigation and Hypernetworks
Low-resource authorship style transfer (LAST) aims to rewrite text into the style of an arbitrary target author using only a few reference examples while preserving the original meaning. Existing methods often struggle to achieve both high style fidelity and semantic preservation because they compre...
- Trace as State: Reasoning Traces as Conditional States for Long-Context Transformers
Transformers process information causally, but long-context reasoning may depend on task state discovered only later. We formalize this mismatch through conditional state update tasks. For causal state update processors, providing the condition first can require exponentially less memory in the wors...
- oHC: Orthogonal Hyper-Connections on SO(4) via Quaternions
Hyper-Connections (HC) replace the single residual stream of a Transformer with $n$ parallel ones, mixing them at every layer with a learned $n \times n$ residual matrix. Leaving that matrix unconstrained places no limit on the factor by which the mixing step rescales the residual streams, and that ...
- WinoQueer-NL: Assessing Bias in Dutch Language Models toward LGBTQ+ Identities
While English language models have been widely examined for anti-queer bias, Dutch models remain understudied. To address this gap, we developed a culturally and linguistically adapted Dutch dataset based on the English WinoQueer benchmark, containing pairs of stereotypical and counter-stereotypical...
- Scalable Direction-Following TTS via Voice Impression-Guided Pseudo Triplet Construction
Voice actors often re-read the same script while modifying their delivery in response to performance directions. We study this setting as direction-following TTS, where a system generates a new utterance that reflects a given direction relative to a reference utterance while preserving speaker ident...
- Glance
AI agents on your Home Screen
- PragAlign: Feedback-Guided Pragmatic Alignment for Controlled Synthetic Dialogue Generation
Synthetic dialogue generation can support research in privacy-restricted service settings, but generated conversations must preserve communicative intent, affective meaning, and natural dialogue flow. We introduce PragAlign, a feedback-guided framework for controlled synthetic dialogue generation co...
- When Decodability Is Not Enough: Logical Validity Representations, Behavioral Dissociation, and Causal Tests in Language Models
Large language models can look capable of logical reasoning, but correct or incorrect answers alone tell us little about what the model represents internally. We study logical verification in five open-weight transformer models using matched valid--invalid premise--claim pairs that vary across infer...
- SonicCaps: Large-Scale Diverse and Fine-Grained Captioning for Improved Audio-Retrieval
Recent advances in audio-language modeling have been driven by large-scale audio captioning datasets. However, existing datasets remain limited by low semantic diversity, generic descriptions lacking acoustic details, and one-to-one audio-caption mappings that poorly reflect the inherent ambiguity o...
- Counter-GEO-Bench: Evaluating Defenses Against Information-Distorting Generative Engine Optimization
Generative engine optimization (GEO) enables content producers to increase the visibility of their web pages in generative search engines, but the same techniques can deliver targeted misinformation when adversaries publish ordinary-looking GEO-optimized documents that victim large language models (...
- DiffIE: Diffusion-based Open Information Extraction
A single sentence often expresses multiple valid relational triplets, which makes Open Information Extraction (OpenIE) fundamentally a multi-output task. Existing neural systems handle this by autoregressive generation, which is flexible but slow and prone to redundancy, or by fixed-slot prediction,...
- Efficient GUI Agents: A Systems Survey of Observation, Memory, Action, and Runtime Optimization
GUI agents increasingly operate across websites, mobile apps, and desktop environments, yet the field still reports progress primarily through task success. We argue that practical deployment depends equally on efficiency: how much context, computation, action budget, and runtime overhead an agent c...
- Improving Evaluation Realism with Inference-Time Compute and Deployment Scaffolds
A core obstacle to alignment evaluation is evaluation awareness: capable models can tell when they are being tested rather than deployed, weakening the conclusions a safety evaluation can support. We present two techniques that make simulated alignment evaluations harder to distinguish from real dep...
- Do Large Language Models Capture the Diversity in their Training Data?
Large language models are trained to model conditional distributions over text, yet it remains inadequately understood whether they capture the full diversity of plausible outputs present in their training data. We study this question through an information-theoretic lens by comparing the conditiona...
- PlantC2USeg: Cross-Scale Consistent Pre-Training for Few-Shot Unified Plant Point Cloud Segmentation
Modern crop breeding demands precise organ-level analysis for trait quantification, making plant point cloud segmentation (PPCS) increasingly important. However, conventional deep learning approaches rely heavily on densely annotated datasets that are labor-intensive to acquire. Unified PPCS adaptat...
- GDB-Reward: From Evaluation Metrics to Training Rewards for Graphic Design
Text-to-image models excel at natural image synthesis but struggle with graphic design, where success depends on satisfying precise constraints on typography, layout, color, and visual communication. While prompt optimization offers an attractive alternative to expensive diffusion model fine-tuning,...
- Generating Medical Image Counterfactuals using Causal Explanations
Deep learning models have achieved impressive performance in medical image diagnosis, yet their deployment in clinical settings remains constrained by limited explainability. Counterfactual images provide one means of auditing model behavior by showing how an image would need to change for a classif...
- Characterizing Text Branch Sensitivity in Medical Vision-Language Segmentation via Evidence Decoupling
Pretrained vision-language models (VLMs) have shown promising performance in medical image segmentation by incorporating clinical text. However, it remains unclear how much textual information actually contributes to pixel-level predictions. In this work, we systematically investigate the role of te...
- Deeply Interleaved Text-Image Contexts for Multimodal LLMs Assessment
Current evaluations and training of multimodal models predominantly focus on multi-image tasks, largely overlooking interleaved text-image scenarios. In such multi-image tasks, text typically serves merely as task instructions, lacking deep semantic interaction with the visual content. In contrast, ...
- MARS: What Retrieval Signals Are Hidden in Multimodal Large Language Models for Text-Video Retrieval?
Text-video retrieval requires representations that can distinguish videos with similar scenes, actions, and temporal patterns. Recent multimodal large language models have been adapted as embedding models, but they often represent each input using a single token from the final layer. This can compre...
- Stereo 4D Radar for 3D Object Detection: Integrating Geometric Alignment and Absolute Velocity Estimation
Four-dimensional (4D) Radar is a powerful sensing modality capable of detecting surrounding three-dimensional (3D) objects under diverse weather conditions and providing Doppler-based motion information. However, raw 4D Radar signals contain significant clutter from road surfaces, guardrails, and su...
- Stress Less 2.0 With On-Device AI
Don't just track stress. Do something about it now
- Beauty is in the AI of the beholder: MLLMs systematically overrate facial attractiveness
Beauty assessments from Multimodal Large Language Models (MLLMs) are increasingly popular amongst users, companies, and aestheticians. This raises the question of whether these AI models can accurately reflect human judgments of attractiveness. In a pre- registered exploratory study, we compared the...
- VIPS: Vehicle-Infrastructure Cooperative Planning Benchmark via Pseudo-Simulation
End-to-end autonomous driving in urban environments requires robust decision-making under partial observability and complex multi-agent interactions. Severe occlusions and dense traffic at intersections limit the perception capability of single-agent systems, motivating recent efforts on Vehicle-to-...
- Adapting a Foundation Model for Lunar Surface Height Estimation
Digital elevation models (DEMs) can provide accurate height information, making it invaluable for analyzing the lunar surface. As the European Space Agency (ESA) prepares for future lunar missions that aim to land on the Moon, a precise method for height estimation will be essential for hazardous te...
- Information Density Imbalance in Visual Object Detection
In object detection, the number of instances is typically used to determine whether a dataset exhibits a long-tailed distribution, implicitly assuming that the model will perform poorly on categories with fewer instances. This assumption has led to extensive research on category bias in datasets wit...
- SolarWM: Open Data and Scalable Training for Long-Horizon Video World Models
We introduce SolarWM, a fully open foundation for building interactive video world models from data preparation through long-horizon inference. Training across heterogeneous data sources and video backbones is challenging: datasets differ in temporal scale, camera geometry, visual quality, motion, a...
- Thinking in Pictures: A Systematic Benchmark for Reasoning-driven Image Generation
Recent advancements in unified generative models (UGMs) and world simulators have achieved unprecedented results in visual perception and synthesis. However, these models primarily rely on surface-level event alignment, leaving the capacity for high-level visual reasoning underexplored. True visual ...
- MuyBridge: Mobile Human Center-of-Mass Estimation from Monocular Video via Sparse Fusion
The 3D center of mass (CoM) is a primary quantity in the biomechanical analysis of sport, rehabilitation, and clinical movement, yet existing 3D pose tracking, mesh recovery, and multi-view triangulation methods either optimize 3D keypoint accuracy without anatomical constraints or carry compute and...
- RoGe: Novel View Synthesis via End-to-End Implicit Reconstruction and Generation
Novel view synthesis from sparse inputs requires both geometric grounding from the observed views and generative priors of unobserved regions, motivating recent hybrid methods that combine reconstruction and generation. However, existing methods bridge the two with rendered images or explicit 3D rep...
- Efficient All-in-One Weather Restoration using Spectral Harmonization
Adverse weather conditions such as rain, haze, and snow significantly degrade image quality, posing challenges for both human perception and physical AI. Existing restoration methods require large computational budgets, struggling to process high-resolution images and handle different degradations. ...
- Benchmarking RAW and RGB Restoration in Image Signal Processors
Modern cameras transform RAW sensor measurements into sRGB images through an image signal processor (ISP). We benchmark two placements for blind restoration around a fixed ISP: (A) pre-ISP restoration in the RAW domain and (B) post-ISP restoration in the sRGB domain. The benchmark covers four smartp...
- AutoCompass: Accurate Visual Localization on Public Maps by Learning from Weak Labels
Neural map matchers estimate an image's 3-DoF pose relative to a 2D map. These models are trained on large-scale datasets of geo-referenced images, whose position and heading labels often contain noise that affects the trained models. To address this, we present AutoCompass, a supervision approach f...
- Video-Based Palm-Vein Authentication under Challenging Conditions
Palm-vein biometrics are increasingly used for secure, contactless authentication. Yet real-world deployment exposes them to surface noise (sweat, dirt), illumination and motion variation, and temperature-driven changes in vascular visibility, which remain underexplored for lack of data captured und...
- Multi-Tool Image Editing Attribution in Facial Forgery
As generative AI tools become increasingly powerful and easy to use, people can easily edit portrait images with a prompt, necessitating the task of image editing attribution, which predicts the involved editing tools from the given image. Existing attribution methods hold the single-tool assumption...
- Balancing Frequencies and Pixels in Flow Matching
Natural images follow a $1/f^2$ spectral distribution: most signal energy lies in the low spatial frequencies, while the perceptually important structures such as textures and edges occupy sparse high-frequency bands. Pixel-space reconstruction objectives, however, treat all spatial errors uniformly...
- InceptionGS: Generative Bootstrapping for Large-Scale Gaussian Splatting under Unstructured View Sampling
Achieving truly immersive large-scale scene digitization necessitates consistent and visually pleasing rendering across all possible viewing perspectives. However, collecting multi-view images covering every fine detail of a large-scale scene is prohibitive due to scene complexity, capture cost, neg...
- MV-dVRK: A Multi-Viewpoint Benchmark for Spatial Surgical Perception
Large-scale training and refined optimization techniques have greatly improved sparse multi-view 3D reconstruction. Despite their relevance to surgery, such methods have never before been rigorously evaluated on real endoscopic images. Current clinical telerobots deploy a single stereo camera inside...
- A Top-Down Framework for Metric-Scale Athlete Localization from Single Broadcast Frames
Accurate world-coordinate localization of athletes from single-frame broadcast footage is inherently challenging due to extreme scale disparities in ultra-high-resolution imagery. In this paper, we propose a top-down framework for metric-scale athlete localization from a single calibrated frame. Our...
- GaLe: memory-efficient Global Approximate and Local Exact features
Embedded devices typically lack the resources of GPU-equipped machines, and existing inference methods suffer from either high computational overhead (patch-based) or accuracy loss (approximation-based). We propose GaLe, a memory-efficient technique that enables the deployment of pretrained networks...
- Genesis: A Generative Engine for Hierarchical Satellite Image Synthesis
Earth observation is fundamentally multi-scale; geospatial tasks span varied resolutions, and satellite imagery is organized into cascading tile pyramids that nest fine detail within wide coverage. Current generative models of satellite imagery, however, operate along a single axis: they either zoom...