AI News Archive: May 18, 2026 — Part 17
Sourced from 500+ daily AI sources, scored by relevance.
- Vision Foundation Models as Generalist Tokenizers for Image Generation
In this work, we explore the largely unexplored direction of building a generalist image tokenizer directly on top of a frozen vision foundation model (VFM). To build this tokenizer, we utilize a frozen VFM as the encoder and introduce two key innovations: (1) a region-adaptive quantization framewor...
- Can These Views Be One Scene? Evaluating Multiview 3D Consistency when 3D Foundation Models Hallucinate
Multiview 3D evaluation assumes that the images being scored are observations of one static 3D scene. This assumption can fail in NVS and sparse-view reconstruction: inputs or generated outputs may contain artifacts, outlier frames, repeated views, or noise, yet still receive high 3D consistency sco...
- WavFlow: Audio Generation in Waveform Space
Modern audio generation predominantly relies on latent-space compression, introducing additional complexity and potential information loss. In this work, we challenge this paradigm with WavFlow, a framework that generates high-fidelity audio directly in raw waveform space without intermediate repres...
- Aurora: Unified Video Editing with a Tool-Using Agent
Recent video editing models have converged on a unified conditioning design: a single diffusion transformer jointly consumes text, source video, and reference images, and one set of weights covers replacement, removal, style transfer, and reference-driven insertion. The design is flexible, but it as...
- The Claude Code Daily
Claude Code news. Curated Daily.
- LongLive-2.0: An NVFP4 Parallel Infrastructure for Long Video Generation
We present LongLive-2.0, an NVFP4-based parallel infrastructure throughout the full training and inference workflow of long video generation, addressing speed and memory bottlenecks. For training, we introduce sequence-parallel autoregressive (AR) training, instantiated as Balanced SP, which co-desi...
- Spectral Progressive Diffusion for Efficient Image and Video Generation
Diffusion models have been shown to implicitly generate visual content autoregressively in the frequency domain, where low-frequency components are generated earlier in the denoising process while high-frequency details emerge only in later timesteps. This structure offers a natural opportunity for ...
- PIXLRelight: Controllable Relighting via Intrinsic Conditioning
We present PIXLRelight, a feed-forward approach for physically controllable single-image relighting. Existing methods either provide limited lighting control (e.g. through text or environment maps), accumulate errors when chaining inverse and forward rendering, or require costly per-image optimizati...
- EgoExoMem: Cross-View Memory Reasoning over Synchronized Egocentric and Exocentric Videos
Egocentric memory is widely used in embodied intelligence, but it may be insufficient for comprehensive spatial-temporal reasoning. Inspired by human recall from both field and observer perspectives, we introduce EgoExoMem, the first benchmark for cross-view memory reasoning over synchronized egocen...
- Advancing Narrative Long Video Generation via Training-Free Identity-Aware Memory
Autoregressive video generation has improved rapidly in visual fidelity and interactivity, but it still suffers from long-term inconsistency and memory degradation. Most existing solutions either compress historical frames using predefined strategies or retrieve keyframes based on coarse implicit at...
- Robo-Cortex: A Self-Evolving Embodied Agent via Dual-Grain Cognitive Memory and Autonomous Knowledge Induction
The ability to navigate and interact with complex environments is central to real-world embodied agents, yet navigation in unseen environments remains challenging due to "experiential amnesia," where existing trajectory-driven or reactive policies fail to synthesize generalizable strategies from pas...
- CMAG: Concept-Scaffolded Retrieval for Marketplace Avatar Generation
Metaverse platforms rely on creator-driven marketplaces where avatars are assembled from discrete, taxonomy-labeled 3D assets (e.g., tops, bottoms, shoes, accessories) under strict category and topology constraints. While users increasingly expect free-form text control, text-only retrieval is britt...
- Dance Across Shifts: Forward-Facilitation Continual Test-Time Adaptation through Dynamic Style Bridging
Continual Test-Time Adaptation (CTTA) aims to empower perception systems to handle dynamic distribution shifts encountered after deployment. Existing methods predominantly follow a backward-alignment paradigm, which rigidly aligns incoming data with supervisory surrogates derived from the source dom...
- Starve to Perceive: Taming Lazy Perception in VLMs with Constrained Visual Bandwidth
Vision-Language Models (VLMs) deployed as situated agents in high-resolution visual environments require active perception -- the ability to dynamically decide where to look through operations like zooming, cropping, and panning. However, current training paradigms produce models that mimic the surf...
- Incantation: Natural Language as the Action Interface for Multi-Entity Video World Models
Modern interactive video world models have achieved impressive visual fidelity, yet lack fine-grained multi-entity control and cross-entity, cross-world generalization. We trace this gap to the action interface: standard control protocols (e.g. animation IDs, device inputs, scene-level captions) bin...
- Resolving Representation Ambiguity in Feedforward Novel View Synthesis Transformer via Semantic-Spatial Decoupling
Transformer-based models have advanced feedforward novel view synthesis (NVS). Current architectures such as GS-LRM and LVSM mix semantic information (e.g., RGB) and spatial information (e.g., Plücker rays) into a shared feature space. Since Plücker rays naturally carry lattice-like spatial structur...
- OmniPro: A Comprehensive Benchmark for Omni-Proactive Streaming Video Understanding
Omni-proactive streaming video understanding, i.e., autonomously deciding when to speak and what to say from continuous audio-visual streams, is an emerging capability of omni-modal large language models. Existing benchmarks fall short in three key aspects: they rely primarily on visual signals, ado...
- Beyond Morphology: Quantifying the Diagnostic Power of Color Features in Cancer Classification
In histopathology, human experts primarily rely on color as a means of enhancing contrast to interpret tissue morphology, whereas machine vision models process color as raw statistical information. This distinction raises a fundamental question: to what extent can pixel intensity alone, independent ...
- Weakly Supervised Cross-Modal Learning for 4D Radar Scene Flow Estimation
Due to the difficulty of obtaining ground-truth data for 4D radar scene flow estimation, previous methods typically rely on either self-supervised losses or cross-modal supervision using 3D LiDAR data, 2D images, and odometry. However, self-supervised approaches often yield suboptimal results due to...
- InstructAV2AV: Instruction-Guided Audio-Video Joint Editing
Recent diffusion-based methods have achieved impressive progress in video content manipulation. However, they typically ignore the accompanying audio, leaving the audio disjointed from the edited results. In this paper, we propose InstructAV2AV, the first end-to-end framework for instruction-guided ...
- Perceptron Mk1
Frontier video reasoning for the physical world
- Code-as-Room: Generating 3D Rooms from Top-Down View Images via Agentic Code Synthesis
Designing realistic and functional 3D indoor rooms is essential for a wide range of applications, including interior design, virtual reality, gaming, and embodied AI. While recent MLLM-based approaches have shown great potential for 3D room synthesis from textual descriptions or reference images, te...
- NeRF-based Spacecraft Reconstruction from Close-Range Monocular Imagery Under Illumination Variability and Pose Uncertainty
Autonomous rendezvous and proximity operations around uncooperative, unknown spacecraft are critical for active debris removal and on-orbit servicing missions. A key component of such operations is the offline reconstruction of a 3D model of the target from a set of 2D images. This task is challengi...
- Cracks in the Foundation: A Civil Infrastructure Dataset to Challenge Vision Foundation Models
Automated structural health monitoring is essential to prevent catastrophic infrastructure failures. Precise, pixel-level defect segmentation is needed to accurately assess structural integrity, but progress in defect segmentation for civil infrastructures has been held back by an extreme scarcity o...
- NEWTON: Agentic Planning for Physically Grounded Video Generation
Video generation models produce visually compelling results but systematically violate physical commonsense -- on VideoPhy-2, the best model achieves only 32.6% joint accuracy. We identify a specification bottleneck: text prompts are lossy compression of the physical world, omitting the parameters t...
- GeoFlow: Enforcing Implicit Geometric Consistency in Video Generation
Generating geometrically consistent videos remains an open challenge: text-to-video diffusion models trained on web-scale data treat geometry only implicitly, leading to object deformation, texture drift, and non-rigid backgrounds under camera motion. Existing solutions either improve consistency as...
- Can Adaptive Gradient Methods Converge under Heavy-Tailed Noise? A Case Study of AdaGrad
Many tasks in modern machine learning are observed to involve heavy-tailed gradient noise during the optimization process. To manage this realistic and challenging setting, new mechanisms, such as gradient clipping and gradient normalization, have been introduced to ensure the convergence of first-o...
- Can machine learning for quantum-gas experiments be explainable?
Virtually all aspects of many-body atomic physics are challenging: experiments are technically demanding, datasets have become enormous, and the memory and CPU requirements for classical simulation of generic quantum systems often scale exponentially with system size. Machine learning (ML) methods a...
- A No-Defense Defense Against Gradient-Based Adversarial Attacks on ML-NIDS: Is Less More?
Gradient-based adversarial attacks subtly manipulate inputs of Machine Learning (ML) models to induce incorrect predictions. This paper investigates whether careful architectural choices alone can yield an inherently robust Deep Neural Network (DNN)-based Network Intrusion Detection Systems (NIDS), ...
- Efficient and Noise-Tolerant PAC Learning of Multiclass Linear Classifiers
Noise-tolerant PAC learning of linear models has been of central interests in machine learning community since the last century. In recent years, many computationally-efficient algorithms have been proposed for the problem of learning linear threshold functions under multiple noise models. Yet, when...
- Aligned Training: A Parameter-Free Method to Improve Feature Quality and Stability of Sparse Autoencoders (SAE)
Sparse autoencoders (SAEs) are one of the main methods to interpret the inner workings of deep neural networks (DNNs), decomposing activations into higher-dimensional features. However, they exhibit critical shortcomings where a large fraction of features are never activated and are unstable. Despit...
- Learning to Look Benign: Targeted Evasion of Malware Detectors via API Import Injection
Machine learning-based malware detectors are widely deployed in antivirus and endpoint detection systems, yet their reliance on static features makes them vulnerable to adversarial manipulation. This paper investigates whether a malware sample can be intentionally misclassified as a specific benign ...
- Perfect Parallelization in Mini-Batch SGD with Classical Momentum Acceleration
Accelerating stochastic gradient methods with classical momentum schemes, such as Polyak's heavy ball, has proven highly successful in training large-scale machine learning models, particularly when combined with the hardware acceleration of large mini-batch computations. Yet, the effect of classica...
- Pointwise Generalization in Deep Neural Networks
We address the fundamental question of why deep neural networks generalize by establishing a pointwise generalization theory for fully connected networks. This framework resolves long-standing barriers to characterizing the rich nonlinear feature-learning regime and builds a new statistical foundati...
- S2Aligner: Pair-Efficient and Transferable Pre-Training for Sparse Text-Attributed Graphs
Pre-training on text-attributed graphs (TAGs) is central to building transferable graph foundation models, where LLM-as-Aligner methods align graph and text representations through the semantic knowledge of large language models. However, these methods usually assume that node texts provide sufficie...
- Self-supervised local learning rules learn the hidden hierarchical structure of high-dimensional data
The brain learns abstract representations of high-dimensional sensory input, but the plasticity rules that enable such learning are unknown. We study biologically plausible algorithms on the Random Hierarchy Model (RHM), an artificial dataset designed to investigate how deep neural networks learn th...
- NonBioS.ai
The AI Software Dev with its own Computer
- Protein Fold Classification at Scale: Benchmarking and Pretraining
Classifying protein topology is essential for deciphering biological function, but progress is held back by the lack of large-scale benchmarks that avoid duplicates and by models that do not scale well. We introduce TEDBench, a large-scale, non-redundant benchmark for protein fold classification con...
- SURGE: Approximation-free Training Free Particle Filter for Diffusion Surrogate
Diffusion-based generative models increasingly rely on inference-time guidance, adding a drift term or reweighting mixture of experts, to improve sample quality on task-specific objectives. However, most existing techniques require repeated score or gradient evaluations, introducing bias, high compu...
- Learned Memory Attenuation in Sage-Husa Kalman Filters for Robust UAV State Estimation
Unmanned Aerial Vehicles in dynamic environments face telemetry outages, structural vibrations, and regime-dependent noise that invalidate the stationary covariance assumptions of classical Kalman filters. The Sage-Husa Kalman Filter (SHKF) estimates noise statistics online, but its reliance on a st...
- Learning Normal Representations for Blood Biomarkers
Blood-based biomarkers underpin clinical diagnosis and management, yet their interpretation relies largely on fixed population reference intervals that ignore stable, intra-patient variability. As such, population-based interpretation can mask meaningful deviation from an individual's baseline, risk...
- Better Together: Evaluating the Complementarity of Earth Embedding Models
Earth embedding models transform Earth observation data into embeddings uniquely tied to locations on the Earth's surface. These models are typically evaluated in isolation, comparing the downstream task performance across different Earth embeddings. However, spatially aligned embeddings can natural...
- Physics-Aligned Canonical Equivariant Fourier Neural Operator under Symmetry-Induced Shifts
Neural operators approximate PDE solution maps, but they need not respect the symmetries of the governing equation. In out-of-distribution (OOD) regimes, a standard neural operator must often learn coordinate alignment and physical evolution within a single map, which can hurt generalization. We use...
- PACE: Geometry-Aware Bridge Transport for Single-Cell Trajectory Inference
Single-cell trajectory inference from destructive time-course snapshots is fundamentally ill-posed: neither cross-time cell correspondences nor continuous trajectories are observed, so the snapshot distributions alone do not uniquely determine the underlying dynamics. Existing optimal transport and ...
- scHelix: Asymmetric Dual-Stream Integration via Explicit Gene-Level Disentanglement
A critical challenge in single-cell RNA sequencing (scRNA-seq) integration is resolving the tension between eliminating batch effects and maintaining biological fidelity. While recent evidence indicates that batch effects manifest heterogeneously across genes, most existing methods process the trans...
- Probing for Representation Manifolds in Superposition
This paper introduces the Manifold Probe, a supervised method for discovering representation manifolds in superposition. The method generalizes linear regression probes by learning the space of features of a concept that can be linearly predicted from the representations, and then learning the direc...
- Beyond Scaling: Agents Are Heading to the Edge
The bottleneck of useful agentic intelligence has shifted from compressing world knowledge into a single model to executing a coordinated system. This position paper argues that personal-agent architecture must move to the edge because the core properties of agentic intelligence tasks, particularly ...
- Unified Walking, Running, and Recovery for Humanoids via State-Dependent Adversarial Motion Priors
We propose a unified reinforcement learning framework that enables a single policy to perform walking, running, and fall recovery on the Unitree G1 humanoid robot, validated on physical hardware without any explicit mode-switching command at deployment. The framework extends Adversarial Motion Prior...
- Qumus: Realization of An Embodied AI Quantum Material Experimentalist
While modern Large Language Models (LLMs) and agentic artificial intelligence (AI) have demonstrated transformative capabilities in digital domains, the realization of embodied AI capable of real-world scientific discovery remains a difficult frontier. The advancements are hindered by the inherent c...
- On Improving Multimodal Pedestrian Trajectory Prediction with CVAE: A Study on Benchmark and Robot Data
Accurate pedestrian trajectory prediction is crucial for autonomous systems operating in complex environments, such as modular buses and delivery robots in suburban or semi-structured areas. Social Spatio-Temporal Graph Convolutional Neural Networks (Social-STGCNN) have shown strong performance by m...