AI News Archive: May 14, 2026 — Part 16
Sourced from 500+ daily AI sources, scored by relevance.
- Beyond Instance-Level Self-Supervision in 3D Multi-Modal Medical Imaging
Self-supervised pre-training methods in medical imaging typically treat each individual as an isolated instance, learning representations through augmentation-based objectives or masked reconstruction. They often do not adequately capitalize on a key characteristic of physiological features: anatomi...
- Deep Image Segmentation via Discriminant Feature Learning
Accurate image segmentation remains challenging, particularly in generating sharp, confident boundaries. While modern architectures have advanced the field, many of them still rely on standard loss functions like Cross-Entropy and Dice, which often neglect the discriminative structure of learned fea...
- Towards Accurate Single Panoramic 3D Detection: A Semantic Gaussian Centric Approach
Three-dimensional object detection in panoramic imagery is crucial for comprehensive scene understanding, yet accurately mapping 2D features to 3D remains a significant challenge. Prevailing methods often project 2D features onto discrete 3D grids, which break geometric continuity and limit represen...
- MechVerse: Evaluating Physical Motion Consistency in Video Generation Models
Text- and image-conditioned video generation models have achieved strong visual fidelity and temporal coherence, but they often fail to generate motion governed by kinematic and geometric constraints. In these settings, object parts must remain rigid, maintain contact or coupling with neighboring co...
- Multi-proposal Collaboration and Multi-task Training for Weakly-supervised Video Moment Retrieval
This study focuses on weakly-supervised Video Moment Retrieval (VMR), aiming to identify a moment semantically similar to the given query within an untrimmed video using only video-level correspondences, without relying on temporal annotations during training. Previous methods either aggregate predi...
- HDRFace: Rethinking Face Restoration with High-Dimensional Representation
Face restoration under complex degradations still remains an ill-posed inverse problem due to severe information loss. Although diffusion models benefit from strong generative priors, most methods still condition only on low-quality inputs, making it difficult to recover identity-critical details un...
- The Velocity Deficit: Initial Energy Injection for Flow Matching
While Flow Matching theoretically guarantees constant-velocity trajectories, we identify a critical breakdown in high-dimensional practice: the Velocity Deficit. We show that the MSE objective systematically underestimates velocity magnitude, causing generated samples to fail to reach the data manif...
- Probing into Camera Control of Video Models
Video is a rich and scalable source of 3D/4D visual observations, and camera control is a key capability for video generation models to produce geometrically meaningful content. Existing approaches typically learn a mapping from camera motion to video using additional camera modules and paired data....
- SuperADD: Training-free Class-agnostic Anomaly Segmentation -- CVPR 2026 VAND 4.0 Workshop Challenge Industrial Track
Visual anomaly detection (AD) for industrial inspection is a highly relevant task in modern production environments. The problem becomes particularly challenging when training and deployment data differ due to changes in acquisition conditions during production. In the VAND 4.0 Industrial Track, mod...
- COAL: Counterfactual and Observation-Enhanced Alignment Learning for Discriminative Referring Multi-Object Tracking
Referring Multi-Object Tracking (RMOT) faces a fundamental structural contradiction between the high-discriminability demand and the sparse semantic supervision. This mismatch is particularly acute in highly homogeneous scenarios that require fine-grained discrimination over complex compositional se...
- BioHuman: Learning Biomechanical Human Representations from Video
Understanding human motion beyond surface kinematics is crucial for motion analysis, rehabilitation, and injury risk assessment. However, progress in this domain is limited by the lack of large-scale datasets with biomechanical annotations, and by existing approaches that cannot directly infer inter...
- Video-Zero: Self-Evolution Video Understanding
Self-evolution offers a promising path for improving reasoning models without relying on intensive human annotation. However, extending this paradigm to video understanding remains underexplored and challenging: videos are long, dynamic, and redundant, while the evidence needed for reasoning is ofte...
- UMo: Unified Sparse Motion Modeling for Real-Time Co-Speech Avatars
Speech-driven gestures and facial animations are fundamental to expressive digital avatars in games, virtual production, and interactive media. However, existing methods are either limited to a single modality for audio motion alignment, failing to fully utilize the potential of massive human motion...
- Deepheem
Evidence-backed AML & compliance investigations
- AirDoc AI
What if invoices just.. showed up in Xero
- Nexalearn
AI Mentor for UPSC & Competitive Exam Success
- LangXP
Your free AI- language exam grader for multiple languages
- CoverRoute
Generate tailored cover letters from your CV
- Lawcrative
All in one Legal software for AI-powered practice management
- LangProtect Guardia
Prompt injection’s least favorite product.
- Tokavy — Less Tokens. Better Answers.
Your AI prompts, refined in a keystroke
- Selint
Sales meeting assistant with real-time suggestions for teams
- Penta-V Kernel
Sub-nanosecond (845ps) Rust safety kernel for AI alignment.
- Visual Prompt Builder for GPT — EmojiPT
Build better prompts with clicks, not typing in ChatGPT
- OpenInterpretability
Open-source toolkit to audit what your LLM knows
- overlandai
Generate real-world adventures with AI in seconds
- RedactEngine
Batch Blur sensitive information in images with offline AI
- X402AgentPay
x402 commerce layer for AI agents — beyond raw HTTP payments
- Mindmesh
AI workspace for focused work and modern teams
- BrandAuditor
Brand auditor for India - TM, Domain, Name, Social, SEO, AI
- Cloe
A realistic AI character living on your desktop
- BAIN tools
Finding best ais
- AI Prism
Gathering the latest AI news from around the world
- TubeFilter
AI reads YouTube so you don't have to
- MiVE: Multiscale Vision-language features for reference-guided video Editing
Reference-guided video editing takes a source video, a text instruction, and a reference image as inputs, requiring the model to faithfully apply the instructed edits while preserving original motion and unedited content. Existing methods fall into two paradigms, each with inherent limitations: deco...
- TERRA-CD: Multi-Temporal Framework for Multi-class and Semantic Change Detection
Urban vegetation monitoring plays a vital role in understanding environmental changes, yet comprehensive datasets for this purpose remain limited. To address this gap, we present the Temporal Remote-sensing Repository for Analyzing Change Detection (TERRA-CD), a benchmark dataset comprising 5,221 Se...
- UniTriGen: Unified Triplet Generation of Aligned Visible-Infrared-Label for Few-Shot RGB-T Semantic Segmentation
RGB-T semantic segmentation requires strictly aligned VIS-IR-Label triplets; however, such aligned triplet data are often scarce in real-world scenarios. Existing generative augmentation methods usually adopt cascaded generation paradigms, decomposing joint triplet generation into local conditional ...
- ViMU: Benchmarking Video Metaphorical Understanding
Any new medium, once it emerges, is used for more than the transmission of overt content alone. The information it carries typically operates on two levels: one is the content directly presented, while the other is the subtext beneath it-the implicit ideas and intentions the creator seeks to convey ...
- MambaRain: Multi-Scale Mamba-Attention Framework for 0-3 Hour Precipitation Nowcasting
Accurate precipitation nowcasting over extended horizons (0-3 hours) is essential for disaster mitigation and operational decision-making, yet remains a critical challenge in the field. Existing deterministic approaches are predominantly constrained to shorter prediction windows (0-2 hours), exhibit...
- VMU-Diff: A Coarse-to-fine Multi-source Data Fusion Framework for Precipitation Nowcasting
Precipitation nowcasting is a vital spatio-temporal prediction task for meteorological applications but faces challenges due to the chaotic property of precipitation systems. Existing methods predominantly rely on single-source radar data to build either deterministic or probabilistic models for ext...
- TOPOS: High-Fidelity and Efficient Industry-Grade 3D Head Generation
High-fidelity 3D head generation plays a crucial role in the film, animation and video game industries. In industrial pipelines, studios typically enforce a fixed reference topology across all head assets, as such a clean and uniform topology is a prerequisite for production-level rigging, skinning ...
- Eradicating Negative Transfer in Multi-Physics Foundation Models via Sparse Mixture-of-Experts Routing
Scaling Scientific Machine Learning (SciML) toward universal foundation models is bottlenecked by negative transfer: the simultaneous co-training of disparate partial differential equation (PDE) regimes can induce gradient conflict, unstable optimization, and plasticity loss in dense neural operator...
- Text Knows What, Tables Know When: Clinical Timeline Reconstruction via Retrieval-Augmented Multimodal Alignment
Reconstructing precise clinical timelines is essential for modeling patient trajectories and forecasting risk in complex, heterogeneous conditions like sepsis. While unstructured clinical narratives offer semantically rich and contextually complete descriptions of a patient's course, they often lack...
- MeMo: Memory as a Model
Large language models (LLMs) achieve strong performance across a wide range of tasks, but remain frozen after pretraining until subsequent updates. Many real-world applications require timely, domain-specific information, motivating the need for efficient mechanisms to incorporate new knowledge. In ...
- Self-Distilled Agentic Reinforcement Learning
Reinforcement learning (RL) has emerged as a central paradigm for post-training LLM agents, yet its trajectory-level reward signal provides only coarse supervision for long-horizon interaction. On-Policy Self-Distillation (OPSD) complements RL by introducing dense token-level guidance from a teacher...
- RoSHAP: A Distributional Framework and Robust Metric for Stable Feature Attribution
Feature attribution analysis is critical for interpreting machine learning models and supporting reliable data-driven decisions. However, feature attribution measures often exhibit stochastic variation: different train--test splits, random seeds, or model-fitting procedures can produce substantially...
- Widening the Gap: Exploiting LLM Quantization via Outlier Injection
LLM quantization has become essential for memory-efficient deployment. Recent work has shown that quantization schemes can pose critical security risks: an adversary may release a model that appears benign in full precision but exhibits malicious behavior once quantized by users. However, existing q...
- Forgetting That Sticks: Quantization-Permanent Unlearning via Circuit Attribution
Standard unlearning evaluations measure behavioral suppression in full precision, immediately after training, despite every deployed language model being quantized first. Recent work has shown that 4-bit post-training quantization can reverse machine unlearning; we show this is not a tuning artefact...
- Learning from Language Feedback via Variational Policy Distillation
Reinforcement learning from verifiable rewards (RLVR) suffers from sparse outcome signals, creating severe exploration bottlenecks on complex reasoning tasks. Recent on-policy self-distillation methods attempt to address this by utilizing language feedback to generate dense, token-level supervision....
- Novel Dynamic Batch-Sensitive Adam Optimiser for Vehicular Accident Injury Severity Prediction
The choice of optimiser is important in deep learning, as it strongly influences model efficiency and speed of convergence. However, many commonly used optimisers encounter difficulties when applied to imbalanced and sequential datasets, limiting their ability to capture patterns of minority classes...