SIGNAL
Tracking the global AI frontier — labs · research · agents · policy
Frontier Signal

Briefing

The fast feed: breaking AI news from the global tech press, deduplicated and time-ordered.

The fast feed: breaking AI news from the global tech press, deduplicated and time-ordered.

Latest in Briefing

30 stories
Not All Claims Are Equally Risky: FACTOR for Adaptive Verification in Factual Long-Form Generation
Research

Not All Claims Are Equally Risky: FACTOR for Adaptive Verification in Factual Long-Form Generation

Large Language Models (LLMs) generate fluent long-form text, however, often add unsupported factual claims. Existing verification techniques improve factuality …

ROMEVA: Geometry-Preserving Vocabulary Expansion for Roman Urdu Language Models
Research

ROMEVA: Geometry-Preserving Vocabulary Expansion for Roman Urdu Language Models

Multilingual Language Models like mBERT are widely used for low-resource NLP, yet their adaptation to morphologically inconsistent languages such as Roman Urdu …

FetSelect: Task-Specific Architectures and Self-Supervised Learning for Automated Fetal Ultrasound Frame Selection
Research

FetSelect: Task-Specific Architectures and Self-Supervised Learning for Automated Fetal Ultrasound Frame Selection

Automated frame selection for fetal biometry remains under addressed, with most prior work targeting generic quality assessment or downstream measurement pipeli…

Generative Relightable Avatars
Research

Generative Relightable Avatars

We present Generative Relightable Avatars (GRA), a person-specific method for photorealistic free-view rendering and environment-map relighting of full-body hum…

Joint Air Traffic Flow and Capacity Management via Answer Set Programming
Research

Joint Air Traffic Flow and Capacity Management via Answer Set Programming

Operational Air Traffic Flow and Capacity Management (ATFCM) balances flight demand with available sector capacity, to ensure safe and efficient operations. Mat…

AdaReP:Adaptive Re-Planning under Model Mismatch for Neural World-Model Predictive Control
Research

AdaReP:Adaptive Re-Planning under Model Mismatch for Neural World-Model Predictive Control

Neural world models coupled with model predictive control (MPC) replan at every environment step to bound accumulated prediction error, but this incurs substant…

A Matter of Time: Towards a General Theory of Agency
Research

A Matter of Time: Towards a General Theory of Agency

Agency is often invoked in research on philosophy, biology, and cognitive science without a clear account of how it originates from material organization. Build…

Automated Semantic Fault Localization in SysML v2: A Human-in-the-Loop Framework Using Knowledge-Graph Augmented LLMs
Research

Automated Semantic Fault Localization in SysML v2: A Human-in-the-Loop Framework Using Knowledge-Graph Augmented LLMs

SysML v2's textual syntax enables compiler-based validation of model structure and language conformance. However, semantic mistakes that preserve syntactic vali…

Leveraging Similarities in Multi-Armed Bandits
Research

Leveraging Similarities in Multi-Armed Bandits

In many online learning and bandit problems, the actions we consider possess inherent similarities--for instance because they share latent traits, tags, or hier…

Selective Time Series Forecasting via Metalearning
Research

Selective Time Series Forecasting via Metalearning

Deep learning methods have achieved state-of-the-art in time series forecasting, yet their accuracy varies considerably across samples, as some instances remain…

SPIRAL: Learning to Search and Aggregate
Research

SPIRAL: Learning to Search and Aggregate

Language model reasoning can be substantially improved at test time via scaffolds that scale inference compute across different primitives -- sequential reasoni…

Sentence-Level Contextual Entrainment in Large Language Models
Research

Sentence-Level Contextual Entrainment in Large Language Models

Contextual entrainment, which is a newly discovered phenomenon in large language models (LLMs), refers to the tendency of a model to assign higher probabilities…

Flood Mapping from RGB imagery using a Vision Foundation Model
Research

Flood Mapping from RGB imagery using a Vision Foundation Model

Timely, high-resolution maps of flood extent around settlements are essential for emergency response and damage assessment. We consider airborne RGB imagery for…

A Dual Edge Spatial Jacobian Image Graph for Interpretable Diabetic Retinopathy Grading
Research

A Dual Edge Spatial Jacobian Image Graph for Interpretable Diabetic Retinopathy Grading

Automated diabetic retinopathy (DR) grading from colour fundus photographs can achieve strong predictive performance, but clinical interpretation requires more …

EERLoss: A Novel Loss Function for Training Deep Biometric Models. A Case Study in Keystroke Dynamics
Research

EERLoss: A Novel Loss Function for Training Deep Biometric Models. A Case Study in Keystroke Dynamics

Deep learning approaches to biometric verification are commonly trained by optimizing indirect objectives, creating a misalignment between the optimization proc…

Cost-Optimal Decision Diagrams for Stochastic Boolean Function Evaluation
Research

Cost-Optimal Decision Diagrams for Stochastic Boolean Function Evaluation

In many decision-making scenarios, acquiring information incurs different costs. We consider the problem of constructing a deterministic evaluation strategy tha…

OrbitForge: Text-to-3D Scene Generation via Reconstruction-Anchored Video Synthesis
Research

OrbitForge: Text-to-3D Scene Generation via Reconstruction-Anchored Video Synthesis

Generic text-to-video models can be used as rich open-world scene priors. Despite the high quality of today's generated videos, they do not directly yield relia…

Real vs. Complex Spectral Bases for Neural Operators: The Role of Green's Function Alignment
Research

Real vs. Complex Spectral Bases for Neural Operators: The Role of Green's Function Alignment

Fourier Neural Operators (FNO) learn solution operators of partial differential equations by parameterizing global convolutions in the complex Fourier domain. F…

Cage-based Texture Transfer with Geometric Filtering
Research

Cage-based Texture Transfer with Geometric Filtering

Real-time texture transfer expands the creative horizon for interactive applications, enabling seamless detail projection in scenarios that range from digital c…

MJEPA: A Simple and Scalable Joint-Embedding Predictive Architecture for Audio-Visual Learning
Research

MJEPA: A Simple and Scalable Joint-Embedding Predictive Architecture for Audio-Visual Learning

Self-supervised learning from large-scale video data has emerged as a dominant paradigm for visual representation learning. Since audio and visual streams natur…

Communicability-Inspired Positional Encoding (CIPE)
Research

Communicability-Inspired Positional Encoding (CIPE)

Positional encodings (PEs) are essential for Transformers. Yet designing effective PEs for non-Euclidean graphs remains challenging. Such encodings should ideal…

Sarashina2.2-TTS: Tackling Kanji Polyphony in Japanese Speech Generation via Data Scaling and Targeted Data Synthesis
Research

Sarashina2.2-TTS: Tackling Kanji Polyphony in Japanese Speech Generation via Data Scaling and Targeted Data Synthesis

While large language model (LLM)-based text-to-speech (TTS) systems have achieved high-quality speech synthesis, most existing systems focus on English and Chin…

Conformal Recovery-Deadline Certificates for Runtime Assurance of Adapting Controllers
Research

Conformal Recovery-Deadline Certificates for Runtime Assurance of Adapting Controllers

Runtime assurance (RTA) protects a safety-critical system by switching from an advanced controller to a verified safe controller when a monitored condition is v…

DFMU: Data-Frugal Machine Unlearning
Research

DFMU: Data-Frugal Machine Unlearning

Machine unlearning is an emerging domain that ensures the safe removal of elements (includes concepts, attributes, entity and class) from the trained model alon…

PolicyAlign: Direct Policy-Based Safety Alignment for Large Language Models
Research

PolicyAlign: Direct Policy-Based Safety Alignment for Large Language Models

Safety alignment of large language models (LLMs) typically depends on high-quality supervision data, such as safe demonstrations or preference pairs. However, i…

Does Translation-Enhanced Speech Encoder Pre-training Affect Speech LLMs?
Research

Does Translation-Enhanced Speech Encoder Pre-training Affect Speech LLMs?

Connecting a pre-trained speech encoder to a Large Language Model (LLM) is the standard architecture for building Speech LLMs. However, a structural misalignmen…

Overview of HIPE-2026: Person-Place Relation Extraction from Multilingual Historical Texts
Research

Overview of HIPE-2026: Person-Place Relation Extraction from Multilingual Historical Texts

Was this person ever at that place, and if so, when? Answering such questions from noisy, multilingual historical documents is the central challenge of HIPE-202…

Otter Weather: Skillful and Computationally Efficient Medium-Range Weather Forecasting
Research

Otter Weather: Skillful and Computationally Efficient Medium-Range Weather Forecasting

State-of-the-art medium-range AI weather models can outperform traditional Numerical Weather Prediction (NWP) but require massive training budgets. This restric…

From Hallucination to Grounding: Diagnosing Visual Spatial Intelligence via CRISP
Research

From Hallucination to Grounding: Diagnosing Visual Spatial Intelligence via CRISP

Current VLM evaluations often conflate language priors with genuine spatial reasoning. To address this, we introduce CRISP, a novel structural-diagnostic evalua…

Extracting Neural Materials from Multi-view Images
Research

Extracting Neural Materials from Multi-view Images

Neural materials can represent complex specular reflections and scattering effects in a compact, universal basis. However, acquiring and authoring such material…