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

Research

Curated daily papers, lab research blogs and national AI research programs across the US, China, EU, UK, Japan and beyond.

Curated daily papers, lab research blogs and national AI research programs across the US, China, EU, UK, Japan and beyond.

Latest in Research

30 stories
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…

Native space based pipelines outperform template space based pipeline in subcortical segmentation
Research

Native space based pipelines outperform template space based pipeline in subcortical segmentation

Accurate segmentation of subcortical regions is critical for neurosurgical planning and functional research. Most automated methods rely on template space coreg…

Adversarial Domain Prompt Tuning and Generation for Single Domain Generalization
Research

Adversarial Domain Prompt Tuning and Generation for Single Domain Generalization

Single domain generalization (SDG) aims to learn a robust model, which could perform well on many unseen domains while there is only one single domain available…

Training the Orchestrator: A Supervised Approach to End-to-End PDDL Planning with LLM Agents
Research

Training the Orchestrator: A Supervised Approach to End-to-End PDDL Planning with LLM Agents

Translating natural-language planning intent into verified plans is a longstanding challenge: people communicate goals in language, while classical planners req…

Reliability-Guided Adaptive Ensembling for Robust Test-Time Adaptation
Research

Reliability-Guided Adaptive Ensembling for Robust Test-Time Adaptation

Test-time adaptation (TTA) can mitigate domain shift without source data, but it is highly brittle under adversarially contaminated test streams, where corrupte…

Enhancing Road Safety: An IoT-Based Accident Detection and Prevention Mechanism
Research

Enhancing Road Safety: An IoT-Based Accident Detection and Prevention Mechanism

Road traffic accidents remain a critical global crisis, consistently serving as a primary driver of preventable mortality and severe injury. These incidents are…

Curvature-Adaptive Consistency Flow Matching: Autonomous Trajectory Optimization via Reinforcement Learning
Research

Curvature-Adaptive Consistency Flow Matching: Autonomous Trajectory Optimization via Reinforcement Learning

Consistency distillation has significantly accelerated the inference of diffusion models. In this work, we reveal an intriguing asymmetry: while Logit-Normal sa…

Code Isn't Memory: A Structural Codebase Index Inside a Coding Agent
Research

Code Isn't Memory: A Structural Codebase Index Inside a Coding Agent

Coding agents now interleave LLMs with retrieval over the working repository, and retrieval implementations vary widely across deployed harnesses. Inside a fixe…

Curvature-aware 3D length estimation of greenhouse cucumbers using RGB-D imaging and cubic spline arc-length integration
Research

Curvature-aware 3D length estimation of greenhouse cucumbers using RGB-D imaging and cubic spline arc-length integration

Commercial greenhouse cucumber production is graded by fruit length, which drives harvest scheduling, labour allocation, and logistics. Manual measurement with …

Projection-Volume Fidelity Divergence: Diagnosing and Controlling Optimization Drift in Sparse-View 3D Gaussian Tomography
Research

Projection-Volume Fidelity Divergence: Diagnosing and Controlling Optimization Drift in Sparse-View 3D Gaussian Tomography

Sparse-view computed tomography is a severely ill-posed inverse problem, where recent 3D Gaussian Splatting methods offer an efficient explicit representation f…

Automated sign detection across the Electronic Babylonian Library: A large-scale dataset and end-to-end cuneiform OCR pipeline
Research

Automated sign detection across the Electronic Babylonian Library: A large-scale dataset and end-to-end cuneiform OCR pipeline

Learning to read cuneiform tablets is an extremely demanding task; consequently, of the roughly half million excavated tablets, only a small fraction has been a…

Federated Learning for Global Carbon Emission Forecasting: A Hybrid Time-Series Approach with Statistical and Neural Models
Research

Federated Learning for Global Carbon Emission Forecasting: A Hybrid Time-Series Approach with Statistical and Neural Models

Climate change, primarily driven by carbon dioxide (CO2) emissions, requires accurate forecasting tools to support effective mitigation policies and sustainable…

4DVLT: Dynamic Scene Understanding with Worldline-Centered Vision-Language Tracking
Research

4DVLT: Dynamic Scene Understanding with Worldline-Centered Vision-Language Tracking

4D dynamic scene understanding requires grounding language to a persistent worldline that binds identity, metric 3D motion, and synchronized multi-view 2D proje…

Physiology-Aware CNN and Zero-Shot Multimodal LLMs for ECG Image Classification: A Comparative Study
Research

Physiology-Aware CNN and Zero-Shot Multimodal LLMs for ECG Image Classification: A Comparative Study

Multimodal large language models (LLMs) are increasingly adopted to interpret 12-lead ECG images, though the interpretations often lack validation. However, ECG…

Scene-agnostic ALS boresight self-calibration
Research

Scene-agnostic ALS boresight self-calibration

ALS boresight calibration has relied for two decades on dedicated flight patterns over structured scenes containing planar surfaces of varied aspect and slope. …

Autonomous Subsea Cable Search and Tracking with Graph-Optimised Priors and Visual Tracking
Research

Autonomous Subsea Cable Search and Tracking with Graph-Optimised Priors and Visual Tracking

Global communications rely on subsea cable infrastructure that remains vulnerable to damage from natural hazards and human activity. Autonomous underwater vehic…

AI Exposure Scores: what they measure, what they miss, and what comes next
Research

AI Exposure Scores: what they measure, what they miss, and what comes next

A set of exposure scores calculated in 2023 has become a central empirical input to the future of work debate. Produced by Eloundou et al. (2023) and referred t…

Semantic Browsing: Controllable Diversity for Image Generation
Research

Semantic Browsing: Controllable Diversity for Image Generation

Modern text-to-image models excel in visual fidelity and prompt adherence. However, this strict adherence comes at the cost of diversity: generated samples tend…

Breaking the Filter Bubble: A Semantic Pareto-DQN Framework for Multi-Objective Recommendation
Research

Breaking the Filter Bubble: A Semantic Pareto-DQN Framework for Multi-Objective Recommendation

Recommender systems often induce filter bubbles and semantic homogenization by monolithically optimizing for immediate user engagement. Standard single-objectiv…

Selective Capability Unlearning in End-to-End Spoken Language Understanding
Research

Selective Capability Unlearning in End-to-End Spoken Language Understanding

Modern spoken language understanding (SLU) systems are increasingly deployed in real-world settings, where specific functionalities may need to be removed due t…

Universal Guideline-Driven Image Clustering via a Hybrid LLM Agent
Research

Universal Guideline-Driven Image Clustering via a Hybrid LLM Agent

Unifying image clustering across different clustering scenarios remains challenging due to fundamental gaps among tasks. We introduce a Guideline-Driven Image C…