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
Physics-Driven Zero-Shot MRI Reconstruction with Non-local Image Priors
Research

Physics-Driven Zero-Shot MRI Reconstruction with Non-local Image Priors

Zero-Shot Self-Supervised Learning (ZS-SSL) has emerged as a promising paradigm for accelerated Magnetic Resonance Imaging (MRI) reconstruction, eliminating the…

Teacher-Student Structure for Domain Adaptation in Ensemble Audio-Visual Video Deepfake Detection
Research

Teacher-Student Structure for Domain Adaptation in Ensemble Audio-Visual Video Deepfake Detection

The rapid advancement of generative AI models is leading to more realistic deepfake media, encompassing the manipulation of audio, video, or both. This raises s…

CODA-BENCH: Can Code Agents Handle Data-Intensive Tasks?
Research

CODA-BENCH: Can Code Agents Handle Data-Intensive Tasks?

Advanced agents are increasingly demonstrating the potential to operate as autonomous engineers, creating a growing demand for evaluation benchmarks that captur…

Discovering Lattice Reduction Strategies via Self-Play
Research

Discovering Lattice Reduction Strategies via Self-Play

The Lenstra-Lenstra-Lovász (LLL) algorithm is a seminal contribution to computer science used for lattice basis reduction, yet its polynomial-time outputs produ…

Repeated Bilateral Trade: The Quest for Fairness
Research

Repeated Bilateral Trade: The Quest for Fairness

We study repeated bilateral trade from a fairness perspective. At each round, a fresh seller-buyer pair arrives, and the platform posts a price before observing…

Defending against Adaptive Prompt Injection Attacks via Reasoning-enabled Task Alignment
Research

Defending against Adaptive Prompt Injection Attacks via Reasoning-enabled Task Alignment

Indirect prompt injection attacks hijack LLM-based agents by embedding malicious instructions in third-party data that the agent retrieves during task execution…

Localizing Credit at the Divergence: Path-Conditioned Self-Distillation for LLM Reasoning
Research

Localizing Credit at the Divergence: Path-Conditioned Self-Distillation for LLM Reasoning

Reinforcement learning from verifiable rewards assigns a single scalar to each rollout, leaving token-level credit assignment underspecified in long reasoning t…

Mutual Distillation of Dual-Foundation Models for Semi-Supervised PET/CT Segmentation
Research

Mutual Distillation of Dual-Foundation Models for Semi-Supervised PET/CT Segmentation

Organ segmentation from PET/CT is critical for quantitative analysis and radiotherapy planning in oncology. To ease the high annotation cost of PET/CT segmentat…

Mitigating Visual Hallucinations in Multimodal Systems through Retrieval-Augmented Reliability-Aware Inference
Research

Mitigating Visual Hallucinations in Multimodal Systems through Retrieval-Augmented Reliability-Aware Inference

Multimodal large language models (MLLMs) have demonstrated strong capabilities in vision-language understanding and natural-language response generation. Howeve…

Bayesian Networks with Latent Time Embedding for Stage-Aware Causal Modeling of Alzheimer's Disease Progression
Research

Bayesian Networks with Latent Time Embedding for Stage-Aware Causal Modeling of Alzheimer's Disease Progression

Alzheimer's disease (AD) progression is often described through the amyloid-tau-neurodegeneration, or AT(N), cascade. However, most longitudinal models represen…

Auditing Machine Unlearning: A Systematic Research on Whether Models Truly Forget
Research

Auditing Machine Unlearning: A Systematic Research on Whether Models Truly Forget

Machine unlearning has been extensively studied in response to growing privacy concerns and regulatory requirements. However, auditing whether unlearning algori…

Who Should Lead Decoding Now? Tracking Reliable Trajectories for Ensembling Masked Diffusion Language Models
Research

Who Should Lead Decoding Now? Tracking Reliable Trajectories for Ensembling Masked Diffusion Language Models

Masked Diffusion Language Models (MDLMs) have emerged as a distinct paradigm for sequence generation. As MDLMs become diverse in capabilities and knowledge cove…

How Post-Training Shapes Biological Reasoning Models
Research

How Post-Training Shapes Biological Reasoning Models

Scientific reasoning models for biology combine language models with foundation models trained on multimodal biological data, including DNA, RNA, and proteins. …

FusionRS: A Large-Scale RGB-Infrared Remote Sensing Dataset for Dual-Modal Vision-Language Foundation Models
Research

FusionRS: A Large-Scale RGB-Infrared Remote Sensing Dataset for Dual-Modal Vision-Language Foundation Models

Remote sensing vision-language models have advanced Earth observation understanding, but most existing work remains centered on RGB imagery, leaving the complem…

Reconfigurable Computing Challenge: Transformer for Jet Tagging on Versal AI Engines
Research

Reconfigurable Computing Challenge: Transformer for Jet Tagging on Versal AI Engines

Transformer-based models achieve strong performance for jet tagging at the CERN LHC, but deploying them in low-latency, resource-constrained trigger systems is …

An expressivity analysis of hierarchical modelling in deep transformers via bounded-depth grammars
Research

An expressivity analysis of hierarchical modelling in deep transformers via bounded-depth grammars

Deep neural networks are widely believed to derive their expressive power from their ability to form \textbf{hierarchical representations}, capturing progressiv…

Public transit gains and spatially uneven travel demand changes after NYC congestion pricing
Research

Public transit gains and spatially uneven travel demand changes after NYC congestion pricing

New York City implemented the nation's first cordon-based congestion pricing program in January 2025, providing an opportunity to evaluate how system-wide urban…

Enhanced Graph Neural Networks using K-Hop Gaussian Diffusion
Research

Enhanced Graph Neural Networks using K-Hop Gaussian Diffusion

Most graph neural network (GNN) cores rely on graph convolutions, typically implemented as message passing between direct (single-hop) neighbors. In many real-w…

Monotonic Kolmogorov-Arnold Networks: A Theoretical and Empirical Study of Monotonicity as an Inductive Bias
Research

Monotonic Kolmogorov-Arnold Networks: A Theoretical and Empirical Study of Monotonicity as an Inductive Bias

Monotonicity has been a long-running architectural inductive bias for neural networks, motivated by tabular, scientific, and economic settings where outputs are…

ConTex: Reformulating Counterfactual Generation For Time Series Forecasting
Research

ConTex: Reformulating Counterfactual Generation For Time Series Forecasting

Decision-making with deep learning-based time series forecasting requires not only accurate predictions but also actionable insights. However, current architect…

When AI Says "I have been in similar situations": Synthetic Lived Experience in Peer-Like Caregiver Support
Research

When AI Says "I have been in similar situations": Synthetic Lived Experience in Peer-Like Caregiver Support

Caregivers often turn to online communities for informational and emotional support. In these spaces, peer supporters frequently draw on personal narratives to …

Domain Generalizable Adaptation of 3D Vision-Language Models via Regularized Fine-Tuning
Research

Domain Generalizable Adaptation of 3D Vision-Language Models via Regularized Fine-Tuning

Domain adaptation remains a central challenge in 3D vision, especially for multimodal foundation models that align 3D point clouds with visual and textual data.…

Splaxel: Efficient Distributed Training of 3D Gaussian Splatting for Large-scale Scene Reconstruction via Pixel-level Communication
Research

Splaxel: Efficient Distributed Training of 3D Gaussian Splatting for Large-scale Scene Reconstruction via Pixel-level Communication

3D Gaussian Splatting (3DGS) enables high-fidelity and real-time 3D scene reconstruction, but scaling training to large-scale scenes requires optimizing hundred…

BCL: Bayesian In-Context Learning Framework for Information Extraction
Research

BCL: Bayesian In-Context Learning Framework for Information Extraction

Existing information extraction (IE) tasks increasingly adopt in-context learning (ICL) with large language models. However, current approaches either show inco…

PragReST: Self-Reinforcing Counterfactual Reasoning for Pragmatic Language Understanding
Research

PragReST: Self-Reinforcing Counterfactual Reasoning for Pragmatic Language Understanding

Natural language understanding often depends on meanings that are implied rather than explicitly stated, requiring pragmatic reasoning. Despite strong performan…

PEC-Home: Interpretation of Progressively Elliptical Commands in Smart Homes
Research

PEC-Home: Interpretation of Progressively Elliptical Commands in Smart Homes

Recent advancements in Large Language Models (LLMs) have empowered home assistants with natural language interaction capabilities. However, current assistants o…

Gender Bias in LLM Hiring Decisions: Evidence from a Japanese Context and Evaluation of Mitigation Strategies
Research

Gender Bias in LLM Hiring Decisions: Evidence from a Japanese Context and Evaluation of Mitigation Strategies

Large language models (LLMs) are increasingly deployed in hiring workflows, yet most research on gender bias in LLM hiring decisions has focused on English-lang…

The Wrong Kind of Right: Quantifying and Localizing Misfired Alignment in LLMs
Research

The Wrong Kind of Right: Quantifying and Localizing Misfired Alignment in LLMs

Warning: This paper studies stereotypes and biases, and contains potentially disturbing examples, used for illustration purposes only. Our findings should not b…

LandslideAgent with Multimodal LandslideBench: A Domain-Rule-Augmented Agent for Autonomous Landslide Identification and Analysis
Research

LandslideAgent with Multimodal LandslideBench: A Domain-Rule-Augmented Agent for Autonomous Landslide Identification and Analysis

Intelligent landslide hazard interpretation is critical for disaster prevention, yet current paradigms struggle to simultaneously extract visual features and hi…

HandwritingAgent: Language-Driven Handwriting Synthesis in Scalable Vector Space
Research

HandwritingAgent: Language-Driven Handwriting Synthesis in Scalable Vector Space

Teaching machines to emulate natural handwriting styles remains an open challenge, as it requires synthesizing stroke sequences that dynamically vary in shape, …