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
NeuralMUSIC: A Hybrid Neural-Subspace Framework for Robot Sound Source Localization
Research

NeuralMUSIC: A Hybrid Neural-Subspace Framework for Robot Sound Source Localization

Reliable sound source localization is fundamental to robot audition, enabling autonomous robots to perceive spatial cues and operate effectively in dynamic envi…

EARS: Explanatory Abstention for Reliable Sub-Agent Modeling in Large-scale Multi-Agent Systems
Research

EARS: Explanatory Abstention for Reliable Sub-Agent Modeling in Large-scale Multi-Agent Systems

In large-scale enterprise settings, centralized multi-agent systems (MAS) are increasingly adopted, in which a coordinator delegates user requests to lightweigh…

UniTemp: Unlocking Video Generation in Any Temporal Order via Bidirectional Distillation
Research

UniTemp: Unlocking Video Generation in Any Temporal Order via Bidirectional Distillation

Autoregressive video diffusion models have emerged as a promising approach for long video generation, achieving strong performance in streaming settings. Howeve…

LLMs Struggle to Measure What Distinguishes Students of Different Proficiency Levels: A Study of Item Discrimination in Reading Comprehension Assessment
Research

LLMs Struggle to Measure What Distinguishes Students of Different Proficiency Levels: A Study of Item Discrimination in Reading Comprehension Assessment

Item discrimination is a fundamental psychometric property of educational assessment, which measures whether an item meaningfully distinguishes students with hi…

Trainable Photonic Measurement for Physics-Informed PDE Learning
Research

Trainable Photonic Measurement for Physics-Informed PDE Learning

Photonic quantum machine learning offers a route to trainable physical representations built from phase, interference and measurement. However, its role in scie…

LegalWorld: A Life-Cycle Interactive Environment for Legal Agents
Research

LegalWorld: A Life-Cycle Interactive Environment for Legal Agents

Civil litigation is inherently a life-cycle process: what a lawyer drafts on day one constrains what unfolds at trial months later. Yet existing legal benchmark…

SMART: A Flexible, Interpretable, and Scalable Spatio-temporal Brain Atlas from High-Resolution Imaging Data
Research

SMART: A Flexible, Interpretable, and Scalable Spatio-temporal Brain Atlas from High-Resolution Imaging Data

We introduce SMART, a framework for learning a flexible, interpretable, and scalable spatio-temporal brain atlas from longitudinal high-resolution 3D medical im…

SpectralDiT: Timestep-Conditioned Spectral Residual Correction for Flow-Matching DiTs
Research

SpectralDiT: Timestep-Conditioned Spectral Residual Correction for Flow-Matching DiTs

We propose SpectralDiT, a lightweight modification to flow-matching Diffusion Transformers that adds timestep-conditioned spectral correction to the MLP residua…

SHIFT: Semantic Harmonization via Index-side Feature Transformation for Multilingual Information Retrieval
Research

SHIFT: Semantic Harmonization via Index-side Feature Transformation for Multilingual Information Retrieval

With the rapid expansion of massive multilingual corpora, Multilingual Information Retrieval (MLIR) has emerged as a critical technology for global information …

ProfiLLM: Utility-Aligned Agentic User Profiling for Industrial Ride-Hailing Dispatch
Research

ProfiLLM: Utility-Aligned Agentic User Profiling for Industrial Ride-Hailing Dispatch

Bringing Large Language Models (LLMs) into industrial ride-hailing dispatch as semantic feature extractors over platform-scale behavioral logs is a compelling b…

Learning from Own Solutions: Self-Conditioned Credit Assignment for Reinforcement Learning with Verifiable Rewards
Research

Learning from Own Solutions: Self-Conditioned Credit Assignment for Reinforcement Learning with Verifiable Rewards

Reinforcement learning with verifiable rewards (RLVR) has driven substantial progress in training LLMs for reasoning tasks, but representative methods such as G…

Reinforcement Learning Foundation Models Should Already Be A Thing
Research

Reinforcement Learning Foundation Models Should Already Be A Thing

Foundation models for language and vision are powered by internet-scale data, while structured domains (tabular prediction, time-series forecasting, graph learn…

Learning from Your Own Mistakes: Constructing Learnable Micro-Reflective Trajectories for Self-Distillation
Research

Learning from Your Own Mistakes: Constructing Learnable Micro-Reflective Trajectories for Self-Distillation

Self-distillation improves reasoning in large language models by using the model's own rollouts as training signal, typically through implicit logit-level align…

Scaling Learning-based AEB with Massive Unlabeled Data
Research

Scaling Learning-based AEB with Massive Unlabeled Data

This paper studies how to scale learning-based automatic emergency braking (AEB) with massive unlabeled fleet data under production constraints. Our approach is…

SAGE: Stochastic Prompt Optimization via Agent-Guided Exploration
Research

SAGE: Stochastic Prompt Optimization via Agent-Guided Exploration

Context engineering has emerged as a primary lever for improving AI systems without parameter updates. Recent work showing that textual gradients do not functio…

SciRisk-Bench: A Risk-Dimension-Aware Benchmark for AI4Science Safety
Research

SciRisk-Bench: A Risk-Dimension-Aware Benchmark for AI4Science Safety

Large language models (LLMs) are increasingly embedded in AI for Science (AI4Science) workflows, from scientific question answering and literature analysis to l…

SenFlow: Inter-Sentence Flow Modeling for AI-Generated Text Detection in Hybrid Documents
Research

SenFlow: Inter-Sentence Flow Modeling for AI-Generated Text Detection in Hybrid Documents

Sentence-level AI-generated text detection (S-AGTD) for hybrid documents, where humans and LLMs co-author one text, faces two gaps: existing methods classify ea…

Be Your Own Teacher: Steering Protein Language Models via Unsupervised Reward Optimization
Research

Be Your Own Teacher: Steering Protein Language Models via Unsupervised Reward Optimization

Protein language models (PLMs) have emerged as powerful tools for controllable biomolecular design, yet their post-training adaptation typically relies on costl…

A Controlled Benchmark of Quantum-Latent GAN Augmentation for Brain MRI
Research

A Controlled Benchmark of Quantum-Latent GAN Augmentation for Brain MRI

Medical image classification is often constrained by limited labeled data, motivating generative augmentation; recently, quantum generative models have been pro…

FOSC-X: An Extended Framework for Optimal Local Cuts and Non-Horizontal Cluster Selection from Clustering Hierarchies
Research

FOSC-X: An Extended Framework for Optimal Local Cuts and Non-Horizontal Cluster Selection from Clustering Hierarchies

Extracting a flat clustering solution from a hierarchy is a common task in practical cluster analysis and can be formulated as an optimisation problem. Existing…

Visual-OPSD: Cross-Modal On-Policy Self-Distillation for Efficient Unified Multimodal Reasoning
Research

Visual-OPSD: Cross-Modal On-Policy Self-Distillation for Efficient Unified Multimodal Reasoning

Unified multimodal models (UMMs) interleave generated ''visual thoughts'' (VTs) with text reasoning to improve spatial tasks. This incurs roughly an order-of-ma…

G-IdiomAlign: A Gloss-Pivoted Benchmark for Cross-Lingual Idiom Alignment
Research

G-IdiomAlign: A Gloss-Pivoted Benchmark for Cross-Lingual Idiom Alignment

Idioms are difficult to transfer across languages due to their non-compositionality and weak surface-form grounding, making literal mappings unreliable. We pres…

Lifecycle-Aware Dynamic Analysis for Secure ML Model Execution
Research

Lifecycle-Aware Dynamic Analysis for Secure ML Model Execution

The growing reliance on pre-trained Machine Learning (ML) models has introduced new attack surfaces. Recent vulnerabilities demonstrate that malicious behavior …

Which Sections of a Research Paper Best Reveal Its Research Methods? Evidence from Library and Information Science
Research

Which Sections of a Research Paper Best Reveal Its Research Methods? Evidence from Library and Information Science

Research methods are essential carriers of knowledge contribution in academic papers. Automatic multi-label classification of research methods can support knowl…

Structure Over Nonlinearity: Explicit Interaction Architectures for Dynamical Learning
Research

Structure Over Nonlinearity: Explicit Interaction Architectures for Dynamical Learning

Most learning architectures for dynamical systems rely on generic nonlinear function approximation, often requiring high model complexity to capture structured …

Smoothness-Based Derandomization of PAC-Bayes Bounds
Research

Smoothness-Based Derandomization of PAC-Bayes Bounds

We study PAC-Bayes derandomization for smooth loss functions. Our goal is to obtain generalization bounds that hold with high probability for deterministic pred…

JourneyFormer: Encoding Airbnb Guest Journey with Sequence Modeling
Research

JourneyFormer: Encoding Airbnb Guest Journey with Sequence Modeling

Sequence modeling has become increasingly popular in recommendation and ranking algorithms, owing to its capacity to model users' historical behaviors and infer…

Towards an Agent-First Web: Redesigning the Web for AI Agents
Research

Towards an Agent-First Web: Redesigning the Web for AI Agents

The World Wide Web was built on an assumption held for three decades: the primary consumer of web content is a human being. This permeates every layer; its acce…

Giskard : Byzantine Robust and Confidential Aggregation for Large-Scale Decentralized Learning
Research

Giskard : Byzantine Robust and Confidential Aggregation for Large-Scale Decentralized Learning

Dealing simultaneously with confidentiality and Byzantine behaviors in decentralized learning is a challenging problem. Indeed, in decentralized learning, clien…

On Local Population-Risk Certificates
Research

On Local Population-Risk Certificates

This paper develops local certificates for population-risk increments around a current model. For a local candidate set \(\mathcal D\), the certificate is a two…