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 storiesLifecycle-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 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
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
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
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
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
Dealing simultaneously with confidentiality and Byzantine behaviors in decentralized learning is a challenging problem. Indeed, in decentralized learning, clien…
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…
AdsMind: A Physics-Grounded Multi-Agent System for Self-Correcting Discovery of Adsorption Configurations on Heterogeneous Catalyst Surfaces
Identifying the lowest-energy surface-adsorbate configuration is critical for modeling heterogeneous catalysis, yet exhaustive exploration with ab initio calcul…
IndicContextEval: A Benchmark for Evaluating Context Utilisation in Audio Large Language Models Across 8 Indic Languages
AudioLLMs enable speech recognition conditioned on textual prompts such as domain descriptions or entity lists. However, it remains unclear whether these models…
Dango: A Strictly L1-Only Large Language Model for Studying Second Language Acquisition
We introduce Dango, a 1.8B-parameter large language model designed for controlled studies of L1-to-L2 (Japanese-to-English) transfer in second language acquisit…
Generalised Eigenvalue Geometry of Semantic Adversarial Attacks
Recent empirical work shows that semantically equivalent paraphrases can fool financial sentiment classifiers: although a paraphrase remains close to the origin…
Machine Unlearning for the XGBoost Model with Network Intrusion Datasets
Machine Unlearning (MU) has emerged as an important technique for removing specific data points from trained models without requiring full retraining. However, …
Mechanism-Guided Selective Unlearning for RLVR-Induced Reasoning
We propose MAST (Mechanism-Aligned Selective Targeting), a mechanism-guided method for unlearning RLVR-induced reasoning with substantially lower collateral dam…
A Human-in-the-Loop Bayesian Optimization Framework for Constraint-Aware Bioprocess Development
This work presents an extension to Pareto Front Guided Sampling (PFGS), a Human-in-the-Loop (HitL) Bayesian Optimization (BO) framework in which Gaussian proces…
Transformer Geometry Observatory TGO-I: Spectral Geometry Observatory
Despite the widespread adoption of Vision Transformers (ViTs) and their success across numerous computer vision applications, the fundamental understanding of t…
Enhancing Decision-Making with Large Language Models through Multi-Agent Fictitious Play
Large language model (LLM)-based multi-agent systems (MAS) have demonstrated great potential in solving tasks with execution complexity, by distributing subtask…
Diffusion-Proof: Recipe for Formal Theorem Proving Beyond Auto-Regressive Generation
Enhancing the formal math reasoning capabilities of Large Language Models (LLMs) has become a key focus in both mathematical and computer science communities in…
Explaining Attention with Program Synthesis
A longstanding goal of research on interpretable deep learning is to replace opaque neural computations with human-meaningful symbolic descriptions. In this pap…
Data Intelligence Agents: Interpreting, Modeling, and Querying Enterprise Data via Autonomous Coding Agents
Production data integration is bottlenecked by repeated, lossy handoffs between data owners, engineers, and analysts who must collaboratively discover, structur…
Reference-Driven Multi-Speaker Audio Scene Generation from In-the-Wild Priors
Existing multi-speaker dialogue systems bind speakers to utterances through structured supervision: per-turn tags, multi-stream transcriptions, or learnable spe…
Rethinking Reward Supervision: Rubric-Conditioned Self-Distillation
Post-training of reasoning language models is commonly driven by supervised distillation and reinforcement learning with verifiable rewards. Distillation often …
The Chandra-Gaia Catalog of Counterparts: Resolving ambiguous Gaia matches to X-ray sources in the Chandra Source Catalog using Machine Learning
We present a framework to cross-match sources from the Chandra Source Catalog (CSC v2.1) with optical sources from Gaia Data Release 3. Unlike purely spatial ap…
State of the blog, mid-2026
About 3 years since I started writing weekly.…
Frontier post-training recipe review with Finbarr Timbers
"Interview" #18…
Import AI 461: "Alignment is not on track"; FrontierCode; and synthetic research interns
Where are your agents right now?…
Welcome to the AGI era of AI governance
It's a one-way door and we weren't ready for it.…
Ire identifies another LOTUSLITE specimen
Project Ire examined a timely malware sample and determined its intent through reverse engineering—identifying LOTUSLITE characteristics even as most major EDR …
Scaling Up Reinforcement Learning for Traffic Smoothing: A 100-AV Highway Deployment
Training Diffusion Models with Reinforcement Learning We deployed 100 reinforcement learning (RL)-controlled cars into rush-hour highway traffic to smooth conge…
Repurposing Protein Folding Models for Generation with Latent Diffusion
PLAID is a multimodal generative model that simultaneously generates protein 1D sequence and 3D structure, by learning the latent space of protein folding model…