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 storiesHumanScale: Egocentric Human Video Can Outperform Real-Robot Data for Embodied Pretraining
Embodied foundation models are expected to benefit from data scaling like large language models, but face a much tighter data bottleneck. Teleoperated real-robo…
Import AI 462: Superpersuasion; self-sustaining AI; paths to ASI
How religious are beliefs in the singularity?…
Banning Open Source AI Would Be A Mistake
This post was originally an op-ed co-authored with Kevin Xu of Interconnected for a general, non-technical audience.…
A startup claims it broke through a bottleneck that’s holding back LLMs
Miami-based AI startup Subquadratic came out of stealth mode last month with a huge claim. It announced that it had solved a mathematical bottleneck that had be…
Hierarchical Multi-Modal Retrieval for Knowledge-Grounded News Image Captioning
Traditional image captioning methods often struggle to generate comprehensive, context-rich descriptions, especially for details not directly observable from vi…
Multi-Modal Hyper-Graph Fusion for Low-Light Crowd Counting
Crowd counting is a fundamental task in computer vision. However, crowd counting in low-light environments remains largely underexplored, despite its practical …
Towards Anomaly Detection on Relational Data
Relational databases are widely used for managing structured data in real-world systems. Detecting anomalies from such relational data is crucial for identifyin…
RegMix-D: Dynamic Data Mixing via Proxy Training Trajectories
Data mixture selection is critical for Large Language Model pretraining. Existing methods such as RegMix select a single static mixture by fitting a regression …
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
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
Idioms are difficult to transfer across languages due to their non-compositionality and weak surface-form grounding, making literal mappings unreliable. We pres…