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 storiesSpreadsheetBench 2: Evaluating Agents on End-to-End Business Spreadsheet Workflows
Spreadsheets are widely used for business analysis, financial modeling, reporting, and decision-making. However, most existing spreadsheet benchmarks evaluate i…
Variance Reduction on the Camera Axis: Multi-View Score Distillation for 3D
Score distillation turns a pretrained 2D diffusion model into a 3D generator, but the per-step gradient is estimated from a single randomly chosen view: it is h…
A multi-architecture study of specificity refinement and false-positive mechanism analysis in prostate MRI
Objectives: To characterize residual false positives in prostate MRI detection, and to evaluate a lightweight post-hoc refinement head for case-level specificit…
Rigel: Self-Distilled Score Adaptation for Image and Video Captioning Evaluation
Automatic evaluation of image and video captioning is essential for benchmarking multimodal systems, although standard evaluation metrics show limited alignment…
Parametric Skills
Since intelligence fundamentally relies on efficient skill acquisition (Chollet, 2019), the ability to leverage skills is critical. For LLMs, skills, manually a…
Monte Carlo Energy Aggregation for Mobile 3D Gaussian Splatting
Recent advances in 3D Gaussian Splatting have demonstrated unprecedented success in novel view synthesis. However, the substantial inference and storage overhea…
OmniDance: Multimodal Driven Dance Video Generation with Large-scale Internet Data
Music-driven dance video generation aims to synthesize expressive human motion that is temporally aligned with music while maintaining high visual fidelity. Des…
Data-Driven Energy-Based Learning via Gibbs Measures on Hierarchical Structures
We introduce a data-driven probabilistic framework for learning systems based on Gibbs measures on hierarchical structures. Unlike standard empirical risk minim…
Neural Subspace Reallocation: Continual Learning as Retrieval-Based Subspace Memory Management
We introduce Neural Subspace Reallocation (NSR), which reframes continual learning as memory management over parameter subspaces. Instead of treating Low-Rank A…
Information Dynamics of Language Communication
Quantifying how meaning propagates through communicative exchanges remains underdeveloped in computational linguistics. Here we introduce an information-theoret…
SciIR: A Large-scale Training Dataset and Benchmark for Scientific Image Reasoning Generation
While Text-to-Image (T2I) models have shown remarkable success in generating photorealistic visual content, they still struggle with the rigorous semantic align…
A Dual-domain Refinement Network with FBP-based Jacobian Learning for Sparse-view Dual-Energy CT Material Decomposition
Dual-energy CT (DECT) exploits attenuation differences across different X-ray spectra to provide richer material information and has been widely used in medical…
The Many-Body Problem of the Data Centre
Modern Artificial Intelligence is often framed as limited by its own disembodiment, as if giving it a body would unlock its true potential. We argue to the cont…
Grounding LLM Reasoning under Incomplete Graph Evidence
Knowledge graphs can guide large language models (LLMs) reasoning, but the graph seen by a system is usually a retrieved, linked, temporally scoped, and incompl…
Curvature-Guided Sheaf Diffusion for Unsupervised Community Detection on Heterophilic Graphs
Detecting communities in heterophilic graphs -- where connected nodes often belong to different classes -- is hard for unsupervised methods: classical modularit…
Defending Against Harmful Supervision Hidden in Benign Samples
Existing defenses are effective when harmful content is explicitly mixed into downstream fine-tuning data, but crafted samples can instead hide harmful supervis…
PromptGNN-sim: Deep Fusion and Alignment of GNN and LLMs for Text-Attributed Graph Learning
Text-Attributed Graphs (TAGs) combine textual semantics with graph structure and are central to many graph learning tasks. However, existing fusion methods ofte…
Always-OnAgents:A Survey of Persistent Memory, State, and Governance in LLMAgents
Always-on agents are systems whose future behavior depends on durable state accumulated across earlier interactions. We treat them as persistent-state systems: …
Toward an Energy-Optimized Operation of Data Centers Located in Wind Farms Using Reinforcement Learning
This paper studies Reinforcement Learning as an online controller for curtailment-aware workload shifting in wind-turbine-integrated high-performance computing …
MCP Server Architecture Patterns for LLM-Integrated Applications
The Model Context Protocol (MCP), introduced by Anthropic in November 2024, defines a standardized interface for connecting large language models (LLMs) to exte…
Optimizing Image Preparation and Compression for Face Recognition within 1024 Bytes
ICAO-compliant machine readable travel documents enable automated biometric face verification. The biometric reference is stored on an RFID chip included in for…
UniGP: Taming Diffusion Transformer for Prior-Preserved Unified Generation and Perception
Recent advances in diffusion models have shown impressive performance in controllable image generation and dense prediction tasks. However, existing approaches …
FlexTab: A Flexible Encoder-Decoder Architecture for In-Context Learning Across Diverse Tabular Tasks
We introduce FlexTab, a flexible encoder-decoder architecture for in-context learning on tabular data that pairs a single, task-agnostic encoder with a suite of…
A Classifier-Agnostic Zero-Shot Adversarial Attack Detection via CLIP
Adversarial attacks pose a challenge to the reliability of deep learning models, motivating effective detection methods. Existing techniques often rely on attac…
Residual-Guided Expert Specialization for Incomplete Multimodal Learning
As real-world prediction systems often face missing modalities at inference, incomplete multimodal learning (IML) remains a practical challenge. While prior met…
Scalar Representations of Neural Network Training Dynamics
Training in artificial neural networks can be viewed as a trajectory evolving through a high-dimensional loss landscape. However, the large number of trainable …
SGD Provably Prioritizes a Shortcut Spurious Feature in the XOR Model
Neural networks are known to be susceptible to over-reliance on spurious correlations. However, the precise mechanism by which models exploit shortcut features …
Curvature-Weighted Gradient Diversity: A Noise Measure for Geometry-Adaptive SGD Schedules
The standard convergence analysis of mini-batch stochastic gradient descent (SGD) models gradient noise using a single variance term that treats all parameter d…
StereoGS: Sparse-View 3D Gaussian Splatting via Stereo Priors
3D Gaussian Splatting (3DGS) has achieved remarkable success in real-time novel view synthesis, yet it suffers from severe overfitting under sparse-view setting…
The Fundamental Limits of Valid Transport Map Estimation
Many modern generative modeling methods, including diffusion models, normalizing flows, and flow matching, estimate transport maps or plans between distribution…