127,664Total entries

60Added by human

127,604Found by agent

13Categories

Knowledge catalogue

Search: “research”

39,575 results

Research

Transferable Graph Metanetworks

DGX agent

arXiv:2610.00420v1 Announce Type: cross Abstract: A weight space network (or metanetwork) takes the weights of another neural network as input and predicts properties of it. Most prior work trains suc

researcharxiv-cs-lg

2 Oct 2026

Research

Uncertainty-Aware Learning from Multi-Expert Interval Targets

DGX agent

arXiv:2610.00102v1 Announce Type: new Abstract: Many machine learning (ML) applications rely on expert labels, and qualified experts may provide different but plausible interpretations of the same obs

Search: “research”

Transferable Graph Metanetworks

Uncertainty-Aware Learning from Multi-Expert Interval Targets

Understanding Latent Diffusability via Fisher Geometry

UniGuardian: A Unified Defense for Detecting Prompt Injection, Backdoor Attacks and Adversarial Attacks in Large Language Models

Universal Byte-Level Encoding: UTF-8/UTF-16 Routing to Reduce Cross-Script Token-Budget Disparities

VANDAM: Viewing a nucleotide sequence with DNA molecular priors

Variational Streaming Flow: Probabilistic Forecasting in Physical Time

VASC: Value-Aware Sparse Attention with Cross-Layer Memory for Efficient 3D Reconstruction

Verbalized and Internal Probabilities Are Coupled in Large Language Models

VETO: Video Efficient Token Optimization for Vision Language Models

VideoSTF: Stress-Testing Output Repetition in Video Large Language Models

VITA: A Multi-Source Vicinal Transfer Augmentation Method for Out-of-Distribution Generalization

VTV-FM: Flow Matching through Variational Terminal-Velocity Closure

Wasserstein Gradient Flows and Forward-Only Diffusion Are Not Enough for Multimodal Sampling

Watch Your Speech: Text-aware Video-to-Speech Synthesis with Textual Conditioning

Weighted Data Selection: Sharp Upper-Half and Five-Dimensional Laws

We'll be spending a lot more time trying to understand the outputs of language models. A few thoughts, tips & tricks: Writing. Something I'v…

What Can Analogy Tell Us About Artificial Consciousness?

What Makes Something Hard(er)? Explaining Question Difficulty in Natural Language

When Do Attention-Head Ablations Support Causal Claims? Projection-Level Confounds, Floor Effects, and Matched Controls

When Does Exercise-Specific Joint Selection Help? An Audit of Evaluation and Control Design

When More Data Is Not Enough: The Context-Sufficiency Frontier in Generative AI Personalization

When Text-to-Image Helps Editing: The Effects of Conditioning During Denoising

When the AI Leaves the Tailorshop: Measuring What an LLM Advisor Leaves Behind in Complex Problem Solving

Which LLM to pick? Online Active Model Selection for Large Language Models

WIPSNet: Deep Learning for Paediatric Wheeze Detection from Overnight Impedance Pneumography

XOR-Trellis: Ultra-Low-Complexity Dequantization and Curvature-Aware Hadamard-Free LLM Quantization

Zero Flux: Flow-Based Comparison of High-Dimensional Discrete Distributions

A Data-Free Physics-Informed Neural Operator for Level-Set Interface Advection

A differentiability framework for zigzag persistent homology via linear interpolation

A Flow Matching Algorithm for Many-Shot Adaptation to Unseen Distributions

A Generalisation Signal Need Not Be a Model-Selection Signal

A Generalizable and Explainable Framework for Synthetic Video Detection Using First-Digit Gradient Statistics

A library for differentiable signal processing and machine learning on the sphere

A Moving-Horizon Approximate Branch-and-Reduce Method for Deep Classification Trees

A polynomial time algebraic solution to exact marginal inference in Markov Random Field models

A strategic roadmap for an atomistic machine-learning ecosystem

A Tilted Bowl Is Not a Slippery Slope: Compressing Looped Models

Acceleration of Diffusion Language Model through Discrete Average Generator

Adaptive Self-Consistency: From Black-Box Sampling to Distribution-Valued Feedback

Adaptive Spectral Feature Forecasting for Diffusion Sampling Acceleration

Airfoil2Vec: Spectral Geometry-Conditioned Neural Surrogate Models for Airfoil Aerodynamics and a Downforce-Generating CFD Dataset

Algorithmic Recourse Under Competition

Aligning Thoughts with Answers: Probability Rewards to Tame Thinking Drift

Alleviating Hallucination in Reasoning Tasks with Training-Free Uncertainty-Guided Steering

Also Small Models Can Reasonably Self-Evaluate Their Confidence

Amortized Bayesian Inference on Multilevel Models of Arbitrary Structure

An Uncertainty-Guided Digital Twin Framework for Online Adaptive Proton Therapy in Head and Neck Cancer: A Feasibility Study