Machine Learning

UMKC Announces New Master of Science in Artificial Intelligence

UMKC announces a new Master of Science in Artificial Intelligence program aimed at addressing workforce demand for AI expertise, set to l...

Improving AI models’ ability to explain their predictions

New technique makes AI models leaner and faster while they’re still learning

[P] Remote sensing foundation models made easy to use.

This project enables the idea of tasking remote sensing models to acquire embeddings like we task satellites to acquire data! https://git...

Can AI truly be creative?

AI has no imagination. “Creativity is the ability to generate novel and valuable ideas or works through the exercise of imagination” http...

AI video generation seems fundamentally more expensive than text, not just less optimized

There’s been a lot of discussion recently about how expensive AI video generation is compared to text, and it feels like this is more tha...

[D] When to transition from simple heuristics to ML models (e.g., DensityFunction)?

Two questions: What are the recommendations around when to transition from a simple heuristic baseline to machine learning ML models for ...

[D] ICML 2026 Average Score

Hi all, I’m curious about the current review dynamics for ICML 2026, especially after the rebuttal phase. For those who are reviewers (or...

[R] VOID: Video Object and Interaction Deletion (physically-consistent video inpainting)

We present VOID, a model for video object removal that aims to handle *physical interactions*, not just appearance. Most existing video i...

FLUX 2 Pro (2026) Sketch to Image

I sketched a cow and tested how different models interpret it into a realistic image for downstream 3D generation, turns out some models ...

[D] TMLR reviews seem more reliable than ICML/NeurIPS/ICLR

This year I submitted a paper to ICML for the first time. I have also experienced the review process at TMLR and ICLR. From my observatio...

[D] icml, no rebuttal ack so far..

Almost all the papers I reviewed have received at least one ack, but I haven’t gotten a single rebuttal acknowledgment yet. Is there anyo...

[2603.29957] Think Anywhere in Code Generation

Abstract page for arXiv paper 2603.29957: Think Anywhere in Code Generation

[2603.17790] The Convergence Frontier: Integrating Machine Learning and High Performance Quantum Computing for Next-Generation Drug Discovery

Abstract page for arXiv paper 2603.17790: The Convergence Frontier: Integrating Machine Learning and High Performance Quantum Computing f...

[2603.16880] NeuroNarrator: A Generalist EEG-to-Text Foundation Model for Clinical Interpretation via Spectro-Spatial Grounding and Temporal State-Space Reasoning

Abstract page for arXiv paper 2603.16880: NeuroNarrator: A Generalist EEG-to-Text Foundation Model for Clinical Interpretation via Spectr...

[2601.14674] LaVR: Scene Latent Conditioned Generative Video Trajectory Re-Rendering using Large 4D Reconstruction Models

Abstract page for arXiv paper 2601.14674: LaVR: Scene Latent Conditioned Generative Video Trajectory Re-Rendering using Large 4D Reconstr...

[2603.12372] Efficient Reasoning with Balanced Thinking

Abstract page for arXiv paper 2603.12372: Efficient Reasoning with Balanced Thinking

[2603.10202] Hybrid Hidden Markov Model for Modeling Equity Excess Growth Rate Dynamics: A Discrete-State Approach with Jump-Diffusion

Abstract page for arXiv paper 2603.10202: Hybrid Hidden Markov Model for Modeling Equity Excess Growth Rate Dynamics: A Discrete-State Ap...

[2512.24420] Virasoro Symmetry in Neural Network Field Theories

Abstract page for arXiv paper 2512.24420: Virasoro Symmetry in Neural Network Field Theories

[2601.10531] Coarsening Causal DAG Models

Abstract page for arXiv paper 2601.10531: Coarsening Causal DAG Models

[2512.21106] Semantic Refinement with LLMs for Graph Representations

Abstract page for arXiv paper 2512.21106: Semantic Refinement with LLMs for Graph Representations

[2512.17585] SkinGenBench: Generative Model and Preprocessing Effects for Synthetic Dermoscopic Augmentation in Melanoma Diagnosis

Abstract page for arXiv paper 2512.17585: SkinGenBench: Generative Model and Preprocessing Effects for Synthetic Dermoscopic Augmentation...

[2512.17466] Linear Attention for Joint Power Optimization and User-Centric Clustering in Cell-Free Networks

Abstract page for arXiv paper 2512.17466: Linear Attention for Joint Power Optimization and User-Centric Clustering in Cell-Free Networks