seq2cause: One Autoregressive Backbone, Four Causal Discovery Tasks in Event Sequences
Research
Research News
New papers, breakthroughs and academic AI research
Fracast-0: Fractal Weight Sharing for a Time Series Foundation Model with Only 85K Parameters
Research
READ-Bench: Benchmarking Historical Instance Retrieval for Time-Series Diagnosis
Research
PastForward: Faster On-Device GUI Agents via Computational Experience Reuse
Research
What does FFN compression change downstream? Same-state causal restoration in diffusion language models
Research
Statistical Testing for Multiple Instance Learning via Selective Inference with Applications to Computational Pathology
Research
Medium-Term Multi-Resolution Electric Load Forecasting using Economic Data and Foundation Model
Research
OmniFysics-Captioner Technical Report: Grounding Omni-Modal Understanding in the Physical World for Better Captioning
Research
Does Joint-Embedding Predictive Architecture Pretraining Help Time Series Forecasting?
Research
Autonomous Research Project Management as an Agent Skill: A Case Study in Exact Spectral Spatial Regression
Research
AI Harness: Certification under Proposal-Conditioned Information for Foundation-Model Agents
Research
CoMemBench: Benchmarking Collaborative Memory Boundaries across Multi-Agent Workflow Topologies
Research