Fork-and-Flush: Escaping Idea Basins in Autoresearch Agents
Research
Research News
New papers, breakthroughs and academic AI research
VisionWeave: Weaving Elastic Visual Representations as a Native Capability of MLLMs
Research
When Forgetting is not Catastrophic: On the Mechanics of Spurious Forgetting
Research
Interpretable Hypergraph Learning via Neural Additive Models
Research
Evaluation of Active Feature Acquisition Policies with Tabular Foundation Models
Research
StaFIR: Convex Learning of Stationarity-Aware Causal Filters
Research
The Missing Minimal Pair: Stereotype Evaluation in LLMs
Research
Pronunciation Editing for Finnish Speech using Phonetic Posteriorgrams
Research
Learnable Spectral Activations
Research
AdvSim2Real : Training Web Agents Against Adaptive Prompt Injection in a Web World Model
Research
Benchmarking Label-Revealed Online Updates for EEG BCI Decoding
Research
Decoupling What from Where: How Should a Small GUI Grounding Model Receive the Action Type?
Research