A Broader Look at Model Merging: Rethinking Implicit Regularization Induced by Task Arithmetic
Research
Research News
New papers, breakthroughs and academic AI research
The Geometry of Empowerment
Research
Knowing When to Trust a Prior: Reliability-Gated Cue Fusion for Video Gaze Prediction
Research
Harness Engineering for Software Engineering via Modular Executable Dev-Primitives
Research
Self-Retrospection Distillation: Turning Post-hoc Experiences into Prior Foresight
Research
CANDLE: Cortical Null-Space Decomposition for Noninvasive Brain Source Imaging
Research
HINTT Submission to the 2nd MLC-SLM Challenge: Comparing Cascaded and Unified Approaches to Diarization and ASR
Research
DAEDALUS: Bootstrapping Agent Memory from Self-Generated Tasks
Research
POLAR: Ontology-Guided Risk Prevention for Tool-Calling LLM Agents
Research
Natural Language Questions as an Interface for Knowledge Graphs: QRAKEN Graph Distillation and Semantic Self-Healing
Research
SpaTime: Streaming Vision-Language Models for Spatio-temporal Reasoning
Research
CtrlCache: Accelerating Interactive Video World Models with Control-Aware Caching
Research