LLMs Can't Handle Peer Pressure: Crumbling under Multi-Agent Social Interactions Paper β’ 2508.18321 β’ Published Aug 24 β’ 2
Running on CPU Upgrade 1.79k 1.79k The Smol Training Playbook: The Secrets to Building World-Class LLMs π Explore loss curves for training LLMs
Demystifying deep search: a holistic evaluation with hint-free multi-hop questions and factorised metrics Paper β’ 2510.05137 β’ Published Oct 1 β’ 4
WebWatcher: Breaking New Frontier of Vision-Language Deep Research Agent Paper β’ 2508.05748 β’ Published Aug 7 β’ 137
view article Article π¦Έπ»#1: Open-endedness and AI Agents β A Path from Generative to Creative AI? By Kseniase β’ Dec 25, 2024 β’ 16
Generate, but Verify: Reducing Hallucination in Vision-Language Models with Retrospective Resampling Paper β’ 2504.13169 β’ Published Apr 17 β’ 39
docling-project/SmolDocling-256M-preview Image-Text-to-Text β’ 0.3B β’ Updated Sep 17 β’ 358k β’ 1.59k
Long Reasoning Collection Datasets with reasoning traces for math and code (Train + Eval) β’ 49 items β’ Updated Mar 21 β’ 1