SWE-FastContext Collection A family of code-search models powering the Explore subagent for coding agents. • 3 items • Updated 5 days ago • 15
VibeThinker-3B: Exploring the Frontier of Verifiable Reasoning in Small Language Models Paper • 2606.16140 • Published 8 days ago • 108
JoyAI-VL-Interaction: Real-Time Vision-Language Interaction Intelligence Paper • 2606.14777 • Published 13 days ago • 197
When Tools Fail: Benchmarking Dynamic Replanning and Anomaly Recovery in LLM Agents Paper • 2606.05806 • Published 19 days ago • 23
Your UnEmbedding Matrix is Secretly a Feature Lens for Text Embeddings Paper • 2606.07502 • Published 18 days ago • 97
LaRA: Layer-wise Representation Analysis for Detecting Data Contamination in RL Post-Training Paper • 2605.29888 • Published 26 days ago • 34
LongLive-RAG: A General Retrieval-Augmented Framework for Long Video Generation Paper • 2606.02553 • Published 22 days ago • 19
How LoRA Remembers? A Parametric Memory Law for LLM Finetuning Paper • 2605.30260 • Published 26 days ago • 44
MUSE-Autoskill: Self-Evolving Agents via Skill Creation, Memory, Management, and Evaluation Paper • 2605.27366 • Published 28 days ago • 29