🏷️:LServe: Efficient Long-sequence LLM Serving with Unified Sparse Attention 🔗:arxiv.org/abs/2502.14866…

🏷️:LLM-Microscope: Uncovering the Hidden Role of Punctuation in Context Memory of Transformers 🔗:arxiv.org/abs/2502.15007…

🏷️:SurveyX: Academic Survey Automation via Large Language Models 🔗:arxiv.org/abs/2502.14776…

🏷️:Mol-LLaMA: Towards General Understanding of Molecules in Large Molecular Language Model 🔗:arxiv.org/abs/2502.13449…

🏷️:MaskGWM: A Generalizable Driving World Model with Video Mask Reconstruction 🔗:arxiv.org/abs/2502.11663…

🏷️:PhotoDoodle: Learning Artistic Image Editing from Few-Shot Pairwise Data 🔗:arxiv.org/abs/2502.14397…

🏷️:SIFT: Grounding LLM Reasoning in Contexts via Stickers 🔗:arxiv.org/abs/2502.14922…

🏷️:VLM$^2$-Bench: A Closer Look at How Well VLMs Implicitly Link Explicit Matching Visual Cues 👤:Paul Liang 🔗:arxiv.org/abs/2502.12084…

🏷️:LightThinker: Thinking Step-by-Step Compression 🔗:arxiv.org/abs/2502.15589…

🏷️:Is Safety Standard Same for Everyone? User-Specific Safety Evaluation of Large Language Models 🔗:arxiv.org/abs/2502.15086…

🏷️:StructFlowBench: A Structured Flow Benchmark for Multi-turn Instruction Following 🔗:arxiv.org/abs/2502.14494…

🏷️:MoBA: Mixture of Block Attention for Long-Context LLMs 🔗:arxiv.org/abs/2502.13189…

🏷️:Towards Fully-Automated Materials Discovery via Large-Scale Synthesis Dataset and Expert-Level LLM-as-a-Judge 🔗:arxiv.org/abs/2502.16457…

🏷️:MedHallu: A Comprehensive Benchmark for Detecting Medical Hallucinations in Large Language Models 🔗:arxiv.org/abs/2502.14302…

🏷️:Evaluating Multimodal Generative AI with Korean Educational Standards 👤:Geewook Kim 🔗:arxiv.org/abs/2502.15422…

🏷️:Think Inside the JSON: Reinforcement Strategy for Strict LLM Schema Adherence 🔗:arxiv.org/abs/2502.14905…

🏷️:FantasyID: Face Knowledge Enhanced ID-Preserving Video Generation 🔗:arxiv.org/abs/2502.13995…

🏷️:KITAB-Bench: A Comprehensive Multi-Domain Benchmark for Arabic OCR and Document Understanding 🔗:arxiv.org/abs/2502.14949…

🚨 Shipping this AI computer worldwide Plug and play workstation ideal for AI applications - $2,199 - RTX 3090 24 GB - 64 GB RAM - 1 TB SSD - Ubuntu, PyTorch, CUDA, cuDNN preinstalled AMA

I built an MCP server to find and chat with academic papers by searching for and retrieving their metadata and content (as Markdown) from arXiv, the OSF API (28 domain-specific repositories), and OpenAlex. leave a star github.com/matsjfunke/pap… or try it paperclip.matsjfunke.com/mcp