@Tsinghua_Uni: Breaking records across all four key benchmarks! Innovative Tsinghua's @AIRTHU1201 and collaborators have unveiled Gala…
Summary
Tsinghua University and AIRTHU introduce GalaxyVS, a method that transforms protein–ligand docking into ultra-large-scale parallel vector retrieval, setting a new global benchmark for high-throughput drug discovery.
View Cached Full Text
Cached at: 07/27/26, 01:52 PM
Breaking records across all four key benchmarks! Innovative Tsinghua’s @AIRTHU1201 and collaborators have unveiled GalaxyVS, transforming protein–ligand docking into ultra-large-scale parallel vector retrieval. This sets a new global benchmark for high-throughput drug discovery. https://t.co/vb2E2yiWDF
Similar Articles
@AlphaSignalAI: A 4B model can now anticipate scientific breakthroughs before scientists do. Researchers often build breakthroughs by c…
A new paper introduces GIANTS-4B, a 4-billion-parameter model trained with reinforcement learning to predict scientific insights by combining ideas from foundational papers, achieving higher similarity and citation potential than larger models like Gemini 3 Pro.
Xiaomi just claimed 1,000+ tps on a 1T model using a standard 8-GPU server
Xiaomi released MiMo-V2.5-Pro-UltraSpeed in collaboration with TileRT, achieving over 1000 tokens/s decode speed on a 1-trillion-parameter model, enabling real-time AI interaction and accelerating coding agents and reasoning tasks.
@AnthropicAI: Many drugs work by binding to a specific target in the body and blocking or changing what it does. An important first s…
Anthropic AI announced that Claude successfully designed novel protein binders for 14 out of 15 drug targets, with independent verification by Adaptyv Bio and Twist Bioscience.
@alex_verem: a team of researchers just proved you don't need a bigger model, you need a smarter plan researchers from Tsinghua and …
Researchers from Tsinghua and South China University of Technology introduced Atomic Task Graph (ATG), a framework that enables 7B-8B open-source models to surpass GPT-4 on complex agent benchmarks without fine-tuning, by using directed graph-based planning and internal simulation to drastically reduce hallucination rates.
TxBench: Antibody Discovery (13 minute read)
TxBench is a benchmark for antibody discovery, likely assessing computational or AI-driven methods in this biotech domain.