#retrieval
- Tencent releases WeMM-Embedding multimodal embedding models (2B/4B/9B) — new MMEB-v2/v3 SOTA Tencent models-llm
- A New Role for Relevance: Guiding Corpus Interaction in Agentic Search Tencent research
- VoiceMem: Streaming Dual-Brain Memory for Real-Time Interaction research
- Cohere releases Rerank 5 with Context Focus and calibrated scores Cohere models-llm
- AskChem: Claim-Centered Infrastructure for Chemistry Literature Synthesis New York University research
- Demystifying Agent Skills: Why They Work — Until They Don't UC San Diego (Zhiyuan Jiang, Mengdi Wang, Yijiang Li et al.) research
- RoboTok: internet-scale retrieval of human demonstrations for dexterous robot policies research
- Tencent open-sources EVIE visual document retrieval models Tencent models-llm
- Qwen-Image-Agent: Agentic Context Building to Bridge the Prompt Underspecification Gap in T2I Qwen (Alibaba) research
- Sentence Transformers v6.0 adds native multi-vector / late-interaction embedding API Hugging Face / UKPLab tools
- LightOn ships full LateOn family + ColBERT-Zero alongside Sentence Transformers v6 LightOn models-llm
- EvoOntology: A Self-Evolving Ontology Layer for Data Agents RUC-DataLab (Renmin University) research