PulseAugur / Brief
EN
LIVE 23:49:37

Brief

last 24h
[2/2] 223 sources

Multi-source AI news clustered, deduplicated, and scored 0–100 across authority, cluster strength, headline signal, and time decay.

  1. FRONTIER RELEASE · Hugging Face Blog English(EN) · · [15 sources]

    Introducing Mellum2: A 12B Mixture-of-Experts Model by JetBrains

    JetBrains has released Mellum2, an open-source 12-billion parameter Mixture-of-Experts (MoE) model optimized for efficient inference in text and code tasks. This model activates only a fraction of its parameters per token, enabling faster, lower-latency operations suitable for routing, RAG pipelines, and sub-agent tasks within larger AI systems. Several research papers also explore advancements in MoE architectures, including efficient serving techniques like CRAFT, novel aggregation methods like DAG-MoE, adaptive gating with Kappa-SwiGLU, and probabilistic routing with ProbMoE, alongside game-theory inspired expert merging strategies. AI

    IMPACT Mellum2's efficiency and specialized design offer a faster, cheaper alternative for specific tasks within larger AI systems, potentially accelerating the adoption of modular AI architectures.

  2. RESEARCH · Hugging Face Blog English(EN) · · [37 sources]

    Direct Preference Optimization Beyond Chatbots

    Researchers are exploring new methods for aligning large language models (LLMs) with human preferences and mitigating specific failure modes. One approach uses Direct Preference Optimization (DPO) to reduce text degeneration in OCR models by leveraging the model's own failures as training signals. Other research focuses on understanding and controlling LLMs' temporal preference reasoning, developing lightweight local preference harnesses for personal agents, and creating frameworks for human-centric preference-driven judgment. Techniques like Inclusion-of-Thoughts and Critique-Driven Reasoning Alignment aim to improve LLM decision-making stability and interpretability. AI

    IMPACT New methods for preference alignment and failure mitigation could lead to more reliable and controllable LLMs.