TaleFrame: An Interactive Story Generation System with Fine-Grained Control and Large Language Models

LeMat-GenBench has been introduced as a unified evaluation framework for generative models of crystalline materials, addressing the challenges posed by the lack of standardized metrics in the field. This framework includes an open-source evaluation suite and a public leaderboard on Hugging Face, benchmarking 12 recent generative models and revealing insights into the trade-offs between stability, novelty, and diversity in model performance.

Large-scale Mixture of Experts (MoE) Large Language Models (LLMs) have emerged as leading open-weight models, but their random expert selection mechanism leads to significant data movement overhead. A recent study conducted comprehensive profiling across four state-of-the-art MoE models, revealing insights that can enhance future serving systems and reduce bottlenecks in multi-unit LLM serving.

Jina-VLM, a 2.4 billion parameter vision-language model, has been introduced, achieving state-of-the-art multilingual visual question answering capabilities among open 2B-scale VLMs. It integrates a SigLIP2 vision encoder with a Qwen3 language backbone, allowing for efficient processing of images at arbitrary resolutions.

A new approach called Semantic Soft Bootstrapping (SSB) has been proposed to enhance long context reasoning in large language models (LLMs) without relying on reinforcement learning. This self-distillation technique allows the model to act as both teacher and student, improving its reasoning capabilities by providing varied semantic contexts during training.

A recent study has introduced a taxonomy for cataloguing Open-source Pre-Trained Models (PTMs) from Hugging Face, specifically tailored to Software Engineering (SE) tasks. This classification encompasses 147 SE tasks, aiming to enhance the identification and reuse of models for software development activities. The research involved a comprehensive five-phase methodology, including data collection and validation processes.

Recent research highlights the importance of on-policy data in mitigating catastrophic forgetting in language models (LMs) during post-training adaptations. The study compares two methods, supervised fine-tuning (SFT) and reinforcement learning (RL), revealing that RL consistently results in less forgetting across various LM families and tasks, while maintaining or improving performance.