Augur: Modeling Covariate Causal Associations in Time Series via Large Language Models

A new benchmark called CaptionQA has been introduced to evaluate the utility of model-generated captions in supporting downstream tasks across various domains, including Natural, Document, E-commerce, and Embodied AI. This benchmark consists of 33,027 annotated multiple-choice questions that require visual information to answer, aiming to assess whether captions can effectively replace images in multimodal systems.

Inferix has been introduced as a next-generation inference engine that utilizes a block-diffusion decoding paradigm, merging diffusion and autoregressive methods to enhance video generation capabilities. This innovation aims to create long, interactive, and high-quality videos, which are essential for applications in agentic AI, embodied AI, and gaming.

MUSE, a new framework for emotional synthesis in images, has been introduced, addressing inefficiencies in current Image Emotional Synthesis (IES) methods by integrating emotional generation and editing tasks. This approach leverages Test-Time Scaling, allowing for stable synthesis guidance without the need for additional model updates or specialized datasets.

Recent advancements in Large Language Models (LLMs) have led to the development of a multi-reward Group Relative Policy Optimization (GRPO) framework aimed at enhancing the stability and prosody of single-codebook text-to-speech (TTS) systems. This framework integrates various rule-based rewards to optimize token generation policies, addressing issues such as unstable prosody and speaker drift that have plagued existing models.

A systematic analysis has been conducted on large language models (LLMs) utilizing retrieval-augmented dynamic prompting (RDP) for the detection and correction of medical errors. The study evaluated various prompting strategies, including zero-shot and static prompting, using the MEDEC dataset and nine instruction-tuned LLMs, revealing performance metrics such as accuracy and recall in error processing tasks.

A new distributed speculative decoding framework, DSD, has been introduced to enhance large language model (LLM) inference by reducing decoding latency and improving scalability across edge-cloud environments. DSD-Sim, a discrete-event simulator, has been developed to analyze network dynamics, while an Adaptive Window Control policy optimizes throughput by adjusting speculation window sizes dynamically.

A new framework has been developed for generating safety-critical scenarios in autonomous driving, utilizing a conditional variational autoencoder (CVAE) and a large language model (LLM). This approach addresses the challenges posed by rare long-tail events and complex multi-agent interactions, which are crucial for safety validation but often underrepresented in real-world data. The integration allows for the creation of realistic and risk-sensitive scenarios.

A new framework called Subgoal Graph-Augmented Actor-Critic-Refiner (SGA-ACR) has been proposed to enhance the planning capabilities of large language models (LLMs) in reinforcement learning (RL) by integrating environment-specific subgoal graphs and structured entity knowledge. This addresses the misalignment between abstract planning and executable actions in RL environments.