5 papers
World Simulation with Video Foundation Models for Physical AI
NVIDIA, :, Arslan Ali +87
We introduce [Cosmos-Predict2.5], the latest generation of the Cosmos World Foundation Models for Physical AI. Built on a flow-based architecture, [Cosmos-Predict2.5] unifies Text2…
MLLM-CTBench: A Benchmark for Continual Instruction Tuning with Reasoning Process Diagnosis
Haiyun Guo, Zhiyan Hou, Yandu Sun +6
Continual instruction tuning(CIT) during the post-training phase is crucial for adapting multimodal large language models (MLLMs) to evolving real-world demands. However, the progr…
Beyond the Needle's Illusion: Decoupled Evaluation of Evidence Access and Use under Semantic Interference at 326M-Token Scale
Tianwei Lin, Zuyi Zhou, Xinda Zhao +6
Long-context LLM agents must access the right evidence from large environments and use it faithfully. However, the popular Needle-in-a-Haystack (NIAH) evaluation mostly measures be…
TsqLoRA: Towards Sensitivity and Quality Low-Rank Adaptation for Efficient Fine-Tuning
Yu Chen, Yifei Han, Long Zhang +2
Fine-tuning large pre-trained models for downstream tasks has become a fundamental approach in natural language processing. Fully fine-tuning all model parameters is computationall…
AQETuner: Reliable Query-level Configuration Tuning for Analytical Query Engines
Lixiang Chen, Yuxing Han, Yu Chen +3
Modern analytical query engines (AQEs) are essential for large-scale data analysis and processing. These systems usually provide numerous query-level tunable knobs that significant…