6 papers
Represent, Then Generate: Multimodal-Conditioned Time-Series Generation under Irregular Missingness
Haochen Zhang, Jiaheng Guo, Yu-Chao Huang +3
Continuous physiological time series underpin modern clinical monitoring, yet many of the most informative signals are invasive, expensive, or simply unavailable for a given patien…
Addressing the Orchestration Gap in Generalist Robots via Physical Agency
Liane Galanti, Dhruv Shah, Tri Dao
General-purpose robots need to reason about their actions, combining perception, world knowledge, planning, success detection, recovery, and low-level control. Today's state-of-the…
M1: Towards Scalable Test-Time Compute with Mamba Reasoning Models
Junxiong Wang, Wen-Ding Li, Daniele Paliotta +3
Effective reasoning is crucial to solving complex mathematical problems. Recent large language models (LLMs) have boosted performance by scaling test-time computation through long…
The Mamba in the Llama: Distilling and Accelerating Hybrid Models
Junxiong Wang, Daniele Paliotta, Avner May +2
Linear RNN architectures, like Mamba, can be competitive with Transformer models in language modeling while having advantageous deployment characteristics. Given the focus on train…
Thinking Slow, Fast: Scaling Inference Compute with Distilled Reasoners
Daniele Paliotta, Junxiong Wang, Matteo Pagliardini +6
Recent advancements have demonstrated that the performance of large language models (LLMs) can be significantly enhanced by scaling computational resources at test time. A common s…
HybriDNA: A Hybrid Transformer-Mamba2 Long-Range DNA Language Model
Mingqian Ma, Guoqing Liu, Chuan Cao +12
Advances in natural language processing and large language models have sparked growing interest in modeling DNA, often referred to as the "language of life". However, DNA modeling…