Related papers: Constable: Improving Performance and Power Efficie…

Multimodal Large Language Models (MLLMs) achieve strong performance through instruction tuning, yet real-world deployment often requires continual capability expansion across sequential tasks. In such scenarios, Multimodal Continual…

Despite significant progress, Vision-Language Models (VLMs) still struggle with complex visual reasoning, where multi-step dependencies cause early errors to cascade through the reasoning chain. Existing post-training paradigms are limited:…

High resource requirement for Deep Neural Network (DNN) training across multiple GPUs necessitates development of various parallelism techniques. In this paper, we introduce two interconnected DNN training frameworks, namely, V-TiMePReSt…

Active learning aims to efficiently build a labeled training set by strategically selecting samples to query labels from annotators. In this sequential process, each sample acquisition influences subsequent selections, causing dependencies…

Recent advances in the reinforcement learning (RL) literature have enabled roboticists to automatically train complex policies in simulated environments. However, due to the poor sample complexity of these methods, solving RL problems using…

To use control charts in practice, the in-control state usually has to be estimated. This estimation has a detrimental effect on the performance of control charts, which is often measured for example by the false alarm probability or the…

Table reasoning with large language models (LLMs) plays a critical role in building intelligent systems capable of understanding and analyzing tabular data. Despite recent progress, existing methods still face key limitations: their…

Reinforcement learning (RL) is central to improving reasoning in large language models (LLMs) but typically requires ground-truth rewards. Test-Time Reinforcement Learning (TTRL) removes this need by using majority-vote rewards, but relies…

The stagnation of EDA technologies roots from insufficient knowledge reuse. In practice, very similar simulation or optimization results may need to be repeatedly constructed from scratch. This motivates my research on introducing more…

Model-based reinforcement learning (MBRL) seeks to enhance data efficiency by learning a model of the environment and generating synthetic rollouts from it. However, accumulated model errors during these rollouts can distort the data…

Parallel iterative applications often suffer from load imbalance, one of the most critical performance degradation factors. Hence, load balancing techniques are used to distribute the workload evenly to maximize performance. A key challenge…

It can be difficult to autonomously produce driver behavior so that it appears natural to other traffic participants. Through Inverse Reinforcement Learning (IRL), we can automate this process by learning the underlying reward function from…

Incremental learning that learns new classes over time after the model's deployment is becoming increasingly crucial, particularly for industrial edge systems, where it is difficult to communicate with a remote server to conduct…

Generative reward models (GRMs) have emerged as a promising approach for aligning Large Language Models (LLMs) with human preferences by offering greater representational capacity and flexibility than traditional scalar reward models.…

Incremental stability is a property of dynamical and control systems, requiring the uniform asymptotic stability of every trajectory, rather than that of an equilibrium point or a particular time-varying trajectory. Similarly to stability,…

Cloud computing has grown rapidly in recent years, mainly due to the sharp increase in data transferred over the internet. This growth makes load balancing a key part of cloud systems, as it helps distribute user requests across servers to…

Causal consistency is an attractive consistency model for replicated data stores. It is provably the strongest model that tolerates partitions, it avoids the long latencies associated with strong consistency, and, especially when using…

Acquiring high-quality data is often a significant challenge in training machine learning (ML) models for tabular prediction, particularly in privacy-sensitive and costly domains like medicine and finance. Providing natural language…

With the continued deployment of synchronized Phasor Measurement Units (PMUs), high sample rate data are rapidly increasing the real time observability of power systems. Prior research has shown that the statistics of these data can provide…

We present MLTCP, a technique to augment today's congestion control algorithms to accelerate DNN training jobs in shared GPU clusters. MLTCP enables the communication phases of jobs that compete for network bandwidth to interleave with each…