Related papers: Optimizing Logical Execution Time Model for Both D…

The deployment of large language models (LLMs) in real-world applications is increasingly limited by their high inference cost. While recent advances in dynamic token-level computation allocation attempt to improve efficiency by selectively…

Register Transfer Level(RTL) code optimization is crucial for achieving high performance and low power consumption in digital circuit design. However, traditional optimization methods often rely on manual tuning and heuristics, which can be…

In modern interactive speech-based systems, speech is consumed and transcribed incrementally prior to having disfluencies removed. This post-processing step is crucial for producing clean transcripts and high performance on downstream tasks…

Most language models (LMs) are trained and applied in an autoregressive left-to-right fashion, assuming that the next token only depends on the preceding ones. However, this assumption ignores the potential benefits of using the full…

We consider a single large language model (LLM) server that serves a heterogeneous stream of queries belonging to $N$ distinct task types. Queries arrive according to a Poisson process, and each type occurs with a known prior probability.…

Large Language Models (LLMs) represent a revolutionary advancement in the contemporary landscape of artificial general intelligence (AGI). As exemplified by ChatGPT, LLM-based applications necessitate minimal response latency and maximal…

In the realm of Large Language Model (LLM) inference, the inherent structure of transformer models coupled with the multi-GPU tensor parallelism strategy leads to a sequential execution of computation and communication. This results in…

We propose Batch-Expansion Training (BET), a framework for running a batch optimizer on a gradually expanding dataset. As opposed to stochastic approaches, batches do not need to be resampled i.i.d. at every iteration, thus making BET more…

Low-latency communication plays an increasingly important role in delay-sensitive applications by ensuring the real-time information exchange. However, due to the constraint on the maximum instantaneous power, guaranteeing bounded latency…

Accurate prediction of resource consumption and runtime for cloud workflow jobs is critical for scheduling efficiency, yet remains challenging due to the semi-structured nature of job configurations -- comprising shell commands,…

This paper offers a methodological contribution at the intersection of machine learning and operations research. Namely, we propose a methodology to quickly predict tactical solutions to a given operational problem. In this context, the…

Explicit chain-of-thought (CoT) reasoning substantially improves the reasoning ability of large language models (LLMs), but incurs high inference cost due to lengthy autoregressive traces. Existing latent reasoning methods offer a promising…

In robotic task planning, symbolic planners using rule-based representations like PDDL are effective but struggle with long-sequential tasks in complicated environments due to exponentially increasing search space. Meanwhile, LLM-based…

Assistive agents performing household tasks such as making the bed or cooking breakfast often compute and execute actions that accomplish one task at a time. However, efficiency can be improved by anticipating upcoming tasks and computing…

Discrete diffusion models have recently become competitive with autoregressive models for language modeling, even outperforming them on reasoning tasks requiring planning and global coherence, but they require more computation at inference…

Optimization is an important module of modern machine learning applications. Tremendous efforts have been made to accelerate optimization algorithms. A common formulation is achieving a lower loss at a given time. This enables a…

Large Language Models (LLMs) have significantly advanced artificial intelligence by optimizing traditional Natural Language Processing (NLP) workflows, facilitating their integration into various systems. Many such NLP systems, including…

In tasks aiming for long-term returns, planning becomes essential. We study generative modeling for planning with datasets repurposed from offline reinforcement learning. Specifically, we identify temporal consistency in the absence of…

Edge intelligence (EI) allows resource-constrained edge devices (EDs) to offload computation-intensive AI tasks (e.g., visual object detection) to edge servers (ESs) for fast execution. However, transmitting high-volume raw task data (e.g.,…

Vision Language Models (VLMs) have become essential backbones for multimodal intelligence, yet significant safety challenges limit their real-world application. While textual inputs are often effectively safeguarded, adversarial visual…