相关论文: Super Monotonic Alignment Search

With the advent of large language models (LLMs), there has been a great deal of interest in applying them to solve difficult programming tasks. Recent work has demonstrated their potential at program optimization, a key challenge in…

Recently, researchers have shown an increasing interest in automatically predicting the subjective evaluation for speech synthesis systems. This prediction is a challenging task, especially on the out-of-domain test set. In this paper, we…

Many modern solvers and program analyzers rely on non-monotone reasoning (e.g. negation-as-failure, speculative updates, backtracking) for which classical monotone fixed-point methods do not apply. The general problem of finding the fixed…

We explore applying the Monte Carlo Tree Search (MCTS) algorithm in a notoriously difficult task: tuning programs for high-performance deep learning and image processing. We build our framework on top of Halide and show that MCTS can…

This paper investigates the optimal signal detection problem with a particular interest in large-scale multiple-input multiple-output (MIMO) systems. The problem is NP-hard and can be solved optimally by searching the shortest path on the…

End-to-end text-to-speech (TTS) synthesis is a method that directly converts input text to output acoustic features using a single network. A recent advance of end-to-end TTS is due to a key technique called attention mechanisms, and all…

Audio alignment is a fundamental preprocessing step in many MIR pipelines. For two audio clips with M and N frames, respectively, the most popular approach, dynamic time warping (DTW), has O(MN) requirements in both memory and computation,…

Semantic segmentation and stereo matching, respectively analogous to the ventral and dorsal streams in our human brain, are two key components of autonomous driving perception systems. Addressing these two tasks with separate networks is no…

Word alignment is essential for the downstream cross-lingual language understanding and generation tasks. Recently, the performance of the neural word alignment models has exceeded that of statistical models. However, they heavily rely on…

Forced alignment systems automatically determine boundaries between segments in speech data, given an orthographic transcription. These tools are commonplace in phonetics to facilitate the use of speech data that would be infeasible to…

Contrastive learning and equivariant learning are effective methods for self-supervised learning (SSL) for audio content analysis. Yet, their application to music information retrieval (MIR) faces a dilemma: the former is more effective on…

We propose efficient algorithms for enumerating maximal common subsequences (MCSs) of two strings. Efficiency of the algorithms are estimated by the preprocessing-time, space, and delay-time complexities. One algorithm prepares a…

This paper investigates the approximability of the Longest Common Subsequence (LCS) problem. The fastest algorithm for solving the LCS problem exactly runs in essentially quadratic time in the length of the input, and it is known that under…

Monte Carlo Tree Search (MCTS) methods have achieved great success in many Artificial Intelligence (AI) benchmarks. The in-tree operations become a critical performance bottleneck in realizing parallel MCTS on CPUs. In this work, we develop…

Scene understanding is paramount in robotics, self-navigation, augmented reality, and many other fields. To fully accomplish this task, an autonomous agent has to infer the 3D structure of the sensed scene (to know where it looks at) and…

Recent studies have demonstrated the cross-lingual alignment ability of multilingual pretrained language models. In this work, we found that the cross-lingual alignment can be further improved by training seq2seq models on sentence pairs…

Model merging has recently emerged as a lightweight alternative to ensembling, combining multiple fine-tuned models into a single set of parameters with no additional training overhead. Yet, existing merging methods fall short of matching…

We present Atos, a task-parallel GPU dynamic scheduling framework that is especially suited to dynamic irregular applications. Compared to the dominant Bulk Synchronous Parallel (BSP) frameworks, Atos exposes additional concurrency by…

Recently, the expert-crafted neural architectures is increasing overtaken by the utilization of neural architecture search (NAS) and automatic generation (and tuning) of network structures which has a close relation to the Hyperparameter…

In stereoscope-based Minimally Invasive Surgeries (MIS), dense stereo matching plays an indispensable role in 3D shape recovery, AR, VR, and navigation tasks. Although numerous Deep Neural Network (DNN) approaches are proposed, the…