相关论文: Can Identifier Splitting Improve Open-Vocabulary L…

Names are essential to both human cognition and vision-language models. Open-vocabulary models utilize class names as text prompts to generalize to categories unseen during training. However, the precision of these names is often overlooked…

Open-vocabulary segmentation (OVS) extends the zero-shot recognition capabilities of vision-language models (VLMs) to pixel-level prediction, enabling segmentation of arbitrary categories specified by text prompts. Despite recent progress,…

Synthetic voice and splicing audio clips have been generated to spoof Internet users and artificial intelligence (AI) technologies such as voice authentication. Existing research work treats spoofing countermeasures as a binary…

Spoken language Identification (LID) systems are needed to identify the language(s) present in a given audio sample, and typically could be the first step in many speech processing related tasks such as automatic speech recognition (ASR).…

Subword tokenization methods, such as Byte-Pair Encoding (BPE), significantly impact the performance and efficiency of large language models (LLMs). The standard approach involves training a general-purpose tokenizer that uniformly…

Existing instance segmentation models learn task-specific information using manual mask annotations from base (training) categories. These mask annotations require tremendous human effort, limiting the scalability to annotate novel (new)…

The cocktail party problem comprises the challenging task of understanding a speech signal in a complex acoustic environment, where multiple speakers and background noise signals simultaneously interfere with the speech signal of interest.…

The popular subword tokenizers of current language models, such as Byte-Pair Encoding (BPE), are known not to respect morpheme boundaries, which affects the downstream performance of the models. While many improved tokenization algorithms…

Word representation is a key component in neural-network-based sequence labeling systems. However, representations of unseen or rare words trained on the end task are usually poor for appreciable performance. This is commonly referred to as…

Despite rapid progress in LLM-based code generation, existing models are predominantly trained on imperative languages, leaving functional programming languages (FPLs) such as Haskell, OCaml, and Scala chronically underexplored, with even…

Evaluating off-policy decisions using batch data poses significant challenges due to limited sample sizes leading to high variance. To improve Off-Policy Evaluation (OPE), we must identify and address the sources of this variance. Recent…

The success of deep learning-based speaker verification systems is largely attributed to access to large-scale and diverse speaker identity data. However, collecting data from more identities is expensive, challenging, and often limited by…

Algorithm selection and hyperparameter tuning remain two of the most challenging tasks in machine learning. Automated machine learning (AutoML) seeks to automate these tasks to enable widespread use of machine learning by non-experts. This…

Prompt engineering has shown remarkable success with large language models, yet its systematic exploration in computer vision remains limited. In semantic segmentation, both textual and visual prompts offer distinct advantages: textual…

Open-vocabulary segmentation aims to achieve segmentation of arbitrary categories given unlimited text inputs as guidance. To achieve this, recent works have focused on developing various technical routes to exploit the potential of…

Code linters play a crucial role in developing high-quality software systems by detecting potential problems (e.g., memory leaks) in the source code of systems. Despite their benefits, code linters are often language-specific, focused on…

As language models accelerate scientific research by automating hypothesis generation and implementation, a new bottleneck emerges: evaluating and filtering hundreds of AI-generated ideas without exhaustive experimentation. We ask whether…

Language mismatch is among the most common and challenging domain mismatches in deploying speaker verification (SV) systems. Adversarial reprogramming has shown promising results in cross-language adaptation for SV. The reprogramming is…

Open-vocabulary instance segmentation aims at segmenting novel classes without mask annotations. It is an important step toward reducing laborious human supervision. Most existing works first pretrain a model on captioned images covering…

Code optimization is the process of enhancing code efficiency, while preserving its intended functionality. This process often requires a deep understanding of the code execution behavior at run-time to identify and address inefficiencies…