Related papers: BEAST: Efficient Tokenization of B-Splines Encoded…

Many existing motion prediction approaches rely on symbolic perception outputs to generate agent trajectories, such as bounding boxes, road graph information and traffic lights. This symbolic representation is a high-level abstraction of…

While most frontier models still use deterministic frequency-based tokenization algorithms such as byte-pair encoding (BPE), there has been significant recent work to design learned neural tokenizers. However, these schemes generally add to…

The Byte Pair Encoding algorithm can be safely batched to merge hundreds of pairs of tokens at a time when building up a tokenizer's vocabulary. This technique combined with reducing the memory footprint of text used in vocabulary training…

Most existing image tokenizers encode images into a fixed number of tokens or patches, overlooking the inherent variability in image complexity. To address this, we introduce Content-Adaptive Tokenizer (CAT), which dynamically adjusts…

To improve the efficiency and sustainability of learning deep models, we propose CREST, the first scalable framework with rigorous theoretical guarantees to identify the most valuable examples for training non-convex models, particularly…

We present AToken, the first unified visual tokenizer that achieves both high-fidelity reconstruction and semantic understanding across images, videos, and 3D assets. Unlike existing tokenizers that specialize in either reconstruction or…

Malware is becoming increasingly complex and widespread, making it essential to develop more effective and timely detection methods. Traditional static analysis often fails to defend against modern threats that employ code obfuscation,…

Effective training of today's large language models (LLMs) depends on large batches and long sequences for throughput and accuracy. To handle variable-length sequences on hardware accelerators, it is common practice to introduce padding…

Tokens serve as the basic units of representation in DNA language models (DNALMs), yet their design remains underexplored. Unlike natural language, DNA lacks inherent token boundaries or predefined compositional rules, making tokenization a…

Token-based video representation has emerged as a promising approach for enabling large language models (LLMs) to interpret video content. However, existing token reduction techniques, such as pruning and merging, often disrupt essential…

Training large AI models typically requires large-scale datasets in the machine learning process, making training and parameter-tuning process both time-consuming and costly. Some researchers address this problem by carefully synthesizing a…

Binary code similarity detection is a fundamental technique for many security applications such as vulnerability search, patch analysis, and malware detection. There is an increasing need to detect similar code for vulnerability search…

We present SkeleTR, a new framework for skeleton-based action recognition. In contrast to prior work, which focuses mainly on controlled environments, we target more general scenarios that typically involve a variable number of people and…

Video generation has recently made striking visual progress, but maintaining coherent object motion and interactions remains difficult. We trace two practical bottlenecks: (i) human-provided motion hints (e.g., small 2D maps) often collapse…

Fast and accurate spoken content retrieval is vital for applications such as voice search. Query-by-Example Spoken Term Detection (STD) involves retrieving matching segments from an audio database given a spoken query. Token-based STD…

Current state-of-the-art methods for skeleton-based action recognition are supervised and rely on labels. The reliance is limiting the performance due to the challenges involved in annotation and mislabeled data. Unsupervised methods have…

Quantization is a widely used compression technique for reducing the memory and computation costs of large pre-trained models. A key challenge in per-channel post-training quantization (PTQ) is selecting appropriate scaling factors to…

Skeleton-based motion representations are robust for action localization and understanding for their invariance to perspective, lighting, and occlusion, compared with images. Yet, they are often ambiguous and incomplete when taken out of…

The end-to-end architecture has made promising progress in speech translation (ST). However, the ST task is still challenging under low-resource conditions. Most ST models have shown unsatisfactory results, especially in the absence of word…

We present a novel approach to feature labeling using gradient descent in token-space. While existing methods typically use language models to generate hypotheses about feature meanings, our method directly optimizes label representations…