Related papers: Language-Guided Transformer Tokenizer for Human Mo…
Tokenizer is an essential component for large language models (LLMs), and a tokenizer with a high compression rate can improve the model's representation and processing efficiency. However, the tokenizer cannot ensure high compression rate…
The dominant approach to generating from language models subject to some constraint is locally constrained decoding (LCD), incrementally sampling tokens at each time step such that the constraint is never violated. Typically, this is…
Language plays a vital role in the realm of human motion. Existing methods have largely depended on CLIP text embeddings for motion generation, yet they fall short in effectively aligning language and motion due to CLIP's pretraining on…
Multimodal large language models (MLLMs) extend the success of language models to visual understanding, and recent efforts have sought to build unified MLLMs that support both understanding and generation. However, constructing such models…
Large language models deliver strong generative performance but at the cost of massive parameter counts, memory use, and decoding latency. Prior work has shown that pruning and structured sparsity can preserve accuracy under substantial…
Tokenization is an understudied and often neglected component of modern LLMs. Most published works use a single tokenizer for all experiments, often borrowed from another model, without performing ablations or analysis to optimize…
Training vision-language models on cognitively-plausible amounts of data requires rethinking how models integrate multimodal information. Within the constraints of the Vision track for the BabyLM Challenge 2025, we propose a lightweight…
Text-to-motion models excel at efficient human motion generation, but existing approaches lack fine-grained controllability over the generation process. Consequently, modifying subtle postures within a motion or inserting new actions at…
Sign language is a visual language that encompasses all linguistic features of natural languages and serves as the primary communication method for the deaf and hard-of-hearing communities. Although many studies have successfully adapted…
Bridging different modalities lies at the heart of cross-modality generation. While conventional approaches treat the text modality as a conditioning signal that gradually guides the denoising process from Gaussian noise to the target image…
Most existing multi-object tracking methods typically learn visual tracking features via maximizing dis-similarities of different instances and minimizing similarities of the same instance. While such a feature learning scheme achieves…
Pretrained Large Language Models (LLM) such as ChatGPT, Claude, etc. have demonstrated strong capabilities in various fields of natural language generation. However, there are still many problems when using LLM in specialized…
Generative recommendation systems, driven by large language models (LLMs), present an innovative approach to predicting user preferences by modeling items as token sequences and generating recommendations in a generative manner. A critical…
Generative transformers have shown their superiority in synthesizing high-fidelity and high-resolution images, such as good diversity and training stability. However, they suffer from the problem of slow generation since they need to…
Image tokenization has significantly advanced visual generation and multimodal modeling, particularly when paired with autoregressive models. However, current methods face challenges in balancing efficiency and fidelity: high-resolution…
Recent breakthroughs in large language models (LLMs) have not only advanced natural language processing but also inspired their application in domains with structurally similar problems--most notably, autonomous driving motion generation.…
The task of text2motion is to generate human motion sequences from given textual descriptions, where the model explores diverse mappings from natural language instructions to human body movements. While most existing works are confined to…
We present Liquid, an auto-regressive generation paradigm that seamlessly integrates visual comprehension and generation by tokenizing images into discrete codes and learning these code embeddings alongside text tokens within a shared…
Tokenization is a foundational step in natural language processing (NLP) tasks, bridging raw text and language models. Existing tokenization approaches like Byte-Pair Encoding (BPE) originate from the field of data compression, and it has…
While model architecture and training objectives are well-studied, tokenization, particularly in multilingual contexts, remains a relatively neglected aspect of Large Language Model (LLM) development. Existing tokenizers often exhibit high…