Tokenization plays a critical role in language modeling, yet existing approaches such as Byte-Pair Encoding (BPE) or WordPiece operate purely on frequency statistics, ignoring the underlying semantic structure of text. This leads to over-tokenization of semantically redundant spans and underutilization of contextual coherence, particularly in long-context scenarios. In this work, we propose SemToken, a semantic-aware tokenization framework that jointly reduces token redundancy and improves computation efficiency. SemToken first extracts contextual semantic embeddings via lightweight encoders and performs local semantic clustering to merge semantically equivalent tokens. Then, it allocates heterogeneous token granularity based on semantic density, allowing finer-grained tokenization in content-rich regions and coarser compression in repetitive or low-entropy spans. SemToken can be seamlessly integrated with modern language models and attention acceleration methods. Experiments on long-context language modeling benchmarks such as WikiText-103 and LongBench show that SemToken achieves up to 2.4× reduction in token count and 1.9× speedup, with negligible or no degradation in perplexity and downstream accuracy. Our findings suggest that semantic structure offers a promising new axis for optimizing tokenization and computation in large language models.

We propose MT2ST, a general and efficient framework for accelerating multi-task training by progressively transitioning to single-task optimization. Unlike conventional multi-task learning (MTL) or single-task fine-tuning (STL), MT2ST dynamically adjusts the training focus via two complementary strategies: Diminish, which gradually down-weights auxiliary losses, and Switch, which explicitly switches to the primary task at a scheduled point. We demonstrate the effectiveness of MT2ST across three key paradigms: representation learning, transformers, and diffusion models, covering both unimodal (text/image) and multimodal (vision-language) tasks. Extensive experiments show that MT2ST significantly improves training efficiency—achieving up to 56% FLOPs compression—while maintaining or surpassing task performance. These results suggest MT2ST as a general-purpose solution for scalable and adaptive multi-task training. Although this work is general-purpose, it is especially suitable for multimodal settings such as VQA or vision-language retrieval, where auxiliary pretraining (e.g., masked language modeling or contrastive learning) often diverges from final objectives. We include a VQA case study and outline its efficiency for multimodal retrieval.