arXiv:2608. 12756v1 Announce Type: cross Abstract: Adaptive latent tokenization maps a fine-grained input to a shorter sequence of continuous representations associated with input-dependent spans.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.
The paper introduces K-Token Merging, a latent-space compression method that merges each contiguous block of K token embeddings into a single embedding using a lightweight encoder. The compressed sequence is then processed by a LoRA-adapted large language model, while generation continues in the original vocabulary. Experiments on tasks such as structural reasoning, sentiment classification, and code editing demonstrate that K-Token Merging achieves up to 75% input length reduction with minimal performance loss, placing it on the Pareto frontier of performance versus compression.
arXiv:2607. 29378v1 Announce Type: cross Abstract: Large language models (LLMs) generate text by auto-regressively sampling the next token.
Cola2 is a hierarchical language modeling framework that jointly optimizes continuous semantic compression, reconstruction–generation balance, and continuous–discrete co‑adaptation. It dynamically segments text into semantic spans, controls compression via negative feedback, and trains a block‑causal masked diffusion decoder with clean, noisy, and dropped latent conditions. Experiments on five downstream tasks with 210 billion training tokens show competitive scaling, and an unconverged checkpoint with 346 billion source tokens outperforms Llama‑3‑8B on HellaSwag and StoryCloze.
arXiv:2610.33811v1 Announce Type: new Abstract: Continuous-state flow and diffusion models offer a promising approach to fast, parallel language generation, but matching the generation quality of aut...
The paper introduces LLMAE, a technique that transforms a pretrained decoder-only language model into a continuous text autoencoder by inserting a fixed-length latent bottleneck into its internal activations. Using a 270M Gemma 3 model with structured attention masks, LoRA adaptation, and KL regularization, LLMAE achieves near-perfect reconstruction of text sequences up to 1024 tokens. The authors further show that the resulting latent representation can be leveraged to train a latent text diffusion model for detailed image captioning, demonstrating downstream utility.
SCOPE is a training‑free generative prompt‑compression framework that reduces LLM input length by chunking a prompt into semantically coherent segments, rewriting each chunk to be more concise, and then reconstructing a coherent prompt. Unlike token‑removal methods, SCOPE’s chunk‑level rewriting preserves critical information and text coherence, and includes optimization techniques for finer‑grained control of compression ratios. Extensive evaluations on question‑answering and summarization tasks show that SCOPE consistently outperforms selective compression baselines, especially at high compression ratios.