arXiv:2505. 23869v4 Announce Type: replace-cross Abstract: A proposition that connects randomness and compression is put forward via Gibbs entropy over set of measurement vectors associated with a compression process.
Compression is fundamental to intelligence. A model that can represent its training data as a short code has discovered regularities that enable generalization.
arXiv:2607. 11883v1 Announce Type: new Abstract: Compression is fundamental to intelligence.
The paper introduces GaugeLasso, a method that applies symmetric group‑lasso penalties to transformer channels during training, enabling entire tensor slices to be zeroed out while maintaining dense tensors for GPU efficiency. By calibrating channel penalties based on inference utility per compute, the network self‑organizes into depth‑dependent structural profiles that can be dramatically smaller than the original architecture, achieving up to 255‑fold compression on a polynomial division task and outperforming hand‑designed baselines on language modeling and autoencoding benchmarks. The approach also accelerates training and reveals over‑provisioned axes that guide subsequent design iterations.
arXiv:2601. 22002v5 Announce Type: replace Abstract: Transformers achieve superior performance on many tasks, but impose heavy compute and memory requirements during inference.
arXiv:2606. 14353v1 Announce Type: new Abstract: Error-bounded lossy compression is a fundamental technique for managing the rapidly growing volumes of scientific data produced by modern simulations and observational instruments.
Deep neural networks have witnessed remarkable advancements in recent years and have become integral to various applications. However, alongside these developments, training and deployment of neural network models on embedding and edge devices face significant challenges due to limited memory and computational resources.
arXiv:2607. 29503v1 Announce Type: new Abstract: While neural networks are typically evaluated by their training and test performance, these metrics do not reveal how robust a learned representation is.
The paper investigates whether large language models (LLMs) capture the full diversity of outputs present in their training data. Using an information‑theoretic approach, the authors compare the conditional entropy of model‑generated outputs with that of the training data, finding that LLMs consistently produce outputs with lower conditional entropy across various models, scales, and decoding strategies. They also extend the analysis to image and text‑conditioned generators, propose a post‑hoc correction method based on matrix‑entropy projection to increase conditional diversity, and provide theoretical guarantees and an efficient algorithm for this correction.
arXiv:2510.08999v2 Announce Type: replace-cross Abstract: Compressing large-scale neural networks is essential for deploying models on resource-constrained devices. Most existing methods adopt weight...
arXiv:2605. 02404v2 Announce Type: replace Abstract: Model quantization has become essential for efficient large language model deployment, yet existing approaches present clear trade-offs: methods such as GPTQ and AWQ achieve practical compression but are lossy, while lossless techniques preserve fidelity but lack inference acceleration.
arXiv:2607. 13432v1 Announce Type: new Abstract: Plasticity -- a neural network's ability to adapt to new tasks -- is critical for continual and transfer learning.
arXiv:2609.39222v1 Announce Type: new Abstract: High-compression tokenizers are essential for scaling latent image generative models. However, aggressive compression creates a fundamental tradeoff be...