Quantization, distillation, pruning and serving work aimed at the same accuracy for less memory, latency and money.
arXiv:2607. 12792v1 Announce Type: cross Abstract: Jailbreak-robustness research typically evaluates safety through generated responses using an LLM-as-judge approach.
arXiv:2607. 11933v1 Announce Type: cross Abstract: Cross-encoders achieve high reranking accuracy in Retrieval-Augmented Generation (RAG) pipelines but impose quadratic inference costs that limit real-time deployment.
arXiv:2607. 11952v1 Announce Type: new Abstract: Network alignment identifies node correspondences across different networks and is a fundamental primitive in many data science applications, including social network analysis, fraud detection, and knowledge graph integration.
arXiv:2607. 12550v1 Announce Type: new Abstract: The key-value (KV) cache has become the dominant memory cost of transformer inference.
arXiv:2607. 12166v1 Announce Type: new Abstract: Sparse autoencoders (SAEs) are the standard for decomposing superposed neural representations into interpretable features, and evaluation relies predominantly on correlational recovery metrics -- cosine similarity between ground-truth directions and decoder atoms.
arXiv:2602. 19938v2 Announce Type: replace Abstract: Sparse Mixture-of-Experts (SMoE) architectures are increasingly used to scale large language models efficiently, delivering strong accuracy under fixed compute budgets.
arXiv:2605. 12765v3 Announce Type: replace Abstract: Large Language Models memorize vast amounts of training data, raising concerns regarding privacy, copyright infringement, and safety.
arXiv:2607. 12789v1 Announce Type: new Abstract: The $\mathcal{O}(N^2)$ complexity of attention over $N$ tokens remains a computational bottleneck in transformer models.
arXiv:2601. 10199v2 Announce Type: replace Abstract: Multivariate data often exhibit complex dependencies that violate the assumption of isotropic residual noise.
arXiv:2607. 12829v1 Announce Type: cross Abstract: Diffusion large language models (dLLMs) offer a theoretical advantage in parallel generation over standard autoregressive models.
arXiv:2607. 12928v1 Announce Type: new Abstract: We study the online binary sequential calibration problem.
arXiv:2607. 11938v1 Announce Type: cross Abstract: This book is about the mathematical foundations of data science.
arXiv:2607. 11919v1 Announce Type: cross Abstract: Human memory is reconstructive, not a faithful recording.
arXiv:2607. 11986v1 Announce Type: cross Abstract: Perineural invasion (PNI) is associated with poor prognosis in cholangiocarcinoma (CCA).
arXiv:2505. 12682v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly released under restricted licenses, creating a growing need for robust model ownership verification.
arXiv:2607. 11898v1 Announce Type: cross Abstract: Large-scale text corpora have become a quiet bottleneck in modern NLP, not just in storage, but in the accumulated cost of training, fine-tuning, and continual learning.
arXiv:2607. 12121v1 Announce Type: cross Abstract: Diffusion models have become the central backbone for modern image, video, and audio generation, but their efficient service remains a challenge.
arXiv:2607. 11897v1 Announce Type: new Abstract: Linear attention replaces softmax attention's growing KV cache with a fixed recurrent state, but this compression limits exact state tracking and long-context memory.
arXiv:2603. 28583v2 Announce Type: replace-cross Abstract: Despite the success of Vision-Language Models (VLMs), misleading charts remain a significant challenge due to their deceptive visual structures and distorted data representations.
arXiv:2602. 02244v3 Announce Type: replace Abstract: The standard post-training recipe for large reasoning models, supervised fine-tuning followed by reinforcement learning (SFT-then-RL), may limit the benefits of the RL stage: while SFT imitates expert demonstrations, it often causes overconfidence and reduces generation diversity, leaving RL with a narrowed solution space to explore.