Quantization, distillation, pruning and serving work aimed at the same accuracy for less memory, latency and money.
arXiv:2603. 18016v2 Announce Type: replace-cross Abstract: Speculative decoding (SD) accelerates large language model inference by using a smaller draft model to propose draft tokens that are subsequently verified by a larger target model.
arXiv:2508. 17320v3 Announce Type: replace Abstract: Understanding the internal representations of large language models (LLMs) remains a central challenge for interpretability research.
arXiv:2606. 02455v1 Announce Type: new Abstract: Molecular dynamics (MD) is a key tool for simulating the dynamical behavior of atomic systems.
arXiv:2606. 00312v1 Announce Type: cross Abstract: Over the past half-dozen years, stochastic rounding (SR) has regained significant attention as a quantization scheme for low-precision floating-point arithmetic, with applications spanning numerical analysis and modern machine learning systems.
arXiv:2606. 00105v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) have achieved remarkable progress on vision-language tasks, but they may also memorize and expose sensitive or restricted knowledge, raising concerns about privacy and broader safety risks.
arXiv:2606. 00440v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards has rapidly advanced reasoning in vision--language models.
arXiv:2606. 01987v1 Announce Type: cross Abstract: We show that the Vehicle Routing Problem (VRP) can be reformulated as a Graph Edit Distance (GED) maximization problem.
arXiv:2606. 00642v1 Announce Type: new Abstract: Reasoning traces have become a valuable form of learning signals for improving and transferring the capabilities of large language models.
arXiv:2507. 19881v2 Announce Type: replace-cross Abstract: Federated domain generalization has shown promising progress in image classification by enabling collaborative training across multiple clients without sharing raw data.
arXiv:2606. 02011v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) rely on long reasoning traces, making inference expensive.
arXiv:2606. 00382v1 Announce Type: new Abstract: Sequential fine-tuning of large language models forces a choice: let the shared substrate keep learning and accept catastrophic forgetting, or freeze it after task one and foreclose cross-task refinement.
arXiv:2606. 01402v1 Announce Type: cross Abstract: Neural network compression is commonly achieved by pruning parameters based on local importance scores, e.
arXiv:2605. 12400v2 Announce Type: replace-cross Abstract: We study on-policy self-distillation (OPSD), where a language model improves its reasoning ability by distilling privileged teacher distributions along its own on-policy trajectories.
arXiv:2605. 00161v2 Announce Type: replace Abstract: Diffusion language models (DLMs) are an attractive alternative to autoregressive models because they promise sublinear-time, parallel generation, yet practical gains remain elusive as high-quality samples still demand hundreds of refinement steps.
arXiv:2606. 01790v1 Announce Type: cross Abstract: Vision-language-model-based graphical user interface (GUI) agents have shown broad automation capabilities, yet deployment is bottlenecked by a key-value (KV) cache that grows linearly with interaction steps.
arXiv:2606. 01839v1 Announce Type: cross Abstract: LLM-based agents resolve a user task through many turns of dependent inference and tool calls, producing a workload whose total cost is unknown when the task arrives.
arXiv:2606. 02256v1 Announce Type: new Abstract: Our work presents a method for ECG segmentation and arrhythmia detection using Tiny Machine Learning (TinyML) models for real-time, on-device inference on resource-constrained embedded systems.
arXiv:2602. 08585v2 Announce Type: replace-cross Abstract: Given the quadratic complexity of attention, KV cache eviction is vital to accelerate model inference.
arXiv:2512. 00062v2 Announce Type: replace-cross Abstract: Robotic policy learning for complex real-world manipulation tasks has seen rapid recent progress, enabled in large part by the ability to collect demonstrations through human operation.
arXiv:2606. 00462v1 Announce Type: cross Abstract: Short-form text rewriting is a constrained variant of paraphrasing in which limited context and high semantic density leave little room for variation.