Quantization, distillation, pruning and serving work aimed at the same accuracy for less memory, latency and money.
arXiv:2606. 00735v1 Announce Type: cross Abstract: In distributed Mixture-of-Experts (MoE) inference, input-dependent token routing interacts with GPU performance variability to create persistent stragglers under synchronized execution, where the slowest GPU determines layer latency.
arXiv:2510. 08948v4 Announce Type: replace-cross Abstract: Effective e-commerce risk management requires in-depth case investigations to identify emerging fraud patterns in highly adversarial environments.
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:2605. 27864v3 Announce Type: replace Abstract: Large language models (LLMs) are increasingly applied in finance, yet most existing work emphasizes trading signals or financial NLP tasks centered on prediction.
arXiv:2606. 01689v1 Announce Type: cross Abstract: The detection and segmentation of infrared small targets have important application significance in the fields of surveillance and security, maritime rescue and so on.
arXiv:2602. 03024v2 Announce Type: replace-cross Abstract: Deep Equilibrium Models (DEQs) have emerged as a powerful paradigm in deep learning, offering the ability to model infinite-depth networks with constant memory usage.
arXiv:2606. 02559v1 Announce Type: cross Abstract: Post-training compression of Large Language Models (LLMs) removes entire architectural components, either deleting them or replacing them with fitted modules.
arXiv:2509. 25837v3 Announce Type: replace-cross Abstract: Large language models (LLMs) deliver remarkable performance but are costly to deploy, motivating knowledge distillation (KD) for efficient inference.
arXiv:2605. 24828v2 Announce Type: replace Abstract: With the continuous advancement of Large Language Models (LLMs), intelligent agents are becoming increasingly vital.
arXiv:2605. 07804v3 Announce Type: replace-cross Abstract: On-policy distillation (OPD) leverages dense teacher rewards to enhance reasoning models.
arXiv:2606. 00889v1 Announce Type: cross Abstract: Phishing attacks remain a major cybersecurity threat, exploiting deceptive URLs to steal sensitive user information.
arXiv:2606. 01923v1 Announce Type: cross Abstract: Large Language Models (LLMs) frequently exhibit "contextual disregard" when faced with input evidence that conflicts with their internal parametric memory, leading to persistent factual hallucinations.
arXiv:2602. 10056v2 Announce Type: replace Abstract: We introduce WildCat, a high-accuracy, low-cost approach to compressing the attention mechanism in neural networks.
arXiv:2606. 00798v1 Announce Type: cross Abstract: Parameter compression of class-conditional diffusion models reveals an underexplored limitation in output-level distillation: the unconditional score branch remains unsupervised, leaving the classifier-free guidance gap underdetermined in the student.
arXiv:2605. 12652v2 Announce Type: replace-cross Abstract: Large language models are often post-trained with sparse verifier rewards, which indicate whether a sampled trajectory succeeds but provide limited guidance about where reasoning succeeds or fails.
arXiv:2605. 27095v2 Announce Type: replace Abstract: Learning from demonstrations in embodied control is often cast as behavioral cloning, and recent diffusion or flow-matching policies improve this paradigm by modeling multi-modal expert actions.
arXiv:2605. 29987v2 Announce Type: replace Abstract: Although multi-scales representation learning enables elastic-dimension embeddings, nested subspaces often suffer from dimensional redundancy and spectral collapse.
arXiv:2603. 28768v2 Announce Type: replace-cross Abstract: Mixture-of-Experts (MoE) has recently emerged as the mainstream architecture for efficiently scaling large language models while maintaining near-constant computational cost.
arXiv:2606. 02011v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) rely on long reasoning traces, making inference expensive.
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.