Quantization, distillation, pruning and serving work aimed at the same accuracy for less memory, latency and money.
arXiv:2606. 14354v1 Announce Type: new Abstract: Federated learning is well suited to edge environments but is often limited by the uplink cost of transmitting model updates.
arXiv:2606. 14695v1 Announce Type: new Abstract: Language Models (LMs) have shown remarkable potential as role-playing chatbots, delivering consistent, stylized interactions when given a specification of a character or user persona.
arXiv:2602. 09258v2 Announce Type: replace Abstract: Deployed graph neural networks (GNNs) are frozen at deployment yet must fit clean data, generalize under distribution shifts, and remain stable to perturbations.
arXiv:2606. 13862v1 Announce Type: cross Abstract: Long Chain-of-Thought (CoT) reasoning improves LLM problem-solving but is computationally expensive due to sequential token generation.
arXiv:2606. 14010v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models have shown strong potential for end-to-end autonomous driving by jointly modeling visual perception, language reasoning, explainability and action prediction.
arXiv:2603. 15481v2 Announce Type: replace-cross Abstract: Data-free knowledge distillation enables model compression without original training data, critical for privacy-sensitive tabular domains.
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.
arXiv:2606. 13300v2 Announce Type: replace Abstract: We introduce the Trajectory-based Quantization Sensitivity Score (TQS), a metric that reframes post-training quantization (PTQ) through the lens of dynamical-systems stability.
arXiv:2603. 10444v2 Announce Type: replace-cross Abstract: FP4 training promises substantial memory and compute savings for large language models, but remains fragile because blockwise quantization is dictated by extreme activation magnitudes, which inflate dynamic range and compress long-tail signals.
arXiv:2606. 13740v1 Announce Type: new Abstract: Diffusion large language models (dLLMs) accelerate generation by denoising multiple tokens in parallel, making them attractive for latency-sensitive mobile inference.
arXiv:2505. 16120v3 Announce Type: replace Abstract: The emergence of Large Language Models (LLMs) has reshaped agent systems.
arXiv:2606. 14199v1 Announce Type: cross Abstract: Large language models are increasingly deployed as human simulators for interactive evaluation and social simulation.
arXiv:2606. 14150v1 Announce Type: new Abstract: Pruning promises a shortcut to strong small language models.
arXiv:2602. 13421v2 Announce Type: replace-cross Abstract: Computation in biological systems is fundamentally energy-constrained, yet standard theories of computation treat energy as freely available.
arXiv:2601. 00821v3 Announce Type: replace Abstract: A growing class of conversational-memory systems compresses dialogue history into structured artifacts -- extracted facts, decisions, or events -- on the premise that distilled structure retrieves better than raw text.
arXiv:2606. 13894v1 Announce Type: cross Abstract: AdamW is a default optimizer for modern deep learning, but its first and second moment states add roughly two parameter-sized buffers to training memory.
arXiv:2603. 24596v3 Announce Type: replace-cross Abstract: While the shift from cascaded dialogue systems to end-to-end (E2E) speech Large Language Models (LLMs) improves latency and paralinguistic modeling, E2E models often exhibit a significant performance degradation compared to their text-based counterparts.
arXiv:2606. 13795v1 Announce Type: new Abstract: RL post-training has become increasingly pivotal for improving diffusion policies, but existing diffusion policy-gradient methods are often unstable and cannot achieve reliable policy improvement.
arXiv:2508. 18166v5 Announce Type: replace-cross Abstract: Modern app store recommender systems struggle with multiple-category apps, as traditional taxonomies fail to capture overlapping semantics, leading to suboptimal personalization.
Organ segmentation from PET/CT is critical for quantitative analysis and radiotherapy planning in oncology. To ease the high annotation cost of PET/CT segmentation, semi-supervised learning (SSL) provides a practical and effective solution for developing deep models with limited labeled data.