Quantization, distillation, pruning and serving work aimed at the same accuracy for less memory, latency and money.
arXiv:2605. 31191v2 Announce Type: replace Abstract: We investigate how teacher-student capacity relationships modulate knowledge distillation (KD) effectiveness in ResNet-based image classification on CIFAR-10.
arXiv:2607. 10805v1 Announce Type: cross Abstract: On-Policy Self-Distillation (OPSD) has emerged as a crucial paradigm for enhancing and aligning Large Language Models (LLMs).
arXiv:2607. 10044v1 Announce Type: new Abstract: Constrained decoding is essential in generative retrieval, where document identifiers generated directly from a query must exactly match a predefined library of valid IDs.
arXiv:2601. 07372v2 Announce Type: replace-cross Abstract: While Mixture-of-Experts (MoE) scales capacity via conditional computation, Transformers lack a native primitive for knowledge lookup, forcing them to inefficiently simulate retrieval through computation.
arXiv:2601. 07155v3 Announce Type: replace-cross Abstract: Knowledge distillation (KD) is a widely adopted technique for transferring knowledge from large language models to smaller student models; however, conventional supervised KD often suffers from a distribution mismatch between training and inference.
arXiv:2607. 10582v1 Announce Type: cross Abstract: Large language model (LLM) agents accumulate heterogeneous context, including system instructions, plans, user turns, retrieved documents, tool outputs, and intermediate reasoning, whose key-value (KV) cache can become a major memory bottleneck.
arXiv:2607. 09680v1 Announce Type: cross Abstract: Continuous cardiac monitoring in wearable devices demands classifiers that are simultaneously accurate, energy-efficient, and deployable on resource-constrained hardware.
arXiv:2607. 10836v1 Announce Type: new Abstract: Multi-agent ensembling multiplies active parameters and inference cost without answering three basic questions: which agents to consult, how deeply a query should traverse a hierarchy of agents, and when inter-agent communication is worth its cost.
arXiv:2607. 10113v1 Announce Type: new Abstract: Large language model agents increasingly store reusable procedures outside the model.
arXiv:2607. 09957v1 Announce Type: cross Abstract: This report studies on-device English-to-Traditional-Chinese subtitle translation for Taiwan under short inputs, short outputs, batch-size-one inference, low latency, and privacy constraints.
arXiv:2507. 01042v2 Announce Type: replace-cross Abstract: Vision-Language Models (VLMs) are increasingly used in industry VLM applications such as retrieval systems, content generation platforms, and decision-support workflows, where model selection is commonly guided by benchmark rankings.
arXiv:2607. 10021v1 Announce Type: new Abstract: Neural networks can learn algorithmic input-output mappings, but trusting a learned executor requires more than a correct final answer because the state transitions that produce it are usually hidden.
arXiv:2602. 17686v5 Announce Type: replace-cross Abstract: Chain-of-Thought (CoT) reasoning has significantly improved LLMs' mathematical problem-solving capabilities, but distilling such capabilities into smaller models remains challenging due to the capacity mismatch between verbose teachers and compact students.
arXiv:2510. 11546v3 Announce Type: replace-cross Abstract: High-dimensional regression often suffers from heavy-tailed noise and outliers, which can severely undermine the reliability of least-squares based methods.
arXiv:2606. 25059v2 Announce Type: replace-cross Abstract: Black-box LLMs (accessible only via API) are vulnerable to distillation attacks, in which an attacker queries the model and trains a student on its outputs.
arXiv:2112. 06362v5 Announce Type: replace Abstract: We consider the problem of scheduling in multi-class, parallel-server queuing systems with uncertain rewards from job-server assignments.
arXiv:2607. 09999v1 Announce Type: cross Abstract: We show that post-training quantization can silently alter how large language models reason even when task accuracy is preserved.
arXiv:2607. 09767v1 Announce Type: cross Abstract: The paper presents a voice anonymization model focusing on preserving content rather than producing realistic speech.
arXiv:2607. 10555v1 Announce Type: cross Abstract: Generative Large Language Models (LLMs) have revolutionized information retrieval, yet their strictly parametric nature frequently leads to severe factual hallucinations when confronted with complex queries beyond their epistemic boundaries.
arXiv:2607. 11257v1 Announce Type: cross Abstract: Pathology Foundation Models (PFMs) offer powerful Whole Slide Image (WSI) representations but suffer from massive computational costs.