Quantization, distillation, pruning and serving work aimed at the same accuracy for less memory, latency and money.
arXiv:2606. 03091v1 Announce Type: cross Abstract: Sequential recommendation systems are widely adopted but often deployed as black-box APIs, which has driven recent interest in model extraction to replicate their capabilities locally.
arXiv:2606. 03014v1 Announce Type: new Abstract: Mixture-of-Agents (MoA) systems improve reasoning accuracy by routing each query to multiple expert LLMs and aggregating their outputs.
arXiv:2606. 02673v1 Announce Type: new Abstract: Graphs have been used to enhance large language models (LLMs) for structured reasoning, mostly as external knowledge sources are provided to models at test time.
arXiv:2506. 06295v2 Announce Type: replace-cross Abstract: Autoregressive Models (ARMs) have long dominated the landscape of Large Language Models.
arXiv:2512. 03627v2 Announce Type: replace Abstract: Despite rapid progress in large-scale language and vision models, AI agents still suffer from a fundamental limitation: they cannot remember.
arXiv:2606. 03002v1 Announce Type: cross Abstract: Quantization is a standard path to deploying large language models, and a quantized model is typically judged acceptable when its perplexity or downstream accuracy stays close to the full-precision original.
arXiv:2606. 03620v1 Announce Type: cross Abstract: Self-distilled policy optimization (SDPO) has become a popular paradigm for LLM post-training, where a model learns from its own predictions conditioned on privileged information.
arXiv:2606. 03428v1 Announce Type: cross Abstract: The large sizes of Spiking Vision Transformers (SViTs) still hinder their embedded implementation, highlighting the need for model compression.
arXiv:2606. 03330v1 Announce Type: cross Abstract: Literature reveals that a Large Language Model's (LLM) behavior is not only conditioned by its original weights but also its instance-level parameters, such as instructional prompt, sampling configuration or quantization.
arXiv:2412. 01282v2 Announce Type: replace-cross Abstract: Vision-Language Models (VLMs) bring powerful understanding and reasoning capabilities to multimodal tasks.
arXiv:2606. 03819v1 Announce Type: new Abstract: One-shot block drafters for speculative decoding generate the full draft in a single forward pass, achieving strong throughput by eliminating sequential token generation.
arXiv:2606. 03180v1 Announce Type: cross Abstract: Vision-language models (VLMs) for radiology have emerged as a scalable paradigm by leveraging image-report pairs naturally produced in clinical workflows.
arXiv:2505. 23725v3 Announce Type: replace Abstract: DiLoCo is a powerful framework for training large language models (LLMs), enabling larger optimal batch sizes and increased accelerator utilization under networking constraints.
arXiv:2412. 05109v2 Announce Type: replace Abstract: We derive universal approximation results for the class of (countably) $m$-rectifiable measures.
arXiv:2606. 03553v1 Announce Type: cross Abstract: While principal component analysis (PCA) is a fundamental tool for dimensionality reduction, its dense representations make it ill-suited for high-dimensional data.
arXiv:2605. 01712v2 Announce Type: replace Abstract: Pareto set learning (PSL) is an emerging paradigm in multi-objective optimization that trains neural networks to map preference vectors to Pareto optimal solutions.
Federated Learning (FL) of foundation and edge models increasingly targets deployments where client data distributions drift over time, yet existing forgetting-mitigation methods assume each client's distribution is stationary. Flashback, the strongest recent FL method against cross-client (spatial) forgetting, uses monotonically accumulating per-class label counts as a knowledge proxy; this proxy becomes miscalibrated under temporal distribution shift and anchors the global model to an outdated class balance.
World models and multimodal large language models (MLLMs) provide complementary capabilities for predicting future outcomes from static visual observations. World models can generate concrete visual rollouts of possible futures, while MLLMs can reason abstractly over questions, goals, and rules.
Vision-Language Models (VLMs) have demonstrated remarkable capabilities but suffer from significant computational overhead during inference. While visual token pruning offers a promising solution, existing methods predominantly rely on initial attention scores.
arXiv:2606. 00147v1 Announce Type: cross Abstract: Domain-specific supervised fine-tuning (SFT) often improves in-domain performance at the cost of degrading a model's general capabilities.