Quantization, distillation, pruning and serving work aimed at the same accuracy for less memory, latency and money.
arXiv:2606. 10716v1 Announce Type: cross Abstract: Pre-trained language models (PLMs) have achieved strong performance in keyphrase extraction (KPE), largely due to their ability to generate rich contextualized representations.
arXiv:2606. 09886v1 Announce Type: cross Abstract: Sparse Mixture-of-Experts (MoE) large language models achieve strong quality with low per-token compute, yet their deployment is often limited by the memory wall: the full expert pool must remain resident to support token-dependent routing.
arXiv:2606. 09941v1 Announce Type: cross Abstract: Surface winds can vary substantially from one minute to the next, so there is scope for studying its variation on this fine time scale.
arXiv:2606. 09861v1 Announce Type: cross Abstract: While Next-Token Prediction (NTP) has unified LLM pretraining, its adaptation to unbounded, continuous time series (TS) remains open.
arXiv:2605. 08565v2 Announce Type: replace Abstract: Microscaling is a critical technique for preserving the quality of Large Language Models (LLMs) quantized to ultra-low precision formats.
arXiv:2606. 11156v1 Announce Type: cross Abstract: Recent one-step generative models accelerate sampling by learning deterministic flow maps of the underlying dynamics.
arXiv:2606. 10944v1 Announce Type: new Abstract: We introduce a new tool, Express, for converting a non-causal attention approximation into a causal approximation with matching approximation guarantees.
arXiv:2606. 11164v1 Announce Type: new Abstract: Long chain-of-thought (CoT) trajectories in large language model (LLM) reasoning cause severe inference bottlenecks due to rapid key-value (KV) cache growth.
arXiv:2606. 10130v1 Announce Type: cross Abstract: Reservoir computers benefit from the inherent complexity of optical phenomena, which provide rich, often nonlinear dynamics.
arXiv:2512. 24787v3 Announce Type: replace-cross Abstract: Slate recommendation, which presents users with a ranked item list in a single display, is ubiquitous across mainstream online platforms.
arXiv:2606. 11173v1 Announce Type: new Abstract: Conditioning a language model on additional context, such as feedback on a previous attempt, typically improves its response.
arXiv:2508. 07048v2 Announce Type: replace-cross Abstract: Autoregressive (AR) encoder-decoder models dominate high-quality multilingual ASR, but their left-to-right decoders make inference latency scale with transcript length.
arXiv:2606. 10493v1 Announce Type: cross Abstract: Local deployment of large Mixture-of-Experts (MoE) models falls short of the service quality achieved in cloud-scale environments, even under low-concurrency workloads.
arXiv:2606. 11033v1 Announce Type: cross Abstract: Recent efforts to extend large language models (LLMs) to speech inputs typically rely on cascaded ASR-LLM pipelines, end-to-end speech-language models, or bridge/distillation-based adaptation.
arXiv:2606. 10458v1 Announce Type: cross Abstract: We derive the optimal quantizer of a real-valued random variable $W$ with distribution $P_W$ such that 1) the distribution of the quantization output $X$ that can take $k$ values follows any specified distribution $P_X$ over $\{1,\ldots,k\}$, and 2) the minimum mean squared error (MMSE) of estimating $W$ from $X$ is minimized.
arXiv:2504. 03118v2 Announce Type: replace-cross Abstract: Vision Transformers (ViTs) often need to be compressed for deployment on resource-constrained edge devices like drones and smart vehicles.
arXiv:2606. 10385v1 Announce Type: cross Abstract: On-policy distillation (OPD) has demonstrated strong empirical gains in enhancing complex reasoning in LLMs by aligning a student model with a teacher's predictive distribution over the student's own trajectories.
arXiv:2606. 10940v1 Announce Type: cross Abstract: Camera traps have become a cornerstone of biodiversity monitoring, but the artificial intelligence that turns vast quantities of images into usable ecological data is often locked behind commercial platforms or trained on fauna that does not match that of the British Isles.
arXiv:2606. 10357v1 Announce Type: cross Abstract: Cross-domain recommendation is a core problem in content-to-e-commerce platforms.
arXiv:2606. 09888v1 Announce Type: new Abstract: Linear attention provides an efficient backbone for long-sequence recommendation by avoiding the quadratic cost of standard Transformers, but its compressed recurrent state can be dominated by repetitive behavior patterns.