Quantization, distillation, pruning and serving work aimed at the same accuracy for less memory, latency and money.
arXiv:2606. 10705v1 Announce Type: cross Abstract: Reinforcement learning promises to optimize sequential decisions in large-scale systems.
arXiv:2606. 10698v1 Announce Type: cross Abstract: In this paper, we use machine learning to discover a new seeding strategy for integration-by-parts reduction of Feynman integrals, which is a frequent bottleneck in state-of-the-art calculations in theoretical particle and gravitational-wave physics.
arXiv:2601. 13994v3 Announce Type: replace-cross Abstract: Differentiable sparse linear algebra is foundational for scientific machine learning, yet PyTorch lacks a unified library for it: torch.
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. 11156v1 Announce Type: cross Abstract: Recent one-step generative models accelerate sampling by learning deterministic flow maps of the underlying dynamics.
arXiv:2602. 22352v2 Announce Type: replace-cross Abstract: With the continuous growth of neural network scales, low-precision quantization is widely used in edge accelerators.
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. 10130v1 Announce Type: cross Abstract: Reservoir computers benefit from the inherent complexity of optical phenomena, which provide rich, often nonlinear dynamics.
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:2606. 09862v1 Announce Type: cross Abstract: The Softmax Attention operation in Transformer language models has a quadratic complexity in the sequence length and a growing state size in the form of KV cache, which becomes a bottleneck in long context scenarios.
arXiv:2606. 10646v1 Announce Type: new Abstract: Token-level credit assignment remains a key obstacle for reinforcement learning (RL) in large language models (LLMs), where RL recipes typically treat all tokens equally, failing to distinguish decisive reasoning steps from routine formatting or fluent filler.
arXiv:2606. 10820v1 Announce Type: cross Abstract: Autoregressive (AR) language modeling is the dominant paradigm for text generation, yet its sequential token-by-token decoding makes inference memory-bound and inefficient.
arXiv:2606. 10703v1 Announce Type: new Abstract: Interpretability methods routinely use population-level summary statistics over observed model behaviour to license claims about the effects of targeted interventions on specific computations; in Pearl's terms, they treat rung-1 associational evidence as if it supported rung-2 interventional conclusions, a move whose validity is rarely tested.
arXiv:2606. 09924v1 Announce Type: cross Abstract: Deploying deep neural networks on memory-constrained edge accelerators is bottlenecked by per-inference off-chip weight transfer rather than computation: the dense network cannot be retained on-chip, and every parameter must be loaded for every input.
arXiv:2606. 10154v1 Announce Type: new Abstract: Quantized checkpoints are often screened first with quality metrics and only later, if at all, with direct safety tests.
arXiv:2606. 09864v1 Announce Type: cross Abstract: Key-value (KV) cache quantization is widely used to reduce Large Language Model (LLM) inference memory, yet existing evaluations solely focus on measuring perplexity and accuracy without assessing the safety impact.
arXiv:2606. 10572v1 Announce Type: new Abstract: External memory effectively grounds large language models (LLMs) and vision-language models (VLMs)-based question answering (QA) in relevant multimodal evidence.
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. 11173v1 Announce Type: new Abstract: Conditioning a language model on additional context, such as feedback on a previous attempt, typically improves its response.
arXiv:2606. 10369v1 Announce Type: cross Abstract: As large language models (LLMs) continue to scale, it becomes increasingly challenging to grow model capacity under fixed computation budgets.