Quantization, distillation, pruning and serving work aimed at the same accuracy for less memory, latency and money.
arXiv:2607. 21692v2 Announce Type: replace Abstract: Sparse attention prunes a long context to the blocks a model needs, and the usual selector is distilled from a dense teacher's attention.
arXiv:2607. 26631v1 Announce Type: new Abstract: Human Activity Recognition (HAR) from wearable sensors supports applications in healthcare, rehabilitation, fitness tracking, and smart environments.
arXiv:2607. 26722v1 Announce Type: cross Abstract: Harness plays a critical role in large language model agent performance, and building a high-performing harness requires substantial expert effort.
Vision-language-action (VLA) models commonly adopt an LLM-centric $V \to L \to A$ pathway, where visual observations are projected into the representation space of a large language model before being decoded into robot actions. Although effective, this design incurs substantial computation and memory overhead at every policy invocation.
Traditional search systems are optimized to retrieve items that strictly match a query, often prioritizing precision over recall. In e-commerce marketplaces and particularly grocery, this paradigm is limiting, as user satisfaction and commercial outcomes depend heavily on the discoverability of substitute, complementary, and thematically related items.
Large language models are increasingly deployed with persistent personalized context, such as accumulated memory profiles or long conversation histories, that is shared across a user's many requests. Production memory systems (e.
In this paper, we formulate three communication tasks for empirical optimal transport: distributed coupling sampling, cost-evaluable coupling output, and scalar value-certified sampling. Our main result is a field-code compiler: any communicated transport field approximating an optimal empirical Monge map to error $η$ can be completed by sparse target-cell residuals into an exact-marginal value-certified sampler with scalar certificate $W_1(μ,ν)\leq U\leq W_1(μ,ν)+2Δ$, where $Δ$ is the public target-partition diameter.
Knowledge distillation (KD) enables a compact student model to learn from a powerful teacher and has become an effective paradigm for model compression. The emergence of diverse model architectures has extended KD from homogeneous to heterogeneous settings.
Federated learning (FL) enables collaborative learning over decentralized data silos without centralizing raw data. However, heterogeneous local architectures often induce non-aligned representation spaces, making it difficult to transfer global knowledge across silos.
Dataset distillation compresses large-scale datasets into compact synthetic sets while preserving their training utility, enabling efficient 3D point cloud training. Current point cloud dataset distillation methods only tackle geometric and representation challenges while ignoring the distributional imbalance prevalent in point cloud datasets where both training and test splits follow long-tailed class distributions.
Spiking neural networks (SNNs) are promoted as an energy-efficient substrate because sparse, event-driven activity replaces dense multiply-accumulates with cheap accumulates. We argue the energy dividend of sparsity is not a property of SNNs but of the task.
Figure 1: CUDA-to-MLX optimization translation map. CUDA optimization knowledge can be translated into architecture-native MLX strategies rather than copied instruction-for-instruction.
Human Activity Recognition (HAR) from wearable sensors supports applications in healthcare, rehabilitation, fitness tracking, and smart environments. Yet, existing deep learning approaches require dataset-specific training, large labeled corpora, and repeated adaptation to new sensor settings or activity taxonomies.
arXiv:2607. 24771v1 Announce Type: new Abstract: Knowledge injection updates pretrained MLLMs with new factual or domain-specific knowledge, but fitting full authoritative answers can cause drift in non-updated behavior.
arXiv:2607. 24833v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards is a powerful paradigm for eliciting reasoning in large language models, yet it suffers from severe reward sparsity on competition-level mathematics.
arXiv:2607. 25970v1 Announce Type: cross Abstract: RL for code correctness is now established: have the model generate a program, run it against hidden test cases, and reward solutions that pass.
arXiv:2607. 25182v1 Announce Type: cross Abstract: The ability to retrieve relevant tables for answering questions is a key task for structured information retrieval.
arXiv:2607. 25947v1 Announce Type: new Abstract: Question answering (QA) over irregular clinical time series (ICTS) plays a pivotal role in a wide range of healthcare applications.
arXiv:2607. 24788v1 Announce Type: new Abstract: As Large Language Models scale to increasingly long contexts, the memory I/O and computational overhead of the Key-Value (KV) cache during decoding emerges as the primary throughput bottleneck.
arXiv:2607. 25504v1 Announce Type: cross Abstract: Fine-grained weight pruning and activation sparsification have emerged as effective approaches for reducing the compute and memory cost of inference for Transformer models.