Quantization, distillation, pruning and serving work aimed at the same accuracy for less memory, latency and money.
arXiv:2512. 04524v4 Announce Type: replace-cross Abstract: Domain adaptive retrieval aims to transfer knowledge from a labeled source domain to an unlabeled target domain, enabling effective retrieval while mitigating domain discrepancies.
arXiv:2603. 18104v5 Announce Type: replace Abstract: Prevailing AI training assumes reverse-mode automatic differentiation over IEEE-754 arithmetic.
arXiv:2606. 17122v1 Announce Type: cross Abstract: The demand for privacy-compliant AI has amplified the need for machine unlearning; yet, existing retraining or distillation-based methods remain unverifiable and computationally costly.
arXiv:2606. 18114v1 Announce Type: cross Abstract: State Space Models (SSMs) such as Mamba-2 offer linear-time inference but their memory footprint limits edge deployment.
arXiv:2605. 20708v2 Announce Type: replace-cross Abstract: Diffusion Transformers (DiTs) have become a de facto backbone of modern visual generation, and nearly every major axis of their design -- tokenization, attention, conditioning, objectives, and latent autoencoders -- has been extensively revisited.
arXiv:2606. 17856v1 Announce Type: new Abstract: Graph-based retrieval-augmented generation (GraphRAG) is effective for knowledge-intensive and multi-hop query tasks; however, many existing methods primarily seed entity-based graphs and rely on implicit semantic relevance propagation.
arXiv:2507. 11178v3 Announce Type: replace-cross Abstract: With the advancement of deep learning technologies, various neural network-based Granger causality models have been proposed.
arXiv:2602. 05790v2 Announce Type: replace-cross Abstract: Fast computation of a matrix product $W^\top X$ is a workhorse of modern LLMs.
arXiv:2606. 17872v1 Announce Type: cross Abstract: Large language models (LLMs) outperform earlier architectures on generative inference and long-context tasks, but their large size introduces significant challenges in memory usage, energy cost, and on-device deployment.
arXiv:2606. 17409v1 Announce Type: cross Abstract: Planar path synthesis requires mechanisms whose coupler curves match a prescribed trajectory; the mapping from curve to linkage is inherently one-to-many across four-, six-, and eight-bar topologies.
arXiv:2606. 17199v1 Announce Type: cross Abstract: Standard on-policy distillation (OPD) for large language models estimates the reverse-KL objective using student-sampled tokens, yielding an unbiased single-sample Monte Carlo estimator that avoids vocabulary-wide computation.
arXiv:2606. 17579v1 Announce Type: cross Abstract: Adding LLM-generated node features to graph neural networks (GNNs) is widely reported to improve accuracy on standard benchmarks.
arXiv:2604. 18701v3 Announce Type: replace-cross Abstract: Local prediction-error-based curiosity rewards focus on the current transition without considering the world model's cumulative prediction error across all visited transitions.
arXiv:2606. 17500v1 Announce Type: new Abstract: Transformer-based models achieve strong performance for jet tagging at the CERN LHC, but deploying them in low-latency, resource-constrained trigger systems is challenging.
arXiv:2606. 17249v1 Announce Type: cross Abstract: The dominant trajectory of modern machine learning has been to scale up: larger models, larger accelerators, larger memory budgets.
arXiv:2506. 17639v2 Announce Type: replace-cross Abstract: Vision-Language-Action models (VLA) have demonstrated remarkable capabilities and strong potential in complex robotic manipulation.
arXiv:2606. 17081v1 Announce Type: cross Abstract: Disaggregated inference architectures physically separate prefill and decode phases onto distinct GPU pools, creating competing "agents" that share a fixed hardware budget.
Natural language understanding often depends on meanings that are implied rather than explicitly stated, requiring pragmatic reasoning. Despite strong performance on math and logical reasoning, large language models (LLMs) still struggle with making pragmatic inferences, often choosing literal interpretations.
Transformer-based models achieve strong performance for jet tagging at the CERN LHC, but deploying them in low-latency, resource-constrained trigger systems is challenging. We present an initial implementation of a quantized, integer-only transformer for jet tagging on the AMD Versal AI Engine (AIE), mapping dense and multi-head attention (MHA) layers to AIE tiles.
arXiv:2606. 16655v1 Announce Type: new Abstract: One-Shot Federated Learning (OSFL) addresses extreme communication regimes in which clients interact with the server only once, amplifying the impact of heterogeneous client data distributions.