Quantization, distillation, pruning and serving work aimed at the same accuracy for less memory, latency and money.
arXiv:2606. 18203v1 Announce Type: cross Abstract: The LLM-empowered personal health agents with user health (sensor) metrics have offered a promising pathway to alleviate global disparities in healthcare access.
arXiv:2606. 17104v1 Announce Type: cross Abstract: As large language models (LLMs) are increasingly deployed in latency- and cost-sensitive settings, inference efficiency has become a central systems challenge.
arXiv:2606. 17082v1 Announce Type: cross Abstract: End-to-end autonomous parking has emerged as a critical task within the realm of autonomous driving.
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:2602. 05790v2 Announce Type: replace-cross Abstract: Fast computation of a matrix product $W^\top X$ is a workhorse of modern LLMs.
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:2603. 25414v4 Announce Type: replace-cross Abstract: A prevailing assumption in machine learning is that model correctness must be enforced after the fact.
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:2605. 29563v3 Announce Type: replace Abstract: Can VLMs predict how each camera move changes the view, and plan many such moves ahead?
arXiv:2606. 17462v1 Announce Type: new Abstract: While Website Fingerprinting (WF) attacks achieve high accuracy in controlled laboratory settings, they often degrade substantially in real-world environments due to spatio-temporal drift, browser heterogeneity, proxy obfuscation and etc.
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: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. 18101v1 Announce Type: new Abstract: Graphical user interface (GUI) grounding requires vision-language models (VLMs) to identify small target elements in high-resolution screenshots and predict precise screen coordinates.
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. 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: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. 17123v1 Announce Type: cross Abstract: In open large language model (LLM) ecosystems, models are frequently adapted across multiple domains and applications, forming multi-stage derivation chains.
arXiv:2502. 08363v3 Announce Type: replace-cross Abstract: We present Top-Theta (Top-$\theta$) Attention, a training-free method for sparsifying transformer attention during inference.
arXiv:2509. 26476v3 Announce Type: replace-cross Abstract: We study code-to-metric regression: predicting numeric outcomes of code executions, a challenging task due to the open-ended nature of programming languages.
arXiv:2606. 17491v1 Announce Type: cross Abstract: Binary data factorization is common, but real-valued methods ignore discreteness and yield hard-to-interpret factors.