Quantization, distillation, pruning and serving work aimed at the same accuracy for less memory, latency and money.
arXiv:2608.15763v2 Announce Type: replace Abstract: AI-powered digital avatar streamers must answer product questions, engage viewers, and execute marketing strategies in real time, demanding low lat...
arXiv:2608.21811v1 Announce Type: new Abstract: Reinforcement learning for vision-language math reasoning starves under sparse reward: on a pool of 20,830 visual-math problems where Qwen2-VL-2B answe...
VeCAS is a two‑stage framework that generates contrast‑free X‑ray angiograms from non‑contrast images. Stage I localizes vascular structures using a discriminative model and cross‑modality latent distillation, while Stage II synthesizes angiographic appearance within those regions with a vessel‑focused inpainting model. Experiments on a lower‑limb vascular intervention dataset show that VeCAS improves vascular structural fidelity and image quality, and robotic guidewire navigation tests demonstrate significant reductions in time to target and operation steps.
SlideGen is a collaborative vision‑language multi‑agent framework designed to generate scientific presentation slides from research papers. It assigns specialized agents to outline the presentation structure, align figures and tables with key claims, generate speaker notes, and compose editable PPTX slides using a diverse layout library. The system introduces a geometry‑aware density metric to evaluate visual clutter and demonstrates significant improvements in layout balance, content coverage, and text coherence over existing baselines on a 200‑paper benchmark.
EG-ARSA introduces an Expert‑Grounded Distillation (EGD) framework that transfers institutional road safety expertise into a compact vision‑language model for visual road safety auditing. The method calibrates a teacher model against authoritative field audits, achieving a Cohen’s kappa of 0.74 before generating structured supervision for an 8‑billion‑parameter student model via Low‑Rank Adaptation. The authors also release Bangladesh Road Safety Audit (BD‑ARSA), an open dataset of 21,947 image‑audit records, and demonstrate that the student model outperforms both its larger teacher and Gemini‑2.5‑Flash in ordinal risk assessment and expert evaluation.
arXiv:2608.22112v1 Announce Type: cross Abstract: We present a machine learning framework for identifying sparse, interpretable models of dynamical systems directly from time-series data. Our approac...
arXiv:2608.21754v1 Announce Type: new Abstract: Despite the success of data pruning (DP) in reducing training data sizes and improving downstream model performance in classification and segmentation...
arXiv:2608.21979v1 Announce Type: new Abstract: Charitable food agencies play an important role in alleviating food insecurity by distributing donated food to people in need. However, they rely on ad...
arXiv:2608.23296v1 Announce Type: cross Abstract: Learned KV-cache eviction often faces a soft-to-hard mismatch: during training, differentiable gates typically attenuate token contributions, whereas...
arXiv:2608.21874v1 Announce Type: cross Abstract: Deep learning has achieved strong performance in encrypted traffic classification (ETC), yet its computational cost limits deployment on resource-con...
arXiv:2608.22762v1 Announce Type: new Abstract: Knowledge graph question answering (KGQA) is a key task for evaluating KG-augmented Large Language Models (LLMs), and complex KGQA that requires multi-...
arXiv:2608.21952v1 Announce Type: new Abstract: Recent advances in sequence modeling have highlighted Mamba as a state space architecture offering efficient long-range dependency modeling and providi...
arXiv:2608.23101v1 Announce Type: cross Abstract: Recent progress in the field of TinyML has demonstrated that low-power hardware based on microcontrollers can achieve bird species monitoring in real...
arXiv:2608.23144v1 Announce Type: cross Abstract: Low-bit weight quantization saves storage but leaves errors that degrade language-model quality. We introduce Activation-Weighted Seeded Residual Cod...
arXiv:2608.21764v1 Announce Type: cross Abstract: Event-based vision has emerged as a promising paradigm for energy-aware artificial intelligence (AI), offering sparse, low-latency visual signals tha...
arXiv:2608.22917v1 Announce Type: new Abstract: We present TSWAP, a deployed eight-language conversational wellness advisor grounded, via retrieval-augmented generation, in a verified knowledge base...
SemanticXR is a device‑cloud system that enables real‑time, open‑vocabulary semantic mapping and querying for XR applications while respecting power, bandwidth, and memory limits. By treating semantically identifiable objects as first‑class units, the system coordinates communication, execution, and memory across device and server, achieving a 2.2× faster server‑side mapping latency and keeping upstream bandwidth below 2.5 Mbps. On the device, an object‑level sparse local map with incremental updates delivers sub‑100 ms query latency for up to 10,000 objects, supports tens of thousands of objects within a 500 MB footprint, and adds only about 2 % to idle power.
The paper introduces Align‑LoRA, a unified LoRA framework for multi‑task learning that replaces complex, isolated adapter designs with a single‑adapter model enhanced by a higher rank and an explicit alignment loss. It demonstrates that a router‑free, multi‑head model with high inter‑head redundancy can outperform more elaborate baselines, and that a unified LoRA can achieve competitive performance while enabling weight merging and zero inference latency. Extensive experiments and theoretical analysis confirm that Align‑LoRA surpasses prevailing approaches, offering a simpler, production‑friendly paradigm for parameter‑efficient fine‑tuning of large language models.
arXiv:2608.22979v1 Announce Type: new Abstract: Deploying high-dimensional multimodal features in industrial recommender systems incurs substantial storage and latency overhead. Hard quantization is...
The paper introduces Mapping the Concept Landscape (MCL), a framework that replaces high‑dimensional feature embeddings with explicit sample‑level graphs of entities, events, and attributes for image‑caption pairs. By aggregating these graphs into a dataset‑level graph, MCL captures the global distribution of semantic concepts and identifies rare concepts. A greedy algorithm then selects samples to maximize coverage of under‑represented concepts, achieving better pruning efficiency and providing a transparent audit trail.