Inference efficiency

Quantization, distillation, pruning and serving work aimed at the same accuracy for less memory, latency and money.

3,184 stories · RSS feed

Hugging Face Trending Papers
Aug 5

HiSC: Hierarchical Spatial Clustering Token Compression for Efficient 3D Scene Understanding

3D vision-language models (3D VLMs) enable spatial reasoning over multi-view scenes but suffer from substantial token redundancy due to duplicated observations and large uninformative regions, leading to high computational cost. Although visual token compression has shown promise in accelerating 2D VLMs, it fails to capture the structured nature of 3D scenes and leads to incomplete spatial coverage and loss of fine-grained details.

Hugging Face Trending Papers
Aug 5

AFD-Ledger: Deployment Provisioning for Attention--FFN Disaggregation

Attention--Feed-Forward Network (FFN) Disaggregation (AFD) is emerging as a promising architecture for serving Mixture-of-Experts (MoE) language models. While existing AFD systems improve the efficiency of disaggregated execution, they leave a deployment question unanswered: under the same model, workload, time-per-output-token (TPOT) service-level objective (SLO), hardware budget, hardware catalog, and runtime capabilities, does AFD provide higher throughput than the best collocated deployment?

arXiv AI
Aug 5

Adaptive Two-Stage Visual Token Pruning for Efficient Inference in Video-Language Models

arXiv:2608. 03112v1 Announce Type: cross Abstract: Vision-language models excel at image and video understanding but suffer from high inference latency due to the need to process thousands of tokens per image, limiting their deployment on resource-constrained edge devices and in real-time surveillance applications.

By Paribesh Regmi, Qingshuang Chen, Chi Zhang, Heba Aly, Yelin Kim, Hongda Mao
arXiv Machine Learning
Aug 5

Any-OPD: Heterogeneous On-Policy Distillation for Flow-Matching Models via Representation-Space Bridging

arXiv:2608. 03316v1 Announce Type: new Abstract: On-policy distillation, in which a teacher corrects samples that the student itself generates, presupposes that the two models speak the same language: identical VAE latents, matching architectures, and a common timestep grid.

By Siming Fu, Zheming Fu, Ruizhe He, Hualiang Wang, Jie Huang, Xiaoxiao Ma, Mingchen Zhong, Weihu Huang, Xiaoxuan He, Haojun Xu
arXiv Machine Learning
Aug 5

Target-Aware Early Stage Ranking

arXiv:2511. 21095v2 Announce Type: replace Abstract: Early Stage Ranking (ESR) in large-scale recommendation systems is dominated by ''user--item decoupling'' Two Tower architectures, which scale efficiently but cannot capture fine-grained, target-aware user--item interactions directly.

By Juhee Hong, Meng Liu, Shengzhi Wang, Jin Zhou, Xiaoheng Mao, Zhao Zhu, Ruochen Liu, Huihui Cheng, Leon Gao, Christopher Leung, Chandra Mouli Sekar, Yijia Liu, Boyang Yu, Tuan Trieu, Dawei Sun, Jeet Kanjani, Rui Li, Jing Qian, Xuan Cao, Minjie Fan, Mingze Gao
arXiv AI
Aug 5

PLAN: Parallel Liquid-Inspired Approximation Network for Efficient Representation Learning in Flexible Job Shop Scheduling

arXiv:2608. 03041v1 Announce Type: cross Abstract: Deep reinforcement learning (DRL) approaches for flexible job shop scheduling (FJSP) heavily rely on attention-centric architectures to achieve state-of-the-art performance.

By Dhivya Dharshini Kannan, Wei Zhang, Jieyi Bi, Yingpeng Du, Tianjun Wei, Jie Zhang, Zuming Liu, Anupam Trivedi
arXiv AI
Aug 5

SKILL-KD: Contrastive Skill Distillation for LLM Agents

arXiv:2607. 28048v2 Announce Type: replace Abstract: Skill-based prompting has become a practical mechanism for improving large language model (LLM) agents, yet existing skill acquisition methods often treat skills as experience summaries, memory entries, or direct summaries of successful demonstrations.

By Qiming Shi, Yibo Dou, Jiawen Zhu, Yulong Tao, Linbo Jin, Zhaolu Kang, Yunfan Zhou, Di Weng
arXiv Machine Learning
Aug 5

Latent Reward Registers for Diffusion Preference Alignment

arXiv:2608. 03929v1 Announce Type: new Abstract: Aligning diffusion models with human preferences usually relies on a sparse terminal reward evaluated on the final generated samples, presenting a severe temporal credit-assignment challenge across the multi-step denoising process.

By Yuanshen Guan, Zipeng Feng, Zhiwei Xiong, Peiqin Sun
arXiv Machine Learning
Aug 5

A Physics-Flavored Transformer Network for Parametrizing Contraction Dynamics of Engineered Skeletal Muscle Tissues

arXiv:2608. 03927v1 Announce Type: new Abstract: Engineered Skeletal Muscle Tissues (ESMs) have become a key structure for biomedical disease modeling and pharmacological screening, yet their functional characterization often relies on simplistic metrics like peak force, discarding critical kinetic information.

By Mattias Luber, Timo Betz