Inference efficiency

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

3,248 stories · RSS feed

arXiv AI
Jul 7

dOPSD: On-Policy Self-Distillation for Diffusion Language Models

arXiv:2607. 04428v1 Announce Type: cross Abstract: Diffusion large language models (dLLMs) generate text by iteratively denoising a masked sequence, offering a parallel alternative to autoregressive models, but eliciting strong reasoning through post-training remains difficult: supervised fine-tuning is off-policy and suffers from exposure bias, while reinforcement learning gives only sparse, sequence-level rewards and is hard to apply without tractable sequence likelihoods.

By Phuong Tuan Dat, Qi Li, Xinchao Wang
arXiv AI
Jul 7

HASSL: Hierarchy-Aware Self-Supervised Learning Framework for Single Cell Microscopy

arXiv:2607. 04353v1 Announce Type: cross Abstract: Hierarchical structure is common in image data, where fine-grained clusters often merge into larger, coarser semantic groups.

By Julius Riel, Vishwa Mohan Singh, Sai Anirudh Aryasomayajula, Anuun Chinbat, Hannes Leonhard, Moritz Ladenburger, Frederik Alexander, Vishisht Choudhary, Fabio Laredo, Giacomo Masserdotti, Thorben Prein, Carsten Marr, Amirhossein Kardoost
arXiv AI
Jul 7

HiFA4: Training-Free 4-bit FlashAttention on Ascend HIF4 NPUs for LLM Inference

arXiv:2607. 04302v1 Announce Type: cross Abstract: We present HiFA4, a post-training operator-level design that executes both QK^T and PV in FlashAttention as 4-bit HIF4 Cube GEMMs for LLM inference on Ascend NPUs, while maintaining the online softmax state in FP16.

By Hui Dong, Yanzhao Li, Jie Gao, Chunlu Li, Zhiyuan Zhang, Yupeng Sun, Zhenyuan Chen, Zhiqiang Zou
arXiv AI
Jul 7

From Arithmetic to Logic: The Resilience of Logic and Lookup-Based Neural Networks Under Parameter Bit-Flips

arXiv:2603. 22770v2 Announce Type: replace-cross Abstract: The deployment of deep neural networks (DNNs) in safety-critical edge environments necessitates robustness against hardware-induced bit-flip errors.

By Alan T. L. Bacellar, Sathvik Chemudupati, Shashank Nag, Allison Seigler, Priscila M. V. Lima, Felipe M. G. Fran\c{c}a, Lizy K. John
arXiv AI
Jul 7

Walrus: A Cross-Domain Foundation Model for Continuum Dynamics

arXiv:2511. 15684v2 Announce Type: replace-cross Abstract: Foundation models have transformed machine learning for language and vision, but achieving comparable impact in physical simulation remains a challenge.

By Michael McCabe, Payel Mukhopadhyay, Tanya Marwah, Bruno Regaldo-Saint Blancard, Francois Rozet, Cristiana Diaconu, Lucas Meyer, Kaze W. K. Wong, Hadi Sotoudeh, Alberto Bietti, Irina Espejo, Rio Fear, Siavash Golkar, Tom Hehir, Keiya Hirashima, Geraud Krawezik, Francois Lanusse, Rudy Morel, Ruben Ohana, Liam Parker, Mariel Pettee, Jeff Shen, Kyunghyun Cho, Miles Cranmer, Shirley Ho
arXiv AI
Jul 7

Metronome: Bound the Cache, Keep the Beat for Real-Time Interaction Model Serving

arXiv:2607. 02640v1 Announce Type: cross Abstract: Real-time interaction models -- Moshi, MiniCPM-o, Qwen-Omni -- turn serving into a periodic real-time task: on every frame a session ingests streaming audio and must respond by a recurring wall-clock deadline, while its KV cache grows monotonically and stays pinned for the whole conversation.

By Jiaying Meng, Bojie Li