arXiv Machine Learning July 3, 2026 By O. M. Kiselev

Boundary-Aware Quantization: Finite-Scale Decision Geometry of Neural Classifiers

Read the original on arXiv Machine Learning →

arXiv:2607. 01478v1 Announce Type: cross Abstract: We measured quantization-induced decision-boundary changes using local logit-margin radii, first-order boundary displacement, normal variation, slice-boundary Jaccard distance, grid prediction changes, multiclass junction counts, and low-margin boundary-band flips.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

Jun 11

Holding the FP8 Quality Ceiling at 8-Bit Weights and Activations: INT8 and GGUF Post-Training Quantization of Ideogram 4.0 for Consumer GPUs

arXiv:2606. 12280v1 Announce Type: new Abstract: Post-training quantization lets large text-to-image diffusion transformers run on consumer GPUs, yet the hardware-specific trade-offs are seldom measured directly.

By Deep Gandhi, Ali Asaria, Tony Salomone

llms diffusion computer-vision efficiency benchmarks

arXiv Machine Learning

Jul 7

Variable Bit-width Quantization: Learning Per-Group Precision for "Bigger-but-Smaller" Language Models

arXiv:2607. 02893v1 Announce Type: new Abstract: Low-bit quantization shrinks language models but treats precision as a single global hyper-parameter: every weight uses the same bit-width.

By Hamish Ogilvy

llms efficiency

arXiv Machine Learning

2d ago

The Integer Alibi: Localizing Cross-Kernel Divergence in INT8-Quantized LLM Inference

arXiv:2608. 13756v1 Announce Type: new Abstract: Two GPU kernels implementing the same scaled INT8 GEMM interface are usually treated as interchangeable.

By Teng-Ruei Chen

llms efficiency benchmarks

arXiv Machine Learning

6d ago

SoftWater: Class-Aware Rate Allocation for Softmax Quantization

arXiv:2608. 12026v1 Announce Type: new Abstract: Post-training quantization pipelines routinely leave the softmax output layer in high precision.

By Joao V. Cavalcanti, Ashia C. Wilson

llms efficiency

arXiv Machine Learning

Aug 11

Which Decisions Low-Bit Quantization Breaks, and How to Predict Them

arXiv:2608. 06564v2 Announce Type: replace Abstract: Quantization is how large language models are actually deployed, and below four bits it hurts.

By Zekun Wu, Swati Dhiman, Adriano Koshiyama

llms agents efficiency benchmarks safety

arXiv Machine Learning

Jul 30

HiFloat4 Format for End-To-End Reinforcement Learning Post-Training of Large Language Models

arXiv:2607. 26515v1 Announce Type: new Abstract: We present, to our knowledge, the first end-to-end FP4 RL post-training, in which both the rollout and training policies, including their forward and backward passes, operate at 4-bit precision.

By Hei Yi Mak, Shadan Golestan, Hoang Le, Mehran Taghian Jazi, Yunke Peng, Yaoyuan Wang, Yao Wang, Junsong Wang, Tianchi Hu, Fengchen He, Guipeng Hu, Tanzila Rahman, Anandharaju Durai Raju

llms reinforcement-learning efficiency

Related stories

Holding the FP8 Quality Ceiling at 8-Bit Weights and Activations: INT8 and GGUF Post-Training Quantization of Ideogram 4.0 for Consumer GPUs

Variable Bit-width Quantization: Learning Per-Group Precision for "Bigger-but-Smaller" Language Models

The Integer Alibi: Localizing Cross-Kernel Divergence in INT8-Quantized LLM Inference

SoftWater: Class-Aware Rate Allocation for Softmax Quantization

Which Decisions Low-Bit Quantization Breaks, and How to Predict Them

HiFloat4 Format for End-To-End Reinforcement Learning Post-Training of Large Language Models