arXiv Machine Learning June 16, 2026 By Janghwan Lee, Sihwa Lee, Jinseok Kim, Yongjik Kim, Jieun Lim, Jinwook Oh, Jungwook Choi

ReQAT: Achieving Full-Precision Reasoning Accuracy with 4-bit Floating-Point Quantization-Aware Training

Read the original on arXiv Machine Learning →

arXiv:2606. 15682v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) achieve strong problem-solving through long chain-of-thought, but their deployment is constrained by the high cost of full-precision inference and growing KV cache footprints.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv AI

Jun 2

Extreme Low-Bit Inference in Reasoning Models: Failure Modes and Targeted Recovery

arXiv:2606. 02011v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) rely on long reasoning traces, making inference expensive.

By Ekaterina Alimaskina, Darya Rudas, Denis Shveykin, Gleb Molodtsov, Pavel Vasiliev, Aleksandr Beznosikov

efficiency benchmarks

arXiv AI

Jun 12

ReSET: Accurate Latency-Critical NVFP4 Reasoning via Step-Aware Temperature Scaling

arXiv:2606. 13233v1 Announce Type: cross Abstract: Large reasoning models (LRMs) improve complex problem-solving by generating long intermediate reasoning traces, but this substantially increases inference costs.

By Sihwa Lee, Janghwan Lee, Donghoon Yoo, Jae Gon Kim, Hanyul Ryu, Soojung Ryu, Jungwook Choi

efficiency benchmarks

Hugging Face Trending Papers

Jun 1

Extreme Low-Bit Inference in Reasoning Models: Failure Modes and Targeted Recovery

Large Reasoning Models (LRMs) rely on long reasoning traces, making inference expensive. While low-bit quantization reduces per-token decoding cost, we show that aggressive 2-bit inference can fail to deliver end-to-end speedup because instability in the generation process inflates total token count.

efficiency benchmarks

arXiv Machine Learning

Jun 26

What Survives When You Compress a Recursive Reasoner for the Edge?

arXiv:2606. 26488v1 Announce Type: new Abstract: Recursive reasoning models can solve complex structured tasks with only a few million parameters by repeatedly updating a latent state.

By Pearse Jim, Steven Kolawole, Opegbemi Matthias Busoye, Glory Bagai, Virginia Smith

rag efficiency

arXiv Machine Learning

Sep 23

Train Where the Quantized Model Goes: On-Policy Distillation for Low-Bit Reasoning

arXiv:2609.26708v1 Announce Type: new Abstract: Quantization-aware distillation (QAD) restores much of the short-form question-answering performance lost to sub-3-bit quantization, yet leaves mathema...

By Yuanteng Chen, Zhilei Liu, Peisong Wang, Yuantian Shao, Chuangyi Li, Weining Wang, Shuang Qiu, Gang Li, Jing Liu, Jian Cheng

efficiency benchmarks safety

arXiv AI

Jul 29

Stable FP4 Training via Transposition-Invariant Block Quantization

arXiv:2607. 24953v1 Announce Type: cross Abstract: Reducing training precision is a key lever for improving the e ciency of large language model (LLM) training, but pushing beyond FP8 to 4-bit oating point (FP4) remains challenging due to instability during optimization.

By Mehdi Rahimifar, Amin Darabi, Mehran Taghian Jazi, Xing Huang, Yao Wang, Zhijun Tu, Yufei Cui, Yunke Peng, Hongliang Li

llms efficiency

One email a morning, machine-written

Related stories

Extreme Low-Bit Inference in Reasoning Models: Failure Modes and Targeted Recovery

ReSET: Accurate Latency-Critical NVFP4 Reasoning via Step-Aware Temperature Scaling

Extreme Low-Bit Inference in Reasoning Models: Failure Modes and Targeted Recovery

What Survives When You Compress a Recursive Reasoner for the Edge?

Train Where the Quantized Model Goes: On-Policy Distillation for Low-Bit Reasoning

Stable FP4 Training via Transposition-Invariant Block Quantization