The paper demonstrates that greedy decoding from large language models is not precision‑invariant: the same model, prompt, and decoding algorithm can produce different outputs when run in BF16 versus FP16 on identical hardware. Across six models (1.1B–7B parameters, four families, and 12B) and three benchmarks, 49–100 % of prompts diverge, with a single token flip often cascading into trajectory‑level divergence. The authors develop an empirical error‑propagation analysis that identifies the top‑two logit margin at the LM head as the key factor, and they propose a low‑overhead intervention—selective FP32 LM head recomputation—that improves exact agreement by 22–36 percentage points with less than 4 % latency overhead.
"whyItMatters":"The findings reveal that precision choices can fundamentally alter model outputs, challenging the assumption of deterministic greedy decoding and highlighting the need for precision‑aware inference strategies."
By Gaoyuan Du, Anam Nawaz Khan, Rex Zhou, Xiaoyang Liu, Deepayan Chakrabarti, Fnu Suya, Xueping Li
arXiv:2607. 07382v1 Announce Type: new Abstract: Fast Radio Bursts (FRBs) are millisecond-duration radio transients whose automated detection increasingly relies on highly specialized deep learning models.
By Raiff H. Santos, Amilcar R. Queiroz, Tharcisyo S. S. Duarte, K. E. L. de Farias, Rafael A. Batista
The paper investigates how different optimizers acquire distinct generalizing relations in single‑hidden‑layer ReLU networks. By manipulating nuisance‑connected weights and performing a strict‑parity sweep, the authors show that training conditions reshape both shared failures and relative optimizer advantages, with specific interventions improving accuracy on hard stages. The study also compares optimizer behavior across tasks and an external architecture (CIFAR‑10).
By Gongyue Zhang, Honghai Liu
arXiv:2607. 02805v1 Announce Type: cross Abstract: High-throughput long-context generation is one of the central challenges for large language models.
By Pranshu Chaturvedi, Parth Shroff, Tarun Suresh, Hangoo Kang, Kaiyue Wen
arXiv:2608. 02947v1 Announce Type: new Abstract: The attention score with rotary position embeddings (RoPE) decomposes exactly into a sum over its 2D-rotation frequency pairs, and each pair's wavelength limits how far it can discriminate position.
By Shun-ichiro Hayashi, Daichi Mukunoki, Tetsuya Hoshino, Takahiro Katagiri
arXiv:2606. 12489v2 Announce Type: replace-cross Abstract: Molecular communication (MC) suffers from severe diffusion memory because molecules released for one symbol may arrive during later symbol intervals.
By Melih \c{S}ahin, Ozgur B. Akan
arXiv:2608. 20210v1 Announce Type: cross Abstract: Small language models are usually built like large ones and then squeezed onto a CPU afterwards.
By Christos Koutsiaris
arXiv:2606. 02628v1 Announce Type: new Abstract: We investigate whether open-source LLMs encode a linearly separable truthfulness signal in their hidden states, and at which network depth this signal is strongest.
By Aizierjiang Aiersilan
arXiv:2607. 13205v1 Announce Type: cross Abstract: Attention-based KV cache eviction (H2O and its descendants) compresses the memory-constrained state of a long-context model by ranking tokens on accumulated attention mass, treated here as signal energy, and keeping the heaviest.
By Soumil Mandal
The paper introduces Right In-Place (RiP) convolution, a memory‑efficient strategy that corrects and generalizes previous in‑place convolution formulations to arbitrary stride, dilation, padding, and rectangular kernels. RiP aligns each layer’s input and output within a shared workspace, enabling safe, row‑major access with minimal memory overhead. Experiments on 10,000 random layers and 84 layers from 25 architectures show no corruption, matching or improving on existing herringbone workspaces while reducing memory usage by up to 24.8% and lowering peak activation memory on Raspberry Pi Pico MCUs by 12.5–33.3% without affecting cycle counts.
By Opegbemi Matthias Busoye, Tolulope Matthew Busoye, Eghonghon-aye Eigbe
arXiv:2607. 07953v1 Announce Type: cross Abstract: Self-attention lets each token retrieve information from the full context, but its quadratic cost in sequence length limits training and inference at long context.
By Tommaso Cerruti, Tim Rieder, George Rowlands, Lingfeng Jin, Imanol Schlag
arXiv:2607. 18553v1 Announce Type: cross Abstract: Can a language model read the quality of ongoing computation, and can an external intervention turn that readout into better outcomes?
By Jan Kirin