The study re‑examines a reported advantage of a routed ternary (1.58‑bit) language model over a full‑precision transformer at 60K parameters. By running controlled experiments with multiple seeds and a fixed training recipe, the authors find that the apparent benefit largely stems from the choice of baseline model shape rather than the ternary architecture itself. While the routed model does outperform other shapes at a larger 130M‑byte budget, its advantage diminishes when a plain gated diagonal‑SSM block is used, and the ternary penalty varies with architecture and quantization details.
By Gautam Veldanda
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
arXiv:2606. 27759v1 Announce Type: new Abstract: Training binary neural networks (BNNs) from scratch is dominated by the straight-through estimator (STE), whose forward/backward mismatch produces severe accuracy degradation as networks deepen.
By Evan Gibson Smith, Bashima Islam
arXiv:2608. 06177v1 Announce Type: new Abstract: Binary neural networks are very attractive for constrained deployment, enabling small footprint and low-power inference.
By Quentin Luquet de Saint-Germain, Massil Ait Abdeslam, Jean Pierre David
arXiv:2607. 19623v1 Announce Type: cross Abstract: We characterize per-bit-position fault sensitivity in ML inference across 16 workloads -- spanning transformer-based models and attention-free CNNs -- and across three floating-point formats.
By Muhammad Husnain Mubarik, Karthik Mohan Kumar, Pedro Antonio Pena, Keshavan Varadarajan, Kunal Tyagi
arXiv:2607. 01984v1 Announce Type: cross Abstract: Newer lightweight convolutional neural networks are often presented as improving predictive performance and deployment efficiency, but such claims require controlled evaluation.
By Tasnim Shahriar
arXiv:2609.37887v1 Announce Type: new
Abstract: Activation and key-value cache precision change what a quantized language model computes without altering its stored weights. Direct weight-code bounds...
By Arian Eamaz, Mojtaba Soltanalian
arXiv:2605.06240v2 Announce Type: replace-cross
Abstract: Forward-Forward (FF) training lets each layer learn from a local goodness criterion. In cumulative-goodness variants, later layers can inheri...
By Amirhossein Yousefiramandi
arXiv:2606. 02608v1 Announce Type: new Abstract: We study a Marchenko--Pastur (MP) random-matrix approach to pruning deep neural networks with very small post-pruning fine-tuning budgets.
By Leonid Berlyand, Theo Bourdais, Houman Owhad, Yitzchak Shmalo
arXiv:2610.02598v1 Announce Type: new
Abstract: Deploying LLMs on consumer-grade GPUs with insufficient memory to hold their weights can result in prohibitively slow inference, because decoding repea...
By JuneHyung Kim, Sankeerth Durvasula, Nandita Vijaykumar
arXiv:2607. 27275v1 Announce Type: new Abstract: Post-training quantization to 4-bit weights is widely reported to be nearly lossless.
By Jiwon Jang, Kisu Yang, Heuiseok Lim, Hyunwoo Park
FORGE is a forward‑only test‑time adaptation technique designed for integer‑only vision models running on microcontrollers. It restores batch‑normalization statistics after BN folding by re‑normalizing each convolution’s per‑channel output using only forward‑pass estimates, enabling adaptation on deployed, folded integer models. The method achieves accuracy gains comparable to gradient‑based TENT, requires adapting only a few layers, works with single‑sample streaming, and has been validated on an ESP32‑S3 with minimal energy and latency overhead.
By Muhammad Rehan, Haider Ali, Muhammad Ali Munir, Moaz Amjad