CurveFP: Co-Designing Numerical Representation and Product Arithmetic for Language Models
Ye Qiao
cs.LG
Submitted: 2026-08-12
Updated: 2026-08-13
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMs
- Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling
- PIQA: Reasoning about Physical Commonsense in Natural Language
- Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
- LO-BCQ: Block Clustered Quantization for 4-bit (W4A4) LLM Inference
- The Llama 3 Herd of Models
- Additive Powers-of-Two Quantization: An Efficient Non-uniform Discretization for Neural Networks
- Pointer Sentinel Mixture Models
- FP8 Formats for Deep Learning
- Convolutional Neural Networks using Logarithmic Data Representation
- The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scale
- FASQ: Flexible Accelerated Subspace Quantization for Calibration-Free LLM Compression
- Compressive Transformers for Long-Range Sequence Modelling
- Microscaling Data Formats for Deep Learning
- WinoGrande: An Adversarial Winograd Schema Challenge at Scale
- Qwen3 Technical Report
- Falcon-H1: A Family of Hybrid-Head Language Models Redefining Efficiency and Performance
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks