{"total":19,"rows":[{"id":"2502.02631","title":"ParetoQ: Improving Scaling Laws in Extremely Low-bit LLM Quantization","created":"2025-02-04","cited_by_count":46,"area":null},{"id":"2505.14669","title":"Quartet: Native FP4 Training Can Be Optimal for Large Language Models","created":"2025-05-20","cited_by_count":39,"area":null},{"id":"2502.05003","title":"QuEST: Stable Training of LLMs with 1-Bit Weights and Activations","created":"2025-02-07","cited_by_count":22,"area":null},{"id":"2408.06003","title":"LUT Tensor Core: A Software-Hardware Co-Design for LUT-Based Low-Bit LLM Inference","created":"2024-08-12","cited_by_count":18,"area":null},{"id":"2411.17691","title":"Low-Bit Quantization Favors Undertrained LLMs: Scaling Laws for Quantized LLMs with 100T Training Tokens","created":"2024-11-26","cited_by_count":18,"area":null},{"id":"2502.16440","title":"Compression Scaling Laws:Unifying Sparsity and Quantization","created":"2025-02-23","cited_by_count":11,"area":null},{"id":"2606.26650","title":"CAT-Q: Cost-efficient and Accurate Ternary Quantization for LLMs","created":"2026-06-25","cited_by_count":6,"area":null},{"id":"2604.07888","title":"Bit-by-Bit: Progressive QAT Strategy with Outlier Channel Splitting for Stable Low-Bit LLMs","created":"2026-04-09","cited_by_count":3,"area":null},{"id":"2512.06443","title":"Vec-LUT: Vector Table Lookup for Parallel Ultra-Low-Bit LLM Inference on Edge Devices","created":"2025-12-06","cited_by_count":2,"area":null},{"id":"2506.23025","title":"Spectra 1.1: Scaling Laws and Efficient Inference for Ternary Language Models","created":"2025-06-28","cited_by_count":1,"area":null},{"id":"2508.06753","title":"Pushing the Envelope of LLM Inference with Ultra-Low-Bit Quantized Models","created":"2025-08-08","cited_by_count":1,"area":null},{"id":"2601.07086","title":"XBTorch: A Unified Framework for Modeling and Co-Design of Crossbar-Based Deep Learning Accelerators","created":"2026-01-11","cited_by_count":1,"area":null},{"id":"2604.25183","title":"Hardware Generation and Exploration of Lookup Table-Based Accelerators for 1.58-bit LLM Inference","created":"2026-04-28","cited_by_count":1,"area":null},{"id":"2605.13859","title":"BiSpikCLM: A Spiking Language Model integrating Softmax-Free Spiking Attention and Spike-Aware Alignment Distillation","created":"2026-04-14","cited_by_count":1,"area":null},{"id":"2609.16338","title":"Breaking the 1.58-bit Barrier for Ternary LLMs","created":"2026-09-14","cited_by_count":1,"area":null},{"id":"2601.20745","title":"HESTIA: A Hessian-Guided Differentiable Quantization-Aware Training Framework for Extremely Low-Bit LLMs","created":"2026-01-28","cited_by_count":0,"area":null},{"id":"2603.25813","title":"MAGNET: Autonomous Expert Model Generation via Decentralized Autoresearch and BitNet Training","created":"2026-03-26","cited_by_count":0,"area":null},{"id":"2609.29397","title":"Baseline Shape Decides the Verdict: A Controlled Re-Examination of Ternary Language Models at 60K Parameters","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2609.32902","title":"Linger and Lose: Knowledge Collapse in Low-Bit Language Models","created":"2026-09-26","cited_by_count":0,"area":null}],"next_cursor":null}