Profiles2023-2026
Dawei Yang
Houmo AI
16Papers
8Last author
21Unique co-authors
0First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers16
- BWLA: Breaking the Barrier of W1AX Post-Training Quantization for LLMsAuthor 3 of 3ACL 2026 · 3 citations
- CAR-SAM: Cross-Attention Reconstruction for Post-Training Quantization of the Segment Anything ModelAuthor 4 of 4CVPR 2026 · 2 citations
- NLI : Non-uniform Linear Interpolation Approximation of Nonlinear Operations for Efficient LLMs InferenceAuthor 7 of 7ICLR 2026 · 2 citations
- DLLMQuant: A Post-Training Quantization Framework Tailored for Diffusion-Based Large Language ModelsAuthor 3 of 3ICML 2026
- FQ-PETR: Fully Quantized Position Embedding Transformation for Multi-View 3D Object DetectionAuthor 6 of 6AAAI 2026
- OTARo: Once Tuning for All Precisions Toward Robust On-Device LLMsAuthor 3 of 5AAAI 2026
- TWLA: Achieving Ternary Weights and Low-Bit Activations for LLMs via Post-Training QuantizationAuthor 6 of 6ICML 2026
- VAEVQ: Enhancing Discrete Visual Tokenization Through Variational ModelingAuthor 4 of 4AAAI 2026
- MQuant: Unleashing the Inference Potential of Multimodal Large Language Models via Static QuantizationAuthor 3 of 10ACM MM 2025 · 11 citations
- BBAL: A Bidirectional Block Floating Point-Based Quantisation Accelerator for Large Language ModelsAuthor 8 of 9DAC 2025 · 5 citations
- RSAVQ: Riemannian Sensitivity-Aware Vector Quantization for Large Language ModelsAuthor 4 of 5NeurIPS 2025 · 2 citations
- NVR: Vector Runahead on NPUs for Sparse Memory AccessAuthor 13 of 14DAC 2025 · 1 citation
- Pushing the Limits of BFP on Narrow Precision LLM InferenceAuthor 5 of 6AAAI 2025 · 1 citation
- MoEQuant: Enhancing Quantization for Mixture-of-Experts Large Language Models via Expert-Balanced Sampling and Affinity GuidanceAuthor 3 of 8ICML 2025
- RWKVQuant: Quantizing the RWKV Family with Proxy Guided Hybrid of Scalar and Vector QuantizationAuthor 9 of 9ICML 2025
- PD-Quant: Post-Training Quantization Based on Prediction Difference MetricAuthor 4 of 6CVPR 2023
