collaborators

6 papers

cs.CL2026

CktFormalizer: Autoformalization of Natural Language into Circuit Representations

Jing Xiong, Qi Han, Chenchen Ding +4

LLMs can generate hardware descriptions from natural language specifications, but the resulting Verilog often contains width mismatches, combinational loops, and incomplete case lo…

cs.CL2026

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models

Hengyuan Zhang, Zhihao Zhang, Mingyang Wang +26

Mechanistic Interpretability (MI) has emerged as a vital approach to demystify the opaque decision-making of Large Language Models (LLMs). However, existing reviews primarily treat…

cs.LG2026

Beyond Outliers: A Data-Free Layer-wise Mixed-Precision Quantization Approach Driven by Numerical and Structural Dual-Sensitivity

Hengyuan Zhang, Xinrong Chen, Zunhai Su +10

Layer-wise mixed-precision quantization (LMPQ) enables effective compression under extreme low-bit settings by allocating higher precision to sensitive layers. However, existing me…

cs.CV2026

XStreamVGGT: Extremely Memory-Efficient Streaming Vision Geometry Grounded Transformer with KV Cache Compression

Zunhai Su, Weihao Ye, Hansen Feng +5

Learning-based 3D visual geometry models have significantly advanced with the advent of large-scale transformers. Among these, StreamVGGT leverages frame-wise causal attention to d…

cs.CL2026

DoPE: Denoising Rotary Position Embedding

Jing Xiong, Liyang Fan, Hui Shen +4

Positional encoding is essential for large language models (LLMs) to represent sequence order, yet recent studies show that Rotary Position Embedding (RoPE) can induce massive acti…

cs.CV2026

XStreamVGGT: Extremely Memory-Efficient Streaming Vision Geometry Grounded Transformer with KV Cache Compression

Zunhai Su, Weihao Ye, Hansen Feng +5

Learning-based 3D visual geometry models have benefited substantially from large-scale transformers. Among these, StreamVGGT leverages frame-wise causal attention for strong stream…