collaborators

6 papers

cs.LG2026

BUDDY: BUdget-Driven DYnamic Depth Routing for Adaptive Large Language Model Inference

Yuhua Zhou, Shaoqi Yu, Shichao Weng +4

Large language models (LLMs) incur high inference cost due to their depth and parameter scale. Depth pruning can reduce latency by skipping redundant Transformer blocks, but existi…

cs.CL2026

From 0-Order Selection to 2-Order Judgment: Combinatorial Hardening Exposes Compositional Failures in Frontier LLMs

Hanmeng Liu, Shichao Weng, Xiulai Liu +3

Multiple-choice reasoning benchmarks face dual challenges: rapid saturation from advancing models and data contamination that undermines static evaluations. Ad-hoc hardening method…

cs.SE2026

CoRE: A Fine-Grained Code Reasoning Benchmark Beyond Output Prediction

Jun Gao, Yun Peng, Qian Qiao +6

Despite strong performance on code generation tasks, it remains unclear whether large language models (LLMs) genuinely reason about code execution. Existing code reasoning benchmar…

cs.AI2026

GeoSketch: A Neural-Symbolic Approach to Geometric Multimodal Reasoning with Auxiliary Line Construction and Affine Transformation

Shichao Weng, Zhiqiang Wang, Yuhua Zhou +5

Geometric Problem Solving (GPS) poses a unique challenge for Multimodal Large Language Models (MLLMs), requiring not only the joint interpretation of text and diagrams but also ite…

cs.LG2026

Balancing Fidelity and Plasticity: Aligning Mixed-Precision Fine-Tuning with Linguistic Hierarchies

Changhai Zhou, Shiyang Zhang, Yuhua Zhou +5

Deploying and fine-tuning Large Language Models (LLMs) on resource-constrained edge devices requires navigating a strict trade-off between memory footprint and task performance. Wh…

cs.LG2024

AutoMixQ: Self-Adjusting Quantization for High Performance Memory-Efficient Fine-Tuning

Changhai Zhou, Shiyang Zhang, Yuhua Zhou +2

Fine-tuning large language models (LLMs) under resource constraints is a significant challenge in deep learning. Low-Rank Adaptation (LoRA), pruning, and quantization are all effec…