Xinzhu Ma

SP-VLA: A Joint Model Scheduling and Token Pruning Approach for VLA Model Acceleration

PhysUniBench: A Multi-Modal Physics Reasoning Benchmark at Undergraduate Level

Point2Primitive: CAD Reconstruction from Point Cloud by Direct Primitive Prediction

CTCal: Rethinking Text-to-Image Diffusion Models via Cross-Timestep Self-Calibration

Venus-MAXWELL: Efficient Learning of Protein-Mutation Stability Landscapes using Protein Language Models

Revisiting Convolution Architecture in the Realm of DNA Foundation Models

COMET: Benchmark for Comprehensive Biological Multi-omics Evaluation Tasks and Language Models

Evaluating the Generalization Ability of Quantized LLMs: Benchmark, Analysis, and Toolbox

MindDETR: Beyond Semantics, Exploring Positional Cues from Brain Activity

EMS: Adaptive Evict-then-Merge Strategy for Head-wise KV Cache Compression Based on Global-Local Importance

3DAxisPrompt: Promoting the 3D Grounding and Reasoning in GPT-4o