5 papers
Action with Visual Primitives
Weilong Guo, Yuchen Wang, Renping Zhou +5
Vision-Language-Action (VLA) models have emerged as a promising paradigm for generalist robotic manipulation. A common design in current architectures maps language instructions an…
Interference-Aware Multi-Task Unlearning
Ying-Hua Huang, Rui Fang, Hsi-Wen Chen +1
Machine unlearning aims to remove the contribution of designated training data from a trained model while preserving performance on the remaining data. Existing work mainly focuses…
LoopQ: Quantization for Recursive Transformers
Rui Fang, Hsi-Wen Chen, Ming-Syan Chen
Looped language models (LoopLMs) improve parameter efficiency by recursively reusing Transformer blocks, enabling deeper computation under a fixed model size. However, this reuse m…
Amortized-Precision Quantization for Early-Exit Vision Transformers
Rui Fang, Hsi-Wen Chen, Ming-Syan Chen
Vision Transformers (ViTs) achieve strong performance across vision tasks, yet their deployment with low-precision early exiting remains fragile. Existing quantization methods assu…
KV Admission: Learning What to Write for Efficient Long-Context Inference
Yen-Chieh Huang, Pi-Cheng Hsiu, Rui Fang +1
Long-context LLM inference is bottlenecked by the quadratic attention complexity and linear KV cache growth. Prior approaches mitigate this via post-hoc selection or eviction but o…