From the 1 of 6 linked papers with an AI index.
6 papers
Steering Instruction Hierarchies at Inference Time
Siqi Zeng, Sewoong Lee, Han Zhao +1
The paper proposes V‑Steer, a training‑free method that modifies cached value vectors during inference to ensure higher‑priority prompts (like system prompts) override lower‑priori…
ELF: Embedded Language Flows
Keya Hu, Linlu Qiu, Yiyang Lu +5
Diffusion and flow-based models have become the de facto approaches for generating continuous data, e.g., in domains such as images and videos. Their success has attracted growing…
Task Vector Bases: A Unified and Scalable Framework for Compressed Task Arithmetic
Siqi Zeng, Yifei He, Meitong Liu +5
Task arithmetic, representing downstream tasks through linear operations on task vectors, has emerged as a simple yet powerful paradigm for transferring knowledge across diverse se…
AB-Sparse: Sparse Attention with Adaptive Block Size for Accurate and Efficient Long-Context Inference
Di Liu, Ruitian Wang, Chen Chen +6
As large language models scale to longer contexts, loading the growing KV cache during attention computation becomes a critical bottleneck. Previous work has shown that attention c…
When LRP Diverges from Leave-One-Out in Transformers
Weiqiu You, Siqi Zeng, Yao-Hung Hubert Tsai +2
Leave-One-Out (LOO) provides an intuitive measure of feature importance but is computationally prohibitive. While Layer-Wise Relevance Propagation (LRP) offers a potentially effici…
Learning Structured Representations by Embedding Class Hierarchy with Fast Optimal Transport
Siqi Zeng, Sixian Du, Makoto Yamada +1
To embed structured knowledge within labels into feature representations, prior work [Zeng et al., 2022] proposed to use the Cophenetic Correlation Coefficient (CPCC) as a regulari…