works on

From the 1 of 6 linked papers with an AI index.

collaborators

6 papers

cs.CL2026

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…

cs.CL2026

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…

cs.LG2026

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…

cs.DC2026

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…

cs.LG2025

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…

cs.LG2025

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…