Papers by Anhao Zhao
LLM as Effective Streaming Processor: Bridging Streaming-Batch Mismatches with Group Position Encoding (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for adapting LLMs to streaming rely on expensive re-encoding or limited scalability. |
| Approach: | They propose a group position encoding paradigm built on batch architectures to enhance consistency between streaming and batch modes. |
| Outcome: | The proposed method outperforms existing methods on cross-lingual and cross-modal tasks. |
VisiPruner: Decoding Discontinuous Cross-Modal Dynamics for Efficient Multimodal LLMs (2025.emnlp-main)
Copied to clipboard
| Challenge: | Multimodal Large Language Models (MLLMs) suffer from significant computational overhead due to the quadratic growth of attention computations with the number of multimodal tokens. |
| Approach: | They propose a training-free pruning framework that prunes multimodal tokens without a trained pruning method. |
| Outcome: | The proposed pruning framework outperforms existing token pruning methods and generalizes across diverse MLLMs. |
Unveiling In-Context Learning: A Coordinate System to Understand Its Working Mechanism (2024.emnlp-main)
Copied to clipboard
| Challenge: | Large language models exhibit remarkable in-context learning (ICL) capabilities, but the underlying working mechanism of ICL remains unclear. |
| Approach: | They propose a Two-Dimensional Coordinate System that unifies both views into a systematic framework that explains the behavior of ICL through two orthogonal variables: whether similar examples are presented in the demonstrations and whether LLMs can recognize the task. |
| Outcome: | The proposed method can interpret ICL for generation tasks effectively. |