Papers by Zicheng Li

7 papers
SCVQ: Sparse-Compensated Vector Quantization for Large Language Models (2026.acl-long)

Copied to clipboard

Challenge: Existing vector quantization methods incur inference overhead due to massive codebook storage and intensive index lookups.
Approach: They propose a framework for vector quantization that incorporates a salience-aware weighted K-means clustering scheme with symmetry constraints to reduce codebook size and indexing costs.
Outcome: The proposed framework achieves a perplexity of 5.78 on WikiText-2 for LLaMA-2-7B at 2-bit quantization while delivering a 1.4 speedup over existing baselines.
Word-level Prefix/Suffix Sense Detection: A Case Study on Negation Sense with Few-shot Learning (2023.findings-acl)

Copied to clipboard

Challenge: Morphological analysis is an important research issue in natural language processing . prefixes/suffixes are sometimes ambiguous, causing difficulty in detecting negation sense .
Approach: They propose a context-free morphological analysis task that deals with negation sense . they propose morphology task that uses input-augmentation prompts to train a model .
Outcome: The proposed approach is effective in detecting negation senses in a corpus of prefixes/suffixes . Empirical studies show that the proposed approach works in context-free mode .
Taming LLMs with Gradient Grouping (2025.acl-long)

Copied to clipboard

Challenge: a new study presents scaling with gradient grouping (SGG) the adaptive learning rate scaling approach is based on per-parameter statistics, which incurs memory overhead.
Approach: They propose an optimizer wrapper that improves adaptive learning rate estimation by dynamic grouping and group-specific scaling.
Outcome: The proposed algorithm improves learning rate estimation on diverse models with different model sizes and batch sizes.
Pre-trained Token-replaced Detection Model as Few-shot Learner (2022.coling-1)

Copied to clipboard

Challenge: Pre-trained masked language models have demonstrated remarkable few-shot learning ability . a novel approach to few- shot learning with pre-tried token-replaced detection models is proposed .
Approach: They propose a method to reformulate a classification or regression task as a token-replaced detection problem by using pre-trained token-based models.
Outcome: The proposed approach outperforms pre-trained masked language models in learning tasks . it can learn models with a few examples and generalize well from limited examples like humans .
Redundancy Principles for MLLMs Benchmarks (2025.acl-long)

Copied to clipboard

Challenge: Rapid growth of Multi-modality Large Language Models has led to significant redundancy among benchmarks.
Approach: They propose a framework to improve MLLM benchmark design by identifying redundancy at three levels: dimension, instance, and cross-benchmark redundancies.
Outcome: The proposed framework streamlines evaluations and enhances reliability.
FlightGPT: Towards Generalizable and Interpretable UAV Vision-and-Language Navigation with Vision-Language Models (2025.emnlp-main)

Copied to clipboard

Challenge: Existing methods for vision-and-language navigation struggle with insufficient multimodal fusion, weak generalization, and poor interpretability.
Approach: They propose a framework for UAV vision-and-language navigation that integrates natural language instructions with visual observations to improve multimodal fusion and interpretability.
Outcome: The proposed framework achieves state-of-the-art performance across all scenarios, with a 9.22% higher success rate than the strongest baseline in unseen environments.
NUWA-XL: Diffusion over Diffusion for eXtremely Long Video Generation (2023.acl-long)

Copied to clipboard

Challenge: Existing work generates long videos segment by segment sequentially, which is inefficient.
Approach: They propose a Diffusion over Difference architecture for eXtremely Long video generation.
Outcome: The proposed architecture reduces the average inference time from 7.55min to 26s (94.26%) and generates high-quality long videos with both global and local coherence.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations