Papers by Feiyang Li

7 papers
Efficient Inference for Large Vision-Language Models: Bottlenecks, Techniques, and Prospects (2026.findings-acl)

Copied to clipboard

Challenge: Large Vision-Language Models are hindered by a systemic efficiency barrier known as visual token dominance.
Approach: They propose a systematic taxonomy of efficiency techniques structured around the inference lifecycle . they examine visual encoding, prefilling, and decoding to understand bottlenecks .
Outcome: The proposed techniques reveal how upstream decisions dictate downstream bottlenecks . the proposed techniques include hybrid compression and modality-aware decoding .
Demystifying Synthetic Data in LLM Pre-training: A Systematic Study of Scaling Laws, Benefits, and Pitfalls (2025.emnlp-main)

Copied to clipboard

Challenge: a large-scale empirical study compares natural web data, diverse synthetic types, and mixtures of natural and synthetic data.
Approach: They conduct a large-scale empirical study on large-volume LLMs using a unified protocol and scaling laws.
Outcome: The proposed method is faster than pre-training on natural web data, the authors show . their results are consistent with previous studies on rephrased text and textbooks .
CoT-RAG: Integrating Chain of Thought and Retrieval-Augmented Generation to Enhance Reasoning in Large Language Models (2025.findings-emnlp)

Copied to clipboard

Challenge: Chain-of-thought reasoning has two key limitations: lack of reliability when solely relying on LLM-generated reasoning chains and interference from natural language reasoning steps with the models’ inference logic.
Approach: They propose a chain-of-thought reasoning framework with three key designs to address these issues.
Outcome: The proposed framework improves the performance of large language models on complex tasks by incorporating knowledge graphs and learnable knowledge case-aware RAG.
HybridKV: Hybrid KV Cache Compression for Efficient Multimodal Large Language Model Inference (2026.acl-long)

Copied to clipboard

Challenge: Multimodal Large Language Models (MLLMs) are hindered by the rapid growth of key–value (KV) caches.
Approach: They propose a hybrid KV cache compression framework that reduces KV memory by 7.9 and speeds up decoding by 1.52.
Outcome: Experiments on 11 multimodal benchmarks show that HYBRIDKV cuts KV cache memory by 7.9 and speeds up decoding by 1.52.
DeCoVec: Building Decoding Space based Task Vector for Large Language Models via In-Context Learning (2026.findings-acl)

Copied to clipboard

Challenge: Existing approaches to steering large language models require fine-tuning or manipulation of internal states, limiting their flexibility and scalability.
Approach: They propose a framework that constructs task vectors directly in the decoding space by leveraging in-context learning.
Outcome: The proposed framework outperforms standard few-shot baselines on TruthfulQA, Math-500, and AQUA-RAT with gains up to +5.50 accuracy.
Rhythm Controllable and Efficient Zero-Shot Voice Conversion via Shortcut Flow Matching (2025.acl-long)

Copied to clipboard

Challenge: Existing methods focus on disentangling speakers and content, while others focus on preserving the source's prosody.
Approach: They propose a rhythm-controllable and efficient zero-shot voice conversion model that transforms the source speaker’s timbre into an unseen one while retaining speech content.
Outcome: The proposed model adapts the linguistic content duration to the desired speaking style, facilitating the transfer of the target speaker’s rhythm.
TransFace: Unit-Based Audio-Visual Speech Synthesizer for Talking Head Translation (2024.findings-acl)

Copied to clipboard

Challenge: Existing methods for talking head translation rely on cascading, resulting in delays and cascadic errors.
Approach: They propose a model for talking head translation, TransFace, which can translate audio-visual speech into audio-visual speech in other languages.
Outcome: The proposed model can translate audio-visual speech into audio-visual speech in other languages.

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