Papers by Yusong Wang
Causal2Vec: Improving Decoder-only LLMs as Embedding Models through a Contextual Token (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods modify attention mechanism to be bidirectional, undermining LLMs’ ability to extract semantic information acquired during pre-training. |
| Approach: | They propose a general-purpose embedding model that pre-encodes input text into a single Contextual token and then prepends it to the LLM's input sequence. |
| Outcome: | The proposed model improves performance of decoder-only large language models without altering their architectures or introducing significant computational overhead. |
Joyful: Joint Modality Fusion and Graph Contrastive Learning for Multimoda Emotion Recognition (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing graph-based methods fail to depict global contextual features and local diverse unimodal features in a dialogue. |
| Approach: | They propose a method for joint modality fusion and graph contrastive learning for multimodal emotion recognition using a multimodal fusion mechanism and a graph contrastative learning framework. |
| Outcome: | The proposed method improves multimodal emotion recognition on unbalanced and small-scale emotional datasets. |
BMAM: Brain-inspired Multi-Agent Memory Framework (2026.findings-acl)
Copied to clipboard
| Challenge: | Language-model-based agents operating over extended interactions face persistent challenges in preserving temporally grounded information and maintaining behavioral consistency across sessions. |
| Approach: | They propose a general-purpose memory architecture that decomposes agent memory into six components that operate at complementary time scales. |
| Outcome: | BMAM outperforms memory-augmented baselines on LoCoMo benchmarks with 78.45% accuracy . a targeted refinement of the temporal-trigger heuristics raises LongMemEval multi-session accuracy from 45.2% to 56.4%. |
LAMBDA: Large Language Model-Based Data Augmentation for Multi-Modal Machine Translation (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Multi-modal machine translation methods are underperforming compared to pre-trained models due to lack of triplet training data. |
| Approach: | They propose a multi-modal machine translation method that integrates images and visual modality to enhance language understanding. |
| Outcome: | The proposed method can enrich the original samples and expand the dataset without requiring external images and text. |