2 citations · 2 across the 9 of their papers we have counts for
10 papers
Persistent Visual Memory: Sustaining Perception for Deep Generation in LVLMs
Siyuan Huang, Xiaoye Qu, Yafu Li +6
While autoregressive Large Vision-Language Models (LVLMs) demonstrate remarkable proficiency in multimodal tasks, they face a "Visual Signal Dilution" phenomenon, where the accumul…
GEMS: Agent-Native Multimodal Generation with Memory and Skills
Zefeng He, Siyuan Huang, Xiaoye Qu +4
Recent multimodal generation models have achieved remarkable progress on general-purpose generation tasks, yet continue to struggle with complex instructions and specialized downst…
Pretraining with Token-Level Adaptive Latent Chain-of-Thought
Boyi Zeng, Yiqin Hao, He Li +8
Scaling large language models by increasing parameters and training data is increasingly constrained by limited high-quality corpora and rising communication costs. This work explo…
Training LLMs to be Better Text Embedders through Bidirectional Reconstruction
Chang Su, Dengliang Shi, Siyuan Huang +5
Large language models (LLMs) have increasingly been explored as powerful text embedders. Existing LLM-based text embedding approaches often leverage the embedding of the final toke…
PonderLM: Pretraining Language Models to Ponder in Continuous Space
Boyi Zeng, Shixiang Song, Siyuan Huang +6
Humans ponder before articulating complex sentence elements, enabling deeper cognitive processing through focused effort. In this work, we introduce this pondering process into lan…
Gumbel Reranking: Differentiable End-to-End Reranker Optimization
Siyuan Huang, Zhiyuan Ma, Jintao Du +5
RAG systems rely on rerankers to identify relevant documents. However, fine-tuning these models remains challenging due to the scarcity of annotated query-document pairs. Existing…
Mirror-Consistency: Harnessing Inconsistency in Majority Voting
Siyuan Huang, Zhiyuan Ma, Jintao Du +3
Self-Consistency, a widely-used decoding strategy, significantly boosts the reasoning capabilities of Large Language Models (LLMs). However, it depends on the plurality voting rule…
Cluster-wise Graph Transformer with Dual-granularity Kernelized Attention
Siyuan Huang, Yunchong Song, Jiayue Zhou +1
In the realm of graph learning, there is a category of methods that conceptualize graphs as hierarchical structures, utilizing node clustering to capture broader structural informa…
Graph Parsing Networks
Yunchong Song, Siyuan Huang, Xinbing Wang +2
Graph pooling compresses graph information into a compact representation. State-of-the-art graph pooling methods follow a hierarchical approach, which reduces the graph size step-b…
Tailoring Self-Attention for Graph via Rooted Subtrees
Siyuan Huang, Yunchong Song, Jiayue Zhou +1
Attention mechanisms have made significant strides in graph learning, yet they still exhibit notable limitations: local attention faces challenges in capturing long-range informati…