6 papers
From Self-Attention to Connection Laplacian: A Unified Operator View of Transformers
Binbin Lin, Wei Chen, Yalun Li +3
Self-attention is a ubiquitous primitive in modern sequence models, yet its operator-level geometry is only partially understood. We view a token sequence as a vector field over th…
InfoQuant: Shaping Activation Distributions for Low-Bit LLM Quantization
Ke Li, Dong An, Xiaoling Zang +6
Low-bit activation quantization remains a major bottleneck in efficient large language model (LLM) deployment. The difficulty is not only that activations contain outliers, but tha…
HeteroCache: A Dynamic Retrieval Approach to Heterogeneous KV Cache Compression for Long-Context LLM Inference
Zhiyuan Shi, Qibo Qiu, Feng Xue +5
The linear memory growth of the KV cache poses a significant bottleneck for LLM inference in long-context tasks. Existing static compression methods often fail to preserve globally…
Improving Complex Reasoning with Dynamic Prompt Corruption: A soft prompt Optimization Approach
Sinan Fan, Liang Xie, Chen Shen +7
Prompt-tuning (PT) for large language models (LLMs) can facilitate the performance on various conventional NLP tasks with significantly fewer trainable parameters. However, our inv…
Depth Any Video with Scalable Synthetic Data
Honghui Yang, Di Huang, Wei Yin +6
Video depth estimation has long been hindered by the scarcity of consistent and scalable ground truth data, leading to inconsistent and unreliable results. In this paper, we introd…
SciPIP: An LLM-based Scientific Paper Idea Proposer
Wenxiao Wang, Lihui Gu, Liye Zhang +7
The rapid advancement of large language models (LLMs) has opened new possibilities for automating the proposal of innovative scientific ideas. This process involves two key phases:…