2 citations · 3 across the 15 of their papers we have counts for
17 papers
D-Quant: Driftable Entropy Coding for KV Cache Quantization
Yi Su, Hong Liu, Guanghua Yu +1
The KV cache has become a major bottleneck in deploying LLMs, as its memory footprint grows linearly with sequence length and batch size, imposing substantial pressure on both memo…
Bole: Efficient Tree Speculation for Hybrid-Attention Language Models
Li Wang, Yi Su, Xiabao Wu +9
Hybrid-attention large language models combine full attention with recurrent linear attention to reduce long-context inference costs, yet their autoregressive decoding remains memo…
PIVOT: Efficient Query-Group Indexing for Token-Level Sparse Attention
Hong Liu, Yuan Cheng, Lin Niu +5
Token-level sparse attention, as implemented by DeepSeek Sparse Attention (DSA) in production systems, makes the downstream attention efficient but shifts the bottleneck to the ind…
LongFlow: Efficient KV Cache Compression for Reasoning Models
Yi Su, Zhenxu Tian, Dan Qiao +3
Recent reasoning models such as OpenAI-o1 and DeepSeek-R1 have shown strong performance on complex tasks including mathematical reasoning and code generation. However, this perform…
Where Matters More Than What: Decoding-aligned KV Cache Compression via Position-aware Pseudo Queries
Zhenxu Tian, Yi Su, Juntao Li +1
The Key-Value (KV) cache is crucial for efficient Large Language Models (LLMs) inference, but excessively long contexts drastically increase KV cache memory footprint. Existing KV…
Quantized Inference for OneRec-V2
Yi Su, Xinchen Luo, Hongtao Cheng +7
Quantized inference has demonstrated substantial system-level benefits in large language models while preserving model quality. In contrast, reliably applying low-precision quantiz…
OpenOneRec Technical Report
Guorui Zhou, Honghui Bao, Jiaming Huang +44
While the OneRec series has successfully unified the fragmented recommendation pipeline into an end-to-end generative framework, a significant gap remains between recommendation sy…
: Attention-Aware Accurate KV Cache Fusion for Fast Large Language Model Serving
Yuechi Zhou, Yi Su, Jianxin Zhang +5
Large language models (LLMs) have demonstrated strong capabilities in processing long contexts, enabling them to tackle tasks involving long textual inputs such as multi-turn conve…
OneRec-Think: In-Text Reasoning for Generative Recommendation
Zhanyu Liu, Shiyao Wang, Xingmei Wang +23
The powerful generative capacity of Large Language Models (LLMs) has instigated a paradigm shift in recommendation. However, existing generative models (e.g., OneRec) operate as im…
CaliDrop: KV Cache Compression with Calibration
Yi Su, Quantong Qiu, Yuechi Zhou +6
Large Language Models (LLMs) require substantial computational resources during generation. While the Key-Value (KV) cache significantly accelerates this process by storing attenti…
OneRec-V2 Technical Report
Guorui Zhou, Hengrui Hu, Hongtao Cheng +72
Recent breakthroughs in generative AI have transformed recommender systems through end-to-end generation. OneRec reformulates recommendation as an autoregressive generation task, a…
Accurate KV Cache Quantization with Outlier Tokens Tracing
Yi Su, Yuechi Zhou, Quantong Qiu +6
The impressive capabilities of Large Language Models (LLMs) come at the cost of substantial computational resources during deployment. While KV Cache can significantly reduce recom…
Crossing the Reward Bridge: Expanding RL with Verifiable Rewards Across Diverse Domains
Yi Su, Dian Yu, Linfeng Song +5
Reinforcement learning with verifiable rewards (RLVR) has demonstrated significant success in enhancing mathematical reasoning and coding performance of large language models (LLMs…
Demonstration Augmentation for Zero-shot In-context Learning
Yi Su, Yunpeng Tai, Yixin Ji +3
Large Language Models (LLMs) have demonstrated an impressive capability known as In-context Learning (ICL), which enables them to acquire knowledge from textual demonstrations with…
OPT-Tree: Speculative Decoding with Adaptive Draft Tree Structure
Jikai Wang, Yi Su, Juntao Li +5
Autoregressive language models demonstrate excellent performance in various scenarios. However, the inference efficiency is limited by its one-step-one-word generation mode, which…
OpenBA-V2: Reaching 77.3% High Compression Ratio with Fast Multi-Stage Pruning
Dan Qiao, Yi Su, Pinzheng Wang +18
Large Language Models (LLMs) have played an important role in many fields due to their powerful capabilities.However, their massive number of parameters leads to high deployment re…
Test-Time Adaptation with Perturbation Consistency Learning
Yi Su, Yixin Ji, Juntao Li +2
Currently, pre-trained language models (PLMs) do not cope well with the distribution shift problem, resulting in models trained on the training set failing in real test scenarios.…