collaborators

6 papers

cs.CV2026

LongCat-Next: Lexicalizing Modalities as Discrete Tokens

Meituan LongCat Team, Bin Xiao, Chao Wang +86

The prevailing Next-Token Prediction (NTP) paradigm has driven the success of large language models through discrete autoregressive modeling. However, contemporary multimodal syste…

cs.CL2025

VitaBench: Benchmarking LLM Agents with Versatile Interactive Tasks in Real-world Applications

Wei He, Yueqing Sun, Hongyan Hao +13

As LLM-based agents are increasingly deployed in real-life scenarios, existing benchmarks fail to capture their inherent complexity of handling extensive information, leveraging di…

cs.CV2025

PrefixKV: Adaptive Prefix KV Cache is What Vision Instruction-Following Models Need for Efficient Generation

Ao Wang, Hui Chen, Jiaxin Li +6

Recently, large vision-language models (LVLMs) have rapidly gained popularity for their strong generation and reasoning capabilities given diverse multimodal inputs. However, these…

cs.CL2025

MaskPrune: Mask-based LLM Pruning for Layer-wise Uniform Structures

Jiayu Qin, Jianchao Tan, Kefeng Zhang +2

The remarkable performance of large language models (LLMs) in various language tasks has attracted considerable attention. However, the ever-increasing size of these models present…

cs.CL2025

C2T: A Classifier-Based Tree Construction Method in Speculative Decoding

Feiye Huo, Jianchao Tan, Kefeng Zhang +2

The growing scale of Large Language Models (LLMs) has exacerbated inference latency and computational costs. Speculative decoding methods, which aim to mitigate these issues, often…

cs.CL2025

EPS-MoE: Expert Pipeline Scheduler for Cost-Efficient MoE Inference

Yulei Qian, Fengcun Li, Xiangyang Ji +4

The Mixture-of-Experts (MoE) model has emerged as a prominent architecture in the field of Large Language Models (LLMs), providing a better balance between model performance and co…