Yuan Feng

yuanfengustc

https://ffy0.github.io/yuanfeng.github.io/

AI & ML interests

LLM Long Context, MLLM

Recent Activity

authored a paper about 14 hours ago

VisionWeave: Weaving Elastic Visual Representations as a Native Capability of MLLMs

authored a paper about 14 hours ago

OmniVChat: Synthesizing, Benchmarking, and Training for Native Audio-Visual Dialogue

authored a paper about 14 hours ago

Identify Critical KV Cache in LLM Inference from an Output Perturbation Perspective

View all activity

Organizations

None yet

upvoted a paper about 18 hours ago

VisionWeave: Weaving Elastic Visual Representations as a Native Capability of MLLMs

Paper • 2610.07987 • Published 4 days ago • 2

upvoted a paper 19 days ago

OmniVChat: Synthesizing, Benchmarking, and Training for Native Audio-Visual Dialogue

Paper • 2609.21465 • Published 22 days ago • 151

upvoted 2 papers about 1 month ago

Qwen-Drive-1.0: An Initial Step towards a Vision-Language Foundation Model for Autonomous Driving

Paper • 2609.00111 • Published Aug 31 • 316

Agentic Artifact Creation: Systems, Evaluation, Principles, and Opportunities

Paper • 2608.28122 • Published Aug 28 • 66

upvoted a paper 4 months ago

Taming the Fragility of KV Cache Eviction in LLM Inference

Paper • 2510.13334 • Published Oct 15, 2025 • 1

upvoted a paper 10 months ago

MMGR: Multi-Modal Generative Reasoning

Paper • 2512.14691 • Published Dec 16, 2025 • 121

upvoted an article over 1 year ago

Article

Mastering Long Contexts in LLMs with KVPress

nvidia

•

Jan 23, 2025

• 76