Kimi K2.5: Visual Agentic Intelligence
Paper β’ 2602.02276 β’ Published β’ 268
Haoning Wu, Teo PRO
teowu
AI & ML interests
Lead of Q-Future: https://github.com/Q-Future. I love MLLMs/LMMs/LVLMs/(any names you call them). Part of two great MoE VLMs as core contributors: Kimi-VL & Aria. Living and Cooking in Singapore Now.
Recent Activity
liked a model 8 days ago
moonshotai/Kimi-K2.6 liked a dataset 21 days ago
ianncity/KIMI-K2.5-1000000x upvoted a paper about 2 months ago
Reasoning Models Struggle to Control their Chains of ThoughtOrganizations
authored a
paper 3 months ago
authored a
paper 11 months ago
authored 3
papers about 1 year ago
authored 4
papers over 1 year ago
Adaptive Image Quality Assessment via Teaching Large Multimodal Model to Compare
Paper β’ 2405.19298 β’ Published
LIME: Less Is More for MLLM Evaluation
Paper β’ 2409.06851 β’ Published β’ 2
VideoAutoArena: An Automated Arena for Evaluating Large Multimodal Models in Video Analysis through User Simulation
Paper β’ 2411.13281 β’ Published β’ 21
Aria: An Open Multimodal Native Mixture-of-Experts Model
Paper β’ 2410.05993 β’ Published β’ 111
authored a
paper almost 2 years ago
authored a
paper about 2 years ago
authored 4
papers over 2 years ago
Q-Align: Teaching LMMs for Visual Scoring via Discrete Text-Defined Levels
Paper β’ 2312.17090 β’ Published β’ 4
Q-Instruct: Improving Low-level Visual Abilities for Multi-modality Foundation Models
Paper β’ 2311.06783 β’ Published β’ 28
Q-Bench: A Benchmark for General-Purpose Foundation Models on Low-level Vision
Paper β’ 2309.14181 β’ Published β’ 2
FAST-VQA: Efficient End-to-end Video Quality Assessment with Fragment Sampling
Paper β’ 2207.02595 β’ Published