Showing cs.CLShow all
2 papers · 1 filter
cs.CL2026
Kimi K3: Open Frontier Intelligence
Kimi Team, Tongtong Bai, Yifan Bai +398
We introduce Kimi K3, a 2.8T parameter Mixture-of-Experts model with 104 billion activated parameters, native vision capabilities, and a 1-million-token context window. Kimi K3 is…
cs.CL2025
Systematic Reward Gap Optimization for Mitigating VLM Hallucinations
Lehan He, Zeren Chen, Zhelun Shi +3
The success of Direct Preference Optimization (DPO) in mitigating hallucinations in Vision Language Models (VLMs) critically hinges on the true reward gaps within preference pairs.…