38 papers
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…
OmniCoT: A Benchmark for Global and Multi-Step Panoramic Reasoning
Haocong He, Chenfei Liao, Zichen Wen +13
Multimodal Large Language Models (MLLMs) have demonstrated promising spatial reasoning capabilities, while these abilities remain underexplored in the emerging visual modality of p…
ICBCBench: An Industry Consortium Benchmark for Financial Deep Research
Weiya Li, Zhiwei Tang, Yizhou He +10
With the rapid advancement of Deep Research Agents in knowledge-intensive domains such as finance, establishing reliable and domain-aligned evaluation standards remains a critical…
LaPA: Length-Aware Prefix and Prompt Attention Augmentation for Long-Form Controllable Text Generation
Jiabing Yang, Yixiang Chen, Zichen Wen +8
Prefix-based methods have emerged as a promising paradigm for Controllable Text Generation (CTG) due to their parameter efficiency. However, while effective in short sequences, the…
Respecting Self-Uncertainty in On-Policy Self-Distillation for Efficient LLM Reasoning
Junlong Ke, Zichen Wen, Weijia Li +2
On-policy self-distillation trains a reasoning model on its own rollouts while a teacher, often the same model conditioned on privileged context, provides dense token-level supervi…
EvoStreaming: Your Offline Video Model Is a Natively Streaming Assistant
Zichen Wen, Boxue Yang, Junlong Ke +5
Streaming video understanding demands more than watching longer videos: assistants must decide when to speak in real time, balancing responsiveness against verbosity. Yet most vide…