6 papers
Crystal-KV: Efficient KV Cache Management for Chain-of-Thought LLMs via Answer-First Principle
Zihan Wang, Cheng Tang, Lei Gong +5
Chain-of-Thought (CoT) reasoning in large language models (LLMs) significantly improves accuracy on complex tasks, yet incurs excessive memory overhead due to the long think-stage…
Virtual Width Networks
Seed, Baisheng Li, Banggu Wu +115
We introduce Virtual Width Networks (VWN), a framework that delivers the benefits of wider representations without incurring the quadratic cost of increasing the hidden size. VWN d…
Kimi K2: Open Agentic Intelligence
Kimi Team, Yifan Bai, Yiping Bao +195
We introduce Kimi K2, a Mixture-of-Experts (MoE) large language model with 32 billion activated parameters and 1 trillion total parameters. We propose the MuonClip optimizer, which…
ReVeal: Self-Evolving Code Agents via Reliable Self-Verification
Yiyang Jin, Kunzhao Xu, Hang Li +4
Reinforcement learning with verifiable rewards (RLVR) has advanced the reasoning capabilities of large language models. However, existing methods rely solely on outcome rewards, wi…
MILLION: Mastering Long-Context LLM Inference Via Outlier-Immunized KV Product Quantization
Zongwu Wang, Peng Xu, Fangxin Liu +7
Large language models (LLMs) are increasingly utilized for complex tasks requiring longer context lengths, with some models supporting up to 128K or 1M tokens. This trend, however,…
Kimi k1.5: Scaling Reinforcement Learning with LLMs
Kimi Team, Angang Du, Bofei Gao +93
Language model pretraining with next token prediction has proved effective for scaling compute but is limited to the amount of available training data. Scaling reinforcement learni…