Latent Reasoning in Continuous Space for Unified Multimodal Models Paper • 2610.42149 • Published 19 days ago • 45
Scaling Agentic Data for Long-Horizon Terminal Intelligence Paper • 2610.13166 • Published Oct 9 • 129
Disaggregated Quantization: Specializing LLM Prefill and Decode Paper • 2609.26333 • Published Sep 22 • 83
DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression Paper • 2609.19969 • Published Sep 17 • 209
Macaron-V1: Towards Open Continual Learning with Self-Improvement and Mixture-of-LoRA Paper • 2608.09819 • Published Aug 10 • 113
FinanceComplexQA: Benchmarking Agentic Reasoning on Industrial-grade Financial Documents Paper • 2607.19238 • Published Jul 21 • 9
Accelerating RL Post-Training Rollouts via System-Integrated Speculative Decoding Paper • 2604.26779 • Published Apr 29 • 15
SEED: Self-Evolving On-Policy Distillation for Agentic Reinforcement Learning Paper • 2607.14777 • Published Jul 16 • 104
Jet-Long: Efficient Long-Context Extension with Dynamic Bifocal RoPE Paper • 2607.07740 • Published Jul 8 • 24
Long-Horizon-Terminal-Bench: Testing the Limits of Agents on Long-Horizon Terminal Tasks with Dense Reward-Based Grading Paper • 2607.08964 • Published Jul 9 • 73
MonkeyOCRv2: A Visual-Text Foundation Model for Document AI Paper • 2607.11562 • Published Jul 13 • 36
Hierarchical Sparse Attention Done Right: Toward Infinite Context Modeling Paper • 2607.02980 • Published Jul 3 • 82