DharmaOCR models reach 0.925 and 0.911 extraction scores with 0.40% and 0.20% degeneration rates on a new benchmark covering printed, handwritten, and legal documents, outperforming open-source and commercial baselines via SFT plus DPO.
Gonzalez, Hao Zhang, and Ion Stoica
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
DuoAttention identifies retrieval heads requiring full KV cache and streaming heads using constant-length cache to reduce memory and latency in long-context LLM inference.
PathCal calibrates reasoning paths by type-aware soft rebalancing of reflection-marker logits at uncertain states, yielding better efficiency-performance trade-offs on six benchmarks.
Pre-trained MoE models exhibit up to 90% intra-expert activation sparsity that enables up to 2.5x faster MoE layer execution when exploited in the vLLM inference system.
MiniCPM-o 4.5 uses the Omni-Flow streaming framework to deliver real-time full-duplex omni-modal interaction with proactive behavior in a 9B model that approaches Gemini 2.5 Flash performance.
citing papers explorer
-
DharmaOCR: Specialized Small Language Models for Structured OCR that outperform Open-Source and Commercial Baselines
DharmaOCR models reach 0.925 and 0.911 extraction scores with 0.40% and 0.20% degeneration rates on a new benchmark covering printed, handwritten, and legal documents, outperforming open-source and commercial baselines via SFT plus DPO.
-
DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads
DuoAttention identifies retrieval heads requiring full KV cache and streaming heads using constant-length cache to reduce memory and latency in long-context LLM inference.
-
PathCal: State-Aware Reflection-Marker Calibration for Efficient Reasoning
PathCal calibrates reasoning paths by type-aware soft rebalancing of reflection-marker logits at uncertain states, yielding better efficiency-performance trade-offs on six benchmarks.
-
Uncovering Intra-expert Activation Sparsity for Efficient Mixture-of-Expert Model Execution
Pre-trained MoE models exhibit up to 90% intra-expert activation sparsity that enables up to 2.5x faster MoE layer execution when exploited in the vLLM inference system.
-
MiniCPM-o 4.5: Towards Real-Time Full-Duplex Omni-Modal Interaction
MiniCPM-o 4.5 uses the Omni-Flow streaming framework to deliver real-time full-duplex omni-modal interaction with proactive behavior in a 9B model that approaches Gemini 2.5 Flash performance.