Lei Wang

The DeepSeek-V4.1-Flash model, a multimodal Mixture-of-Experts model with 552B backbone parameters and support for contexts of up to one million tokens, is introduced, substantially improving cost efficiency for agentic workloads and pushing the limits of KV cache compression.

M2Heat is introduced, a physics-inspired framework that investigates multimodal fusion through the lens of heat conduction and indicates the potential of heat-conduction-guided neural operators for efficient and interpretable RS multimodal fusion.

Structuring supervision around disease-specific relationships leads to better radiology report generation than simply scaling up model size.

Iterative refinement in radiology report generation can significantly enhance accuracy, with DRRG outperforming traditional methods despite using a smaller model.

Traditional frame-wise evaluation fails to capture the nuances of speech-driven facial motion, but a new sequence-alignment approach reveals clearer trade-offs in generative model performance.

Removing misleading reasoning from answer-correct CoT traces can drastically enhance fine-tuning performance in LLMs.

Quantizing rollouts in LLM RL pipelines introduces a training-inference gap that QaRL closes, leading to +5.5 performance on math problems.