CIERA: Cross-Iteration Exponent Reuse for Lossless Allgather in Sharded MoE Training
为解决MoE模型训练中Allgather操作导致的通信开销问题，提出CIERA方法，通过跨迭代指数重用来实现无损压缩，显著提高训练速度。
0 citationsRead paper
Selected work
Representative Papers
Pro-Router: Token-Aware Progressive Model Routing with Adaptive Edge-Cloud Collaboration for Efficient Multimodal LLM Inference
为解决多模态大语言模型实时部署和成本效益问题，提出Pro-Router方法，通过令牌感知渐进式模型路由与自适应边缘-云协作提高推理效率。
0 citationsRead paper
What Do World Models Learn in RL? Probing Latent Representations in Learned Environment Simulators
This study investigates how world models in reinforcement learning acquire structured representations of environmental states. Focusing on the IRIS and DIAMOND architectures trained on Atari games, the work presents the first systematic evaluation of their latent representations through a combination of linear and nonlinear probing, causal interventions, attention head analysis, and multi-baseline token ablation experiments. The findings reveal that both models learn approximately linear encodings of key state variables—such as object positions and game scores—and that these representations are effectively leveraged by downstream policies. Furthermore, IRIS exhibits spatially specific attention heads, indicating a mechanism that selectively focuses on localized regions of the environment, thereby offering insight into how such models attend to and process structured visual information.
0 citationsRead paper
Stabilizing Iterative Self-Training with Verified Reasoning via Symbolic Recursive Self-Alignment
Recursive self-training is prone to recursive drift, mode collapse, and performance degradation due to the accumulation of intermediate reasoning errors. This work proposes the Neural-Symbolic Recursive Self-Alignment (NSRSA) framework, which introduces a symbolic verification mechanism at the level of individual reasoning steps for the first time. By integrating SymPy for arithmetic validation, logical consistency checking, and enforcement of domain-specific constraints, NSRSA effectively filters out samples with correct answers but flawed reasoning processes. Leveraging preference pairs constructed via Direct Preference Optimization (DPO), NSRSA rejects 34% of erroneous reasoning samples over five rounds of self-training on GSM8K using the Qwen3-4B-Thinking model, improving the model’s accuracy in judging reasoning correctness from 46% to 63%. This significantly enhances the reliability and stability of recursive self-training.
0 citationsRead paper
Recent publications
Latest Papers
CIERA: Cross-Iteration Exponent Reuse for Lossless Allgather in Sharded MoE Training
为解决MoE模型训练中Allgather操作导致的通信开销问题，提出CIERA方法，通过跨迭代指数重用来实现无损压缩，显著提高训练速度。
0 citationsRead paper
Pro-Router: Token-Aware Progressive Model Routing with Adaptive Edge-Cloud Collaboration for Efficient Multimodal LLM Inference
为解决多模态大语言模型实时部署和成本效益问题，提出Pro-Router方法，通过令牌感知渐进式模型路由与自适应边缘-云协作提高推理效率。
0 citationsRead paper
What Do World Models Learn in RL? Probing Latent Representations in Learned Environment Simulators
This study investigates how world models in reinforcement learning acquire structured representations of environmental states. Focusing on the IRIS and DIAMOND architectures trained on Atari games, the work presents the first systematic evaluation of their latent representations through a combination of linear and nonlinear probing, causal interventions, attention head analysis, and multi-baseline token ablation experiments. The findings reveal that both models learn approximately linear encodings of key state variables—such as object positions and game scores—and that these representations are effectively leveraged by downstream policies. Furthermore, IRIS exhibits spatially specific attention heads, indicating a mechanism that selectively focuses on localized regions of the environment, thereby offering insight into how such models attend to and process structured visual information.
0 citationsRead paper
Stabilizing Iterative Self-Training with Verified Reasoning via Symbolic Recursive Self-Alignment
Recursive self-training is prone to recursive drift, mode collapse, and performance degradation due to the accumulation of intermediate reasoning errors. This work proposes the Neural-Symbolic Recursive Self-Alignment (NSRSA) framework, which introduces a symbolic verification mechanism at the level of individual reasoning steps for the first time. By integrating SymPy for arithmetic validation, logical consistency checking, and enforcement of domain-specific constraints, NSRSA effectively filters out samples with correct answers but flawed reasoning processes. Leveraging preference pairs constructed via Direct Preference Optimization (DPO), NSRSA rejects 34% of erroneous reasoning samples over five rounds of self-training on GSM8K using the Qwen3-4B-Thinking model, improving the model’s accuracy in judging reasoning correctness from 46% to 63%. This significantly enhances the reliability and stability of recursive self-training.
0 citationsRead paper