5 papers
Convergence Theory of Knowledge Distillation in Asynchronous P2P Gossip Learning Network
Lucas Qingyang Fang, Tiyao Liu, Jinhao Jing +4
Decentralized, serverless learning increasingly connects devices running different architectures, where the standard tool, decentralized SGD, is undefined as models with different…
Predictive Memory Localization: Forecasting Selective Intervention Paths from Internal Signals
Jinhao Jing, Tian Zeyu, Lucas Qingyang Fang +4
Activation steering turns localized representations into control directions, but localization alone does not reveal whether a direction has a selective operating regime. We introdu…
GeoSym127K: Scalable Symbolically-verifiable Synthesis for Multimodal Geometric Reasoning
Jinhao Jing, Zheng Ma, Jinwei Liang +9
Large Multimodal Models (LMMs) often struggle with geometric reasoning due to visual hallucinations and a lack of mathematically precise Chain-of-Thought (CoT) data. To address thi…
Efficient Data Selection for Multimodal Models via Incremental Optimization Utility
Jinhao Jing, Qiannian Zhao, Chao Huang +1
The scaling of Large Multimodal Models (LMMs) is constrained by the quality-quantity trade-off inherent in synthetic data. Previous approaches, such as LLM-as-a-Judge, have proven…
MineEvolve: Self-Evolution with Accumulated Knowledge for Long-Horizon Embodied Minecraft Agents
Zhengwei Xie, Zhisheng Chen, Ziyan Weng +7
Long-horizon embodied intelligence requires agents to improve through interaction, not merely to execute plans generated from static goals. A central challenge is therefore to tran…