16 papers
TransMem: Transforming Hidden States into Memory for Large Language Models
Haodong Lei, Junming Liu, Yirong Chen +4
Large language model (LLM) agents increasingly operate over long interaction histories, where effective reasoning requires identifying and exploiting task-relevant evidence distrib…
Mosaic: Data-Free Knowledge Distillation via Mixture-of-Experts for Heterogeneous Distributed Environments
Junming Liu, Yanting Gao, Yuqi Li +6
Federated Learning (FL) is a decentralized machine learning paradigm that enables clients to collaboratively train models while preserving data privacy. However, the coexistence of…
MemVerse: Multimodal Memory for Lifelong Learning Agents
Junming Liu, Yifei Sun, Weihua Cheng +11
Despite rapid progress in large-scale language and vision models, AI agents still suffer from a fundamental limitation: they cannot remember. Without reliable memory, agents catast…
Self-Evolving Spatial Reasoning in Vision Language Models via Geometric Logic Consistency
Junming Liu, Yuqi Li, Yifei Sun +4
Vision-Language Models (VLMs) have made striking progress, yet their spatial reasoning remains fragile: models that answer an original input correctly can still fail under paired t…
MemCoT: Test-Time Scaling through Memory-Driven Chain-of-Thought
Haodong Lei, Junming Liu, Yirong Chen +2
Large Language Models (LLMs) still suffer from severe hallucinations and catastrophic forgetting during causal reasoning over massive, fragmented long contexts. Existing memory mec…
Domain-Adaptive Model Merging Across Disconnected Modes
Junming Liu, Yusen Zhang, Rongchao Zhang +2
Learning across domains is challenging when data cannot be centralized due to privacy or heterogeneity, which limits the ability to train a single comprehensive model. Model mergin…