5 papers
LARC: Low-Rank Adaptive Residual Connections for Learning in Frozen Models
Junyi Zou, Avrova Donz
Low-Rank Adaptive Residual Connections (LARC) give a frozen model a compact numerical state that can learn from feedback. The map adds a low-rank correction to a hidden rep…
MMLA: Memory-Mediated Learning Architecture for Predictive Dual-State Adaptation
Junyi Zou, Avrova Donz
Memory-Mediated Learning Architecture (MMLA) separates slow base parameters theta, a bounded numerical policy carrier Phi, and a bounded authoritative memory M. Predictive Dual-Sta…
SpatialGrammar: A Domain-Specific Language for LLM-Based 3D Indoor Scene Generation
Song Tang, Kaiyong Zhao, Yuliang Li +5
Automatically generating interactive 3D indoor scenes from natural language is crucial for virtual reality, gaming, and embodied AI. However, existing LLM-based approaches often su…
Instruction-Tuned, but Not More Verifiable Instruction-Following: A Cross-Task Diagnosis for LoRA Adapters
Junyi Zou
Adapters are often selected and deployed based on nominal labels (e.g., instruction-tuned), which implicitly suggest what capability improves after adaptation. We test whether nomi…
Adapter Merging Reactivates Latent Reasoning Traces: A Mechanism Analysis
Junyi Zou
Large language models fine-tuned via a two-stage pipeline (domain adaptation followed by instruction alignment) can exhibit non-trivial interference after adapter merging, includin…