#memory
12 briefs tagged #memory.
Paper tests memory transfer across language models
A new arXiv paper studies whether frozen external memory can move between model backbones.
Researchers target better visual navigation for embodied agents
Two papers propose memory and alignment methods to improve VLM-based navigation.
Researchers target memory failures in long-term LLM agents
New papers propose graph, segment and interference methods for maintaining agent memory.
Researchers propose ReMEMBER for dialogue summaries
The framework targets missing evidence in streaming dialogue summarization under fixed memory budgets.
New VLA papers target robotic manipulation gaps
Recent research focuses on memory, recovery data and cross-embodiment training for robot policies.
Researchers target agent memory limits
New papers argue LLM agents need versioning, decay and long-horizon memory beyond lookup.
Benchmarks test whether LLM agents can improve skills
New papers evaluate skill learning, retrieval and memory in self-evolving LLM agents.
Study finds LLMs fabricate user-profile claims
MirageBench reports pervasive over-inference across 12 personalized LLMs with memory.
Study finds stale memory risks in VLM agents
Dynamic FrozenLake tests show VLM agents can miss conflicts between stored spatial memory and observations.
GROVE adds layered memory for streaming video assistants
The training-free framework shares one video memory for reactive QA and proactive assistance.
New papers target long-horizon agent memory
Researchers propose harnesses and memory designs for agents that must work across extended tasks.
Wall Street weighs Micron as an AI chip beneficiary
Investors are looking at Micron as another public company tied to AI infrastructure demand.