6 citations · 6 across the 7 of their papers we have counts for
7 papers
MemDelta: Controlled Baselines and Hidden Confounds in Agent Memory Evaluation
Kuan Wang
Agent memory systems are increasingly evaluated against RAG and full-context baselines, but reported gains often mix changes in the memory method with changes in the language model…
MemLeak: Diagnosing Information Leaks in Multimodal Agent Memory
Kuan Wang, Chao Zhang
When a multimodal AI agent is asked to forget a fact, current memory systems usually delete the text entry and report success. We find that the fact can remain recoverable from ret…
What Matters in Learning from Large-Scale Datasets for Robot Manipulation
Vaibhav Saxena, Matthew Bronars, Nadun Ranawaka Arachchige +5
Imitation learning from large multi-task demonstration datasets has emerged as a promising path for building generally-capable robots. As a result, 1000s of hours have been spent o…
RNR: Teaching Large Language Models to Follow Roles and Rules
Kuan Wang, Alexander Bukharin, Haoming Jiang +9
Instruction fine-tuning (IFT) elicits instruction following capabilities and steers the behavior of large language models (LLMs) via supervised learning. However, existing models t…
VIMI: Grounding Video Generation through Multi-modal Instruction
Yuwei Fang, Willi Menapace, Aliaksandr Siarohin +5
Existing text-to-video diffusion models rely solely on text-only encoders for their pretraining. This limitation stems from the absence of large-scale multimodal prompt video datas…
ARL2: Aligning Retrievers for Black-box Large Language Models via Self-guided Adaptive Relevance Labeling
Lingxi Zhang, Yue Yu, Kuan Wang +1
Retrieval-augmented generation enhances large language models (LLMs) by incorporating relevant information from external knowledge sources. This enables LLMs to adapt to specific d…
Adapting LLM Agents with Universal Feedback in Communication
Kuan Wang, Yadong Lu, Michael Santacroce +3
Recent advances in large language models (LLMs) have demonstrated potential for LLM agents. To facilitate the training for these agents with both linguistic feedback and non-lingui…