6 papers
Maximum Likelihood Reinforcement Learning
Fahim Tajwar, Guanning Zeng, Yueer Zhou +7
Reinforcement learning (RL) is the method of choice for training models in setups where the objective function can only be evaluated by sampling from the model. Our key observation…
Amory: Building Coherent Narrative-Driven Agent Memory through Agentic Reasoning
Yue Zhou, Xiaobo Guo, Belhassen Bayar +1
Long-term conversational agents face a fundamental scalability challenge as interactions extend over time: repeatedly processing entire conversation histories becomes computational…
Resolving Conflicts in Lifelong Learning via Aligning Updates in Subspaces
Yueer Zhou, Yichen Wu, Ying Wei
Low-Rank Adaptation (LoRA) enables efficient Continual Learning but often suffers from catastrophic forgetting due to destructive interference between tasks. Our analysis reveals t…
MotionStreamer: Streaming Motion Generation via Diffusion-based Autoregressive Model in Causal Latent Space
Lixing Xiao, Shunlin Lu, Huaijin Pi +7
This paper addresses the challenge of text-conditioned streaming motion generation, which requires us to predict the next-step human pose based on variable-length historical motion…
ConfProBench: A Confidence Evaluation Benchmark for MLLM-Based Process Judges
Yue Zhou, Yi Chang, Yuan Wu
Reasoning is a critical capability of multimodal large language models (MLLMs) for solving complex multimodal tasks, and judging the correctness of reasoning steps is crucial for i…
Mixup Model Merge: Enhancing Model Merging Performance through Randomized Linear Interpolation
Yue Zhou, Yi Chang, Yuan Wu
Model merging aims to integrate multiple task-specific models into a unified model that inherits the capabilities of the task-specific models, without additional training. Existing…