arXiv
AutoMem: Automated Learning of Memory as a Cognitive Skill
Memory expertise is a learned skill: knowing what to encode, when to retrieve, and how to organize knowledge--a capac...
🤖 AI 前沿资讯
每天自动聚合 AI 领域最新动态
arXiv
Language-Critique Imitation Learning from Suboptimal Demonstrations
Prior work on imitation learning from suboptimal demonstrations typically relies on compressed supervision signals su...
arXiv
Measuring the Gap Between Human and LLM Research Ideas
LLMs are increasingly used to brainstorm research ideas, but existing evaluations mostly judge individual ideas by no...
HuggingFace
Valdi: Value Diffusion World Models
World models can enable Model Predictive Control (MPC), but this requires dynamics prediction that is both fast enoug...
HuggingFace
ABot-M0.5: Unified Mobility-and-Manipulation World Action Model
Mobile manipulation is a key capability for general-purpose robots, yet remains challenging for current embodied lear...
HuggingFace
Domain Arithmetic: One-Shot VLA Adaptation under Environmental Shifts
Vision-Language-Action (VLA) models often fail to perform the same learned tasks under environmental shifts, such as ...
HuggingFace
CausalMix: Data Mixture as Causal Inference for Language Model Training
In Large Language Model (LLM) training, data mixing plays a pivotal role in determining model performance. Recent met...
HuggingFace
AutoTrainess: Teaching Language Models to Improve Language Models Autonomously
Training language models (LMs) remains a highly human-intensive process, even as frontier language model agents becom...
HuggingFace
TurboServe: Serving Streaming Video Generation Efficiently and Economically
Streaming video generation is emerging as a new serving workload in which users interact with long-lived sessions tha...
HuggingFace
Perceive-to-Reason: Decoupling Perception and Reasoning for Fine-Grained Visual Reasoning
Fine-grained visual reasoning remains challenging for vision-language models, especially when small but critical visu...
HuggingFace
The State-Prediction Separation Hypothesis
Transformers use the same forward computation stream to both predict the next token and store useful state for future...
HuggingFace
When LLMs Read Tables Carelessly: Measuring and Reducing Data Referencing Errors
While large language models (LLMs) perform well on table tasks, they still make data referencing errors (DREs), i.e.,...