Papers Skill Generalization
“Skill Generalization” 태그가 달린 논문 13편 · 필터 해제
Learning Globally Reusable Skills for Coding Agents
Automated skill evolution enables Large Language Model (LLM) agents to continuously improve without expensive retraining. However, existing approaches typically treat skill evolution as a sequence of local updates, overl…
Skill GeneralizationSPECTRA: Context-Conditioned Spectral Movement Primitives for Robot Skill Generalization
Robot imitation learning for manipulation should preserve demonstrated task geometry while producing dynamically admissible robot motions. Existing pipelines often learn task-dependent trajectories and impose execution l…
Skill GeneralizationAnalytic Concept-Centric Memory for Agentic Embodied Manipulation
Long-horizon embodied manipulation requires agents to remember persistent objects, track changing scene states, and reuse prior interaction knowledge. However, existing agent memories are often stored as unstructured his…
Skill GeneralizationJobMatchAI An Intelligent Job Matching Platform Using Knowledge Graphs, Semantic Search and Explainable AI
Recruiters and job seekers rely on search systems to navigate labor markets, making candidate matching engines critical for hiring outcomes. Most systems act as keyword filters, failing to handle skill synonyms and nonli…
Skill GeneralizationKnowledge GraphsLessMimic: Long-Horizon Humanoid Interaction with Unified Distance Field Representations
Humanoid robots that autonomously interact with physical environments over extended horizons represent a central goal of embodied intelligence. Existing approaches rely on reference motions or task-specific rewards, tigh…
Reinforcement LearningSkill GeneralizationTReF-6: Inferring Task-Relevant Frames from a Single Demonstration for One-Shot Skill Generalization
Robots often struggle to generalize from a single demonstration due to the lack of a transferable and interpretable spatial representation. In this work, we introduce TReF-6, a method that infers a simplified, abstracted…
Skill GeneralizationA Taxonomy of Transcendence
Although language models are trained to mimic humans, the resulting systems display capabilities beyond the scope of any one person. To understand this phenomenon, we use a controlled setting to identify properties of th…
Skill GeneralizationSkill Generalization with Verbs
It is imperative that robots can understand natural language commands issued by humans. Such commands typically contain verbs that signify what action should be performed on a given object and that are applicable to many…
ObjectSkill GeneralizationAgentBank: Towards Generalized LLM Agents via Fine-Tuning on 50000+ Interaction Trajectories
Fine-tuning on agent-environment interaction trajectory data holds significant promise for surfacing generalized agent capabilities in open-source large language models (LLMs). In this work, we introduce AgentBank, by fa…
Skill GeneralizationLaying the Foundation First? Investigating the Generalization from Atomic Skills to Complex Reasoning Tasks
Current language models have demonstrated their capability to develop basic reasoning, but struggle in more complicated reasoning tasks that require a combination of atomic skills, such as math word problem requiring ski…
MathSkill GeneralizationRobot Skill Generalization via Keypoint Integrated Soft Actor-Critic Gaussian Mixture Models
A long-standing challenge for a robotic manipulation system operating in real-world scenarios is adapting and generalizing its acquired motor skills to unseen environments. We tackle this challenge employing hybrid skill…
Skill GeneralizationZero-shot GeneralizationA Generalist Agent
Inspired by progress in large-scale language modeling, we apply a similar approach towards building a single generalist agent beyond the realm of text outputs. The agent, which we refer to as Gato, works as a multi-modal…
Language ModelingLanguage ModellingSkill GeneralizationSkill MasteryBeyond Pick-and-Place: Tackling Robotic Stacking of Diverse Shapes
We study the problem of robotic stacking with objects of complex geometry. We propose a challenging and diverse set of such objects that was carefully designed to require strategies beyond a simple "pick-and-place" solut…
Offline RLReinforcement Learning (RL)Skill GeneralizationSkill Mastery