4 citations · 15 across the 25 of their papers we have counts for
27 papers
SVoT: State-aware Visualization-of-Thought for Spatial Reasoning via Reinforcement Learning
Chao Lei, Yanbei Jiang, Markus Hiller +4
Spatial reasoning remains a challenge for Multimodal Large Language Models (MLLMs), as it requires reliable multi-hop inference over both intermediate states and state transitions.…
Mind the Perspective: Let's Reason Recursively for Theory of Mind
Chao Lei, Guang Hu, Meng Yang +2
Theory of Mind (ToM) reasoning requires inferring agents' beliefs from partial and asymmetric observations, which remains an open challenge for LLMs. Existing prompting-based appro…
Planning as Goal Recognition: Deriving Heuristics from Intention Models -- Extended Version
Giacomo Rosa, Jean Honorio, Nir Lipovetzky +1
Classical planning aims to find a sequence of actions, a plan, that maps a starting state into one of the goal states. If a trajectory appears to be leading to the goal, should we…
Generative AI-assisted Participatory Modeling in Socio-Environmental Planning under Deep Uncertainty
Zhihao Pei, Nir Lipovetzky, Angela M. Rojas-Arevalo +2
Socio-environmental planning under deep uncertainty requires researchers to identify and conceptualize problems before exploring policies and deploying plans. In practice and model…
From Reasoning to Generalization: Knowledge-Augmented LLMs for ARC Benchmark
Chao Lei, Nir Lipovetzky, Krista A. Ehinger +1
Recent reasoning-oriented LLMs have demonstrated strong performance on challenging tasks such as mathematics and science examinations. However, core cognitive faculties of human in…
State-Based Disassembly Planning
Chao Lei, Nir Lipovetzky, Krista A. Ehinger
It has been shown recently that physics-based simulation significantly enhances the disassembly capabilities of real-world assemblies with diverse 3D shapes and stringent motion co…
Chasing Progress, Not Perfection: Revisiting Strategies for End-to-End LLM Plan Generation
Sukai Huang, Trevor Cohn, Nir Lipovetzky
The capability of Large Language Models (LLMs) to plan remains a topic of debate. Some critics argue that strategies to boost LLMs' reasoning skills are ineffective in planning tas…
Where Common Knowledge Cannot Be Formed, Common Belief Can -- Planning with Multi-Agent Belief Using Group Justified Perspectives
Guang Hu, Tim Miller, Nir Lipovetzky
Epistemic planning is the sub-field of AI planning that focuses on changing knowledge and belief. It is important in both multi-agent domains where agents need to have knowledge/be…
Planning-Driven Programming: A Large Language Model Programming Workflow
Chao Lei, Yanchuan Chang, Nir Lipovetzky +1
The strong performance of large language models (LLMs) raises extensive discussion on their application to code generation. Recent research suggests continuous program refinements…
Planning in the Dark: LLM-Symbolic Planning Pipeline without Experts
Sukai Huang, Nir Lipovetzky, Trevor Cohn
Large Language Models (LLMs) have shown promise in solving natural language-described planning tasks, but their direct use often leads to inconsistent reasoning and hallucination.…
The Dark Side of Rich Rewards: Understanding and Mitigating Noise in VLM Rewards
Sukai Huang, Shu-Wei Liu, Nir Lipovetzky +1
While Vision-Language Models (VLMs) are increasingly used to generate reward signals for training embodied agents to follow instructions, our research reveals that agents guided by…
Count-based Novelty Exploration in Classical Planning
Giacomo Rosa, Nir Lipovetzky
Count-based exploration methods are widely employed to improve the exploratory behavior of learning agents over sequential decision problems. Meanwhile, Novelty search has achieved…
Human Goal Recognition as Bayesian Inference: Investigating the Impact of Actions, Timing, and Goal Solvability
Chenyuan Zhang, Charles Kemp, Nir Lipovetzky
Goal recognition is a fundamental cognitive process that enables individuals to infer intentions based on available cues. Current goal recognition algorithms often take only observ…
Generalized Planning for the Abstraction and Reasoning Corpus
Chao Lei, Nir Lipovetzky, Krista A. Ehinger
The Abstraction and Reasoning Corpus (ARC) is a general artificial intelligence benchmark that poses difficulties for pure machine learning methods due to its requirement for fluid…
Data-Driven Goal Recognition in Transhumeral Prostheses Using Process Mining Techniques
Zihang Su, Tianshi Yu, Nir Lipovetzky +6
A transhumeral prosthesis restores missing anatomical segments below the shoulder, including the hand. Active prostheses utilize real-valued, continuous sensor data to recognize pa…
Diverse, Top-k, and Top-Quality Planning Over Simulators
Lyndon Benke, Tim Miller, Michael Papasimeon +1
Diverse, top-k, and top-quality planning are concerned with the generation of sets of solutions to sequential decision problems. Previously this area has been the domain of classic…
Lifted Sequential Planning with Lazy Constraint Generation Solvers
Anubhav Singh, Miquel Ramirez, Nir Lipovetzky +1
This paper studies the possibilities made open by the use of Lazy Clause Generation (LCG) based approaches to Constraint Programming (CP) for tackling sequential classical planning…
Novelty and Lifted Helpful Actions in Generalized Planning
Chao Lei, Nir Lipovetzky, Krista A. Ehinger
It has been shown recently that successful techniques in classical planning, such as goal-oriented heuristics and landmarks, can improve the ability to compute planning programs fo…
A Reminder of its Brittleness: Language Reward Shaping May Hinder Learning for Instruction Following Agents
Sukai Huang, Nir Lipovetzky, Trevor Cohn
Teaching agents to follow complex written instructions has been an important yet elusive goal. One technique for enhancing learning efficiency is language reward shaping (LRS). Wit…
Sampling from Pre-Images to Learn Heuristic Functions for Classical Planning
Stefan O'Toole, Miquel Ramirez, Nir Lipovetzky +1
We introduce a new algorithm, Regression based Supervised Learning (RSL), for learning per instance Neural Network (NN) defined heuristic functions for classical planning problems.…
Planning for Novelty: Width-Based Algorithms for Common Problems in Control, Planning and Reinforcement Learning
Nir Lipovetzky
Width-based algorithms search for solutions through a general definition of state novelty. These algorithms have been shown to result in state-of-the-art performance in classical p…
Width-based Lookaheads with Learnt Base Policies and Heuristics Over the Atari-2600 Benchmark
Stefan O'Toole, Nir Lipovetzky, Miquel Ramirez +1
We propose new width-based planning and learning algorithms inspired from a careful analysis of the design decisions made by previous width-based planners. The algorithms are appli…
Approximate Novelty Search
Anubhav Singh, Nir Lipovetzky, Miquel Ramirez +1
Width-based search algorithms seek plans by prioritizing states according to a suitably defined measure of novelty, that maps states into a set of novelty categories. Space and tim…
Planimation
Gang Chen, Yi Ding, Hugo Edwards +9
Planimation is a modular and extensible open source framework to visualise sequential solutions of planning problems specified in PDDL. We introduce a preliminary declarative PDDL-…