25 papers
TAFFY: A Task-Adaptive Tabular Foundation Model with In-Context Diversity
Zijian Li, Xiangchen Song, Gongxu Luo +7
Recent progress in tabular foundation models suggests that training on synthetic tasks can substantially improve in-context learning capabilities, with overall performance largely…
Video2World: Benchmarking Coding Agents for Interactive World Modeling from Embodied Videos
Jinzhou Tang, Zijun Zhang, Jing Yang +10
Building interactive simulators from real-world observations is a promising way to scale embodied data, but current pipelines still rely heavily on manual environment construction…
TimeBraid: Unifying Time Series and Language for Understanding and Forecasting
Xinyue Wang, Jiacheng Pang, Kun Zhou +7
We present TimeBraid, a series of unified time-series and language models that align pretrained language models and pretrained time-series foundation models through interleaved glo…
Causally Debiased Latent Action Model for Embodied Action-Conditioned World Models
Yufan Wei, Kun Zhou, Lingjun Mao +9
Action-conditioned world models (ACWMs) aim to simulate future observations conditioned on embodied actions. However, learning controllable ACWMs requires large-scale action-labele…
Learning Task-Sufficient World Models by Synergizing Agentic Exploration and Structured Modeling
Fan Feng, Yujia Zheng, Minghao Fu +5
Learning and planning in imagination using world models provides an effective paradigm for training agents for decision-making. However, existing approaches often rely on high-dime…
ReFPO: Reflow Regularization for Flow Matching Policy Gradients
Ge Wang, Yibo Peng, Fan Feng +10
We present Reflow-regularized Flow Matching Policy Gradients (ReFPO), a simple online RL method that adds explicit Reflow regularization to FPO for efficient flow-based control. We…
MimicIK: Real-Time Generative Inverse Kinematics from Teleoperation with FK Consistency
Jiahao Yang, Shenhao Yan, Fan Feng +5
Inverse kinematics (IK) remains a critical bottleneck for real-time robot manipulation. Classical numerical solvers achieve high geometric precision but often suffer from discontin…
Acting While Understanding: Asynchronous Semantic-Action Decoupling for Real-Time Vision-Language-Action Models
Shenhao Yan, Ge Wang, Qi Liu +7
Vision-Language-Action models (VLAs) have demonstrated strong task understanding and generalization in robotic manipulation, yet the high computational cost of full-model inference…
Elastic Queries Reinforcement Learning: Self-Aware Policy Execution for VLA Models
Ge Wang, Xinyu Tan, Xiang Li +11
Vision-language-action (VLA) models are powerful action generators for robot manipulation, but they are typically executed with fixed inference and replanning schedules. This rigid…
Learning Object Manipulation from Scratch via Contrastive Interaction
Tongle Shen, Caleb Chuck, Fan Feng +1
Contrastive Reinforcement Learning (CRL) has seen recent success in a wide variety of goal-conditioned robotics tasks by learning structured representations of the dynamics. Howeve…
World Action Verifier: Self-Improving World Models via Forward-Inverse Asymmetry
Yuejiang Liu, Fan Feng, Lingjing Kong +6
General-purpose world models promise scalable policy evaluation, optimization, and planning, yet achieving the required level of robustness remains challenging. Unlike policy learn…
Back to Parsimonious Latents: Learning Task-Centric World Models from Visual Foundations
Minghao Fu, Fan Feng, Nicklas Hansen +1
World models enable agents to predict future dynamics conditioned on actions, making the choice of latent representation central to planning and control. Such representations are o…
CHI-Bench: Can AI Agents Automate End-to-End, Long-Horizon, Policy-Rich Healthcare Workflows?
Haolin Chen, Deon Metelski, Leon Qi +30
End-to-end automation of realistic healthcare operations stresses three capabilities underrepresented in current benchmarks: policy density, decisions must be grounded in a large l…
Ada-Diffuser: Latent-Aware Adaptive Diffusion for Decision-Making
Fan Feng, Selena Ge, Minghao Fu +6
Recent work has framed decision-making as a sequence modeling problem using generative models such as diffusion models. Although promising, these approaches often overlook latent f…
SCAR: Self-Supervised Continuous Action Representation Learning
Hongjia Liu, Fan Feng, Minghao Fu +3
Despite the central role of action in embodied intelligence, learning transferable action representations from visual transitions remains a fundamental challenge, particularly when…
From Generalist to Specialist Representation
Yujia Zheng, Fan Feng, Yuke Li +3
Given a generalist model, learning a task-relevant specialist representation is fundamental for downstream applications. Identifiability, the asymptotic guarantee of recovering the…
KoopmanFlow: Spectrally Decoupled Generative Control Policy via Koopman Structural Bias
Chengsi Yao, Ge Wang, Kai Kang +9
Generative Control Policies (GCPs) show immense promise in robotic manipulation but struggle to simultaneously model stable global motions and high-frequency local corrections. Whi…
DreamSAC: Learning Hamiltonian World Models via Symmetry Exploration
Jinzhou Tang, Fan Feng, Minghao Fu +3
Learned world models excel at interpolative generalization but fail at extrapolative generalization to novel physical properties. This limitation arises because they learn statisti…
Factored Causal Representation Learning for Robust Reward Modeling in RLHF
Yupei Yang, Lin Yang, Wanxi Deng +5
A reliable reward model is essential for aligning large language models with human preferences through reinforcement learning from human feedback. However, standard reward models a…
FRoD: Full-Rank Efficient Fine-Tuning with Rotational Degrees for Fast Convergence
Guoan Wan, Tianyu Chen, Fangzheng Feng +2
Parameter-efficient fine-tuning (PEFT) methods have emerged as a practical solution for adapting large foundation models to downstream tasks, reducing computational and memory cost…
Learning Interactive World Model for Object-Centric Reinforcement Learning
Fan Feng, Phillip Lippe, Sara Magliacane
Agents that understand objects and their interactions can learn policies that are more robust and transferable. However, most object-centric RL methods factor state by individual o…
Online Time Series Forecasting with Theoretical Guarantees
Zijian Li, Changze Zhou, Minghao Fu +6
This paper is concerned with online time series forecasting, where unknown distribution shifts occur over time, i.e., latent variables influence the mapping from historical to futu…
Hallucination-Resistant Relation Extraction via Dependency-Aware Sentence Simplification and Two-tiered Hierarchical Refinement
Yupei Yang, Fan Feng, Lin Yang +5
Relation extraction (RE) enables the construction of structured knowledge for many downstream applications. While large language models (LLMs) have shown great promise in this task…
Null Counterfactual Factor Interactions for Goal-Conditioned Reinforcement Learning
Caleb Chuck, Fan Feng, Carl Qi +4
Hindsight relabeling is a powerful tool for overcoming sparsity in goal-conditioned reinforcement learning (GCRL), especially in certain domains such as navigation and locomotion.…