Search Results for author:
Found 12 papers, 5 papers with code
ThinkEdit: Interpretable Weight Editing to Mitigate Overly Short Thinking in Reasoning Models
Recent studies have shown that Large Language Models (LLMs) augmented with chain-of-thought (CoT) reasoning demonstrate impressive problem-solving abilities.
Interpretable Generative Models through Post-hoc Concept Bottlenecks
Concept bottleneck models (CBM) aim to produce inherently interpretable models that rely on human-understandable concepts for their predictions.
Humanoid Policy ~ Human Policy
The state-action space of HAT is unified for both humans and humanoid robots and can be differentiably retargeted to robot actions.
Movable Antenna Aided Multiuser Communications: Antenna Position Optimization Based on Statistical Channel Information
To address this issue, we propose in this paper a new approach to optimize the MA positions based on the users' statistical CSI over a large timescale.
Integrating LMM Planners and 3D Skill Policies for Generalizable Manipulation
In aligning high-level and low-level control for robot actions, language embeddings representing the high-level policy are jointly attended with the 3D feature field in the 3D transformer for seamless integration.
Power Measurement Enabled Channel Autocorrelation Matrix Estimation for IRS-Assisted Wireless Communication
Prior works on IRS CSI acquisition mainly estimate IRS-cascaded channels based on the extra pilot signals received at the users/base station (BS) with time-varying IRS reflections, which, however, needs to modify the existing channel training/estimation protocols of wireless systems.
VLG-CBM: Training Concept Bottleneck Models with Vision-Language Guidance
Concept Bottleneck Models (CBMs) provide interpretable prediction by introducing an intermediate Concept Bottleneck Layer (CBL), which encodes human-understandable concepts to explain models' decision.
Provably Robust Conformal Prediction with Improved Efficiency
To address these limitations, we first propose a novel framework called RSCP+ to provide provable robustness guarantee in evaluation, which fixes the issues in the original RSCP method.
DNAct: Diffusion Guided Multi-Task 3D Policy Learning
To learn a generalizable multi-task policy with few demonstrations, the pre-training phase of DNAct leverages neural rendering to distill 2D semantic features from foundation models such as Stable Diffusion to a 3D space, which provides a comprehensive semantic understanding regarding the scene.
Channel Autocorrelation Estimation for IRS-Aided Wireless Communications Based on Power Measurements
Intelligent reflecting surface (IRS) can bring significant performance enhancement for wireless communication systems by reconfiguring wireless channels via passive signal reflection.
GNFactor: Multi-Task Real Robot Learning with Generalizable Neural Feature Fields
To incorporate semantics in 3D, the reconstruction module utilizes a vision-language foundation model ($\textit{e. g.}$, Stable Diffusion) to distill rich semantic information into the deep 3D voxel.
Entropy-stable discontinuous Galerkin difference methods for hyperbolic conservation laws
The results suggest that DGD and SBP solution errors are similar for the same number of degrees of freedom.
Numerical Analysis Numerical Analysis 65M60, 65M70, 65M12
