Asia
Adaptive Online Replanning with Diffusion Models Siyuan Zhou
Given a previously generated plan, how do we effectively regenerate a new plan?
Generating Code World Models with Large Language Models Guided by Monte Carlo Tree Search
Given the description of an environment and a task, we use an LLM guided by the GIF-MCTS method to iteratively generate and refine a candidate CWM. The candidate's correctness is evaluated by checking if it correctly
Weakly Coupled Deep Q-Networks
"subagents," one for each subproblem, and then combine their solutions to establish
Leveraging partial stragglers within gradient coding
Large scale distributed learning is the workhorse of modern day machine learning (ML) algorithms.
LayoutPrompter: Awaken the Design Ability of Large Language Models
In this work, we propose Layout-Prompter, which leverages large language models (LLMs) to address the above problems through in-context learning.
Training Energy-Based Normalizing Flow with Score-Matching Objectives Chen-Hao Chao 1, Wei-Fang Sun 1,2, Yen-Chang Hsu
Our experimental results demonstrate that this approach significantly improves the training efficiency as compared to maximum likelihood training.
ETO: Efficient Transformer-based Local Feature Matching by Organizing Multiple Homography Hypotheses
During the coarse matching phase, we organize multiple homography hypotheses to approximate continuous matches. Each hypothesis encompasses several features to be matched, significantly reducing the number of features that require enhancement via transformers.
Front-door Adjustment Beyond Markov Equivalence with Limited Graph Knowledge
However, the exact formula for front-door adjustment depends on the structure of the graph, which is difficult to learn in practice.
Infusing Synthetic Data with Real-World Patterns for Zero-Shot Material State Segmentation
Minerals in rocks, sediment in soil, dust on surfaces, infection on leaves, stains on fabrics, and foam in liquids are some of these almost infinite numbers of states and patterns.